Scylla's Band v2-20261006
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- README.md +14 -14
- SHA256SUMS.json +44 -272
- coreai/assets/fixed_references.json +0 -0
- coreai/assets/g2p/export_config.json +0 -33
- coreai/assets/g2p/language_map.json +0 -47
- coreai/assets/g2p/normalization.json +0 -40
- coreai/assets/g2p/phoneme_dict.json +0 -9
- coreai/assets/g2p/pronunciation_overrides.json +0 -4
- coreai/assets/g2p/tokenizer.json +0 -517
- coreai/assets/languages.json +0 -30
- coreai/assets/phone_vocab.json +0 -111
- coreai/assets/voices.json +0 -42
- coreai/coreai/duration_predictor.aimodel/main.hash +0 -1
- coreai/coreai/duration_predictor.aimodel/main.mlirb +0 -3
- coreai/coreai/duration_predictor.aimodel/metadata.json +0 -5
- coreai/coreai/g2p.aimodel/main.hash +0 -1
- coreai/coreai/g2p.aimodel/main.mlirb +0 -3
- coreai/coreai/g2p.aimodel/metadata.json +0 -5
- coreai/coreai/vector_context_encoder.aimodel/main.hash +0 -1
- coreai/coreai/vector_context_encoder.aimodel/main.mlirb +0 -3
- coreai/coreai/vector_context_encoder.aimodel/metadata.json +0 -5
- coreai/coreai/vector_estimator.aimodel/main.hash +0 -1
- coreai/coreai/vector_estimator.aimodel/main.mlirb +0 -3
- coreai/coreai/vector_estimator.aimodel/metadata.json +0 -5
- coreai/coreai/vocoder.aimodel/main.hash +0 -1
- coreai/coreai/vocoder.aimodel/main.mlirb +0 -3
- coreai/coreai/vocoder.aimodel/metadata.json +0 -5
- coreai/manifest.json +0 -1003
- coreml/assets/fixed_references.json +0 -0
- coreml/assets/g2p/export_config.json +0 -33
- coreml/assets/g2p/language_map.json +0 -47
- coreml/assets/g2p/normalization.json +0 -40
- coreml/assets/g2p/phoneme_dict.json +0 -9
- coreml/assets/g2p/pronunciation_overrides.json +0 -4
- coreml/assets/g2p/tokenizer.json +0 -517
- coreml/assets/languages.json +0 -30
- coreml/assets/phone_vocab.json +0 -111
- coreml/assets/voices.json +0 -42
- coreml/coreml/duration_predictor.mlmodelc/analytics/coremldata.bin +0 -3
- coreml/coreml/duration_predictor.mlmodelc/coremldata.bin +0 -3
- coreml/coreml/duration_predictor.mlmodelc/model.mil +0 -0
- coreml/coreml/duration_predictor.mlmodelc/weights/weight.bin +0 -3
- coreml/coreml/g2p.mlmodelc/analytics/coremldata.bin +0 -3
- coreml/coreml/g2p.mlmodelc/coremldata.bin +0 -3
- coreml/coreml/g2p.mlmodelc/model.mil +0 -0
- coreml/coreml/g2p.mlmodelc/weights/weight.bin +0 -3
- coreml/coreml/vector_context_encoder.mlmodelc/analytics/coremldata.bin +0 -3
- coreml/coreml/vector_context_encoder.mlmodelc/coremldata.bin +0 -3
- coreml/coreml/vector_context_encoder.mlmodelc/model.mil +0 -267
- coreml/coreml/vector_context_encoder.mlmodelc/weights/weight.bin +0 -3
README.md
CHANGED
|
@@ -3,14 +3,14 @@ license: apache-2.0
|
|
| 3 |
language: [en, es, it, fr, de, vi]
|
| 4 |
library_name: litert
|
| 5 |
pipeline_tag: text-to-speech
|
| 6 |
-
tags: [text-to-speech, tts, litert, onnx, coreml, coreai, pytorch, multilingual, expressive-tts, duration-flow
|
| 7 |
---
|
| 8 |
|
| 9 |
# Scylla's Band v2
|
| 10 |
|
| 11 |
-
Release **`v2-
|
| 12 |
|
| 13 |
-
The model exposes **energy, tension, valence and assertiveness** on **0–4 scales with neutral at 2**
|
| 14 |
|
| 15 |
## Quick start
|
| 16 |
|
|
@@ -19,8 +19,8 @@ Install the [runtime](https://github.com/lowkeytea/scyllasband) (`pip install -e
|
|
| 19 |
```bash
|
| 20 |
python -m scyllasband download --yes
|
| 21 |
python -m scyllasband speak --voice ariadne --language en_us \
|
| 22 |
-
--delivery energy=2.3,tension=1.7,valence=2.6,assertiveness=2
|
| 23 |
-
-
|
| 24 |
```
|
| 25 |
|
| 26 |
The default download is the Core ML bundle on an Apple silicon Mac and the LiteRT bundle elsewhere, installed under `scyllasband/models/<bundle>`. A Mac that can build apps for iOS, iPadOS or visionOS 27 is also offered the Core AI bundle those apps use. `--flavor coreml`, `--flavor coreai`, `--flavor litert` or `--flavor onnx` choose explicitly. Downloads pin a release tag. The manifest declares graph contract `scyllasband_measured_delivery_v2`; runtimes written for earlier releases cannot run these graphs.
|
|
@@ -30,7 +30,6 @@ The default download is the Core ML bundle on an Apple silicon Mac and the LiteR
|
|
| 30 |
| Input | Values | Default |
|
| 31 |
| --- | --- | --- |
|
| 32 |
| Energy, tension, valence, assertiveness | 0–4 or unspecified | 2 each |
|
| 33 |
-
| Whisper | on/off or unspecified | off |
|
| 34 |
|
| 35 |
With every control at 2, the default, voices speak in a calm, conversational delivery with a neutral tone. Raising or lowering a control changes the delivery:
|
| 36 |
|
|
@@ -41,8 +40,6 @@ With every control at 2, the default, voices speak in a calm, conversational del
|
|
| 41 |
| Valence | Flatter, more downcast pitch | Livelier pitch, a little quicker, shorter pauses |
|
| 42 |
| Assertiveness | More pauses between phrases | Faster and clipped with fewer pauses; the strongest control over pace |
|
| 43 |
|
| 44 |
-
Whisper on gives quieter, breathy speech.
|
| 45 |
-
|
| 46 |
The model learned delivery mostly from settings between about 1.7 and 2.8 for energy, 1.9 and 3.0 for valence, 1.8 and 2.7 for assertiveness, and 1.0 and 3.1 for tension. The controls are most reliable inside those ranges; further out, voices can sound strained or a style can become ambiguous.
|
| 47 |
|
| 48 |
Combining the controls gives familiar deliveries:
|
|
@@ -53,14 +50,13 @@ Combining the controls gives familiar deliveries:
|
|
| 53 |
| Assertive and quick | `energy=2.6,tension=2.4,valence=2.1,assertiveness=2.8` |
|
| 54 |
| Joyful | `energy=2.4,tension=2,valence=2.8,assertiveness=2.2` |
|
| 55 |
| Angry | `energy=2.7,tension=3.1,valence=1.3,assertiveness=2.5` |
|
| 56 |
-
| Sad | `energy=1.7,tension=1.
|
| 57 |
-
| Whispered | `whisper=on` |
|
| 58 |
|
| 59 |
-
Angry
|
| 60 |
|
| 61 |
`--delivery auto` omits all coordinates. A per-axis `auto` omits just that coordinate; other unspecified fields in a partial request use neutral defaults. Omission is represented by a separate mask, not by the value 2. It is not an automatic text-to-performance planner.
|
| 62 |
|
| 63 |
-
The graph receives `(rating - 2) / 4` for the four continuous axes
|
| 64 |
|
| 65 |
Controls are **global within each request**. This release does not support control curves, singing, or trained automatic variation over a multi-sentence passage.
|
| 66 |
|
|
@@ -75,11 +71,14 @@ Controls are **global within each request**. This release does not support contr
|
|
| 75 |
| Duration model | Hidden size 320; 8 layers; reads the neighbouring text as context |
|
| 76 |
| Vector model | Hidden size 512; 12 layers; adaptive layer normalization and QK normalization |
|
| 77 |
| Maximum graph phones per sentence | 512 |
|
|
|
|
| 78 |
| Latent buckets | 128, 256, 384, 512, 768, 1024 frames |
|
| 79 |
-
|
|
| 80 |
| Voice conditioning | Fixed per-voice/per-locale identity and prosody references embedded in the graphs |
|
| 81 |
| Text frontend | Trained Scylla's Band G2P with its matched tokenizer and vocabulary |
|
| 82 |
|
|
|
|
|
|
|
| 83 |
Long text is spoken as passages within the trained target lengths (64 to 420 latent frames, about 1.4 to 9 seconds): a short first passage so audio starts quickly, then passages as long as the text allows, cut at a sentence end, else a clause, else between words, and measured with the requested delivery. Each passage sees the surrounding text as context and continues from the acoustics of the one before it, and consecutive passages are decoded as one continuous waveform. Durations are predicted deterministically; different controls can alter them.
|
| 84 |
|
| 85 |
## Voices and language coverage
|
|
@@ -92,7 +91,7 @@ All ten have Spanish (`es`), Italian (`it`), French (`fr`), German (`de`) and Vi
|
|
| 92 |
|
| 93 |
- `litert/` (164 MB): LiteRT bundle; default download. Transformer and vocoder weights are dynamic-range INT8; each size bucket is a signature of one model file, sharing weights.
|
| 94 |
- `coreai/` (155 MB): Core AI bundle for apps on iOS, iPadOS and visionOS 27 (`.aimodel` assets); it also runs on macOS 27, where the runtime uses the Core ML bundle by default. INT8 weights per output channel with FP16 compute; size buckets are functions of one asset sharing weights. The flow also runs accurately on the Neural Engine (`controls.coreai.neural_engine_assets`), which is the placement for apps that speak in the background; the GPU is the default.
|
| 95 |
-
- `coreml/` (142 MB): Core ML bundle for Apple silicon with iOS 18 / macOS 15 and later (compiled `.mlmodelc` assets), with INT8 weights and FP16 compute; GPU by default, CPU in background apps.
|
| 96 |
- `onnx/`: ONNX Runtime bundle with dynamic INT8 transformer weights; the vocoder stays in full precision.
|
| 97 |
- `pytorch/`: duration, vector, adapter/vocoder and G2P weights (no training state), with the release configuration assets.
|
| 98 |
- `SHA256SUMS.json`: published-file hashes.
|
|
@@ -104,6 +103,7 @@ Every runtime bundle includes the G2P model in a matching precision. The Apple b
|
|
| 104 |
Release validation separates graph accuracy, frontend/timing behaviour and perceived speech quality:
|
| 105 |
|
| 106 |
- Component comparisons against PyTorch during export, and end-to-end comparison of full passages against the PyTorch reference path.
|
|
|
|
| 107 |
- Quantized bundles compared with full precision on real sentences: identical phonemes, phone durations and generated latents within small tolerances, followed by listening across all ten voices.
|
| 108 |
- G2P conversions compared with the full-precision G2P on multilingual text.
|
| 109 |
- Core ML and Core AI bundles compared with the PyTorch model on every graph and on real passages, on each compute unit they are used with (GPU, CPU, and for Core AI the Neural Engine): identical phonemes apart from two near-tie stress marks also seen in FP16, fewer changed phone durations than the LiteRT bundle, and smaller latent and spectral differences. The Apple exports rewrite three computations into equivalent forms that FP16 and the Neural Engine evaluate exactly (span pooling, the modifier bit decoding, the duration model's combined phone/segment index), and scale the flow's residual stream; in FP32 the rewritten graphs are bit-identical to the trained ones.
|
|
|
|
| 3 |
language: [en, es, it, fr, de, vi]
|
| 4 |
library_name: litert
|
| 5 |
pipeline_tag: text-to-speech
|
| 6 |
+
tags: [text-to-speech, tts, litert, onnx, coreml, coreai, pytorch, multilingual, expressive-tts, duration-flow]
|
| 7 |
---
|
| 8 |
|
| 9 |
# Scylla's Band v2
|
| 10 |
|
| 11 |
+
Release **`v2-20261006`**. The [Scylla's Band runtime](https://github.com/lowkeytea/scyllasband) supports this release. Tag `v2-20261006-apple` adds Core ML and Core AI bundles of the same model; the runtime downloads from that tag.
|
| 12 |
|
| 13 |
+
The model exposes **energy, tension, valence and assertiveness** on **0–4 scales with neutral at 2**. Combining the controls changes the generated delivery; a request is not a guarantee of a particular perceived emotion or exact external scorer value.
|
| 14 |
|
| 15 |
## Quick start
|
| 16 |
|
|
|
|
| 19 |
```bash
|
| 20 |
python -m scyllasband download --yes
|
| 21 |
python -m scyllasband speak --voice ariadne --language en_us \
|
| 22 |
+
--delivery energy=2.3,tension=1.7,valence=2.6,assertiveness=2 \
|
| 23 |
+
-o hello.wav "It is a pleasure to meet you."
|
| 24 |
```
|
| 25 |
|
| 26 |
The default download is the Core ML bundle on an Apple silicon Mac and the LiteRT bundle elsewhere, installed under `scyllasband/models/<bundle>`. A Mac that can build apps for iOS, iPadOS or visionOS 27 is also offered the Core AI bundle those apps use. `--flavor coreml`, `--flavor coreai`, `--flavor litert` or `--flavor onnx` choose explicitly. Downloads pin a release tag. The manifest declares graph contract `scyllasband_measured_delivery_v2`; runtimes written for earlier releases cannot run these graphs.
|
|
|
|
| 30 |
| Input | Values | Default |
|
| 31 |
| --- | --- | --- |
|
| 32 |
| Energy, tension, valence, assertiveness | 0–4 or unspecified | 2 each |
|
|
|
|
| 33 |
|
| 34 |
With every control at 2, the default, voices speak in a calm, conversational delivery with a neutral tone. Raising or lowering a control changes the delivery:
|
| 35 |
|
|
|
|
| 40 |
| Valence | Flatter, more downcast pitch | Livelier pitch, a little quicker, shorter pauses |
|
| 41 |
| Assertiveness | More pauses between phrases | Faster and clipped with fewer pauses; the strongest control over pace |
|
| 42 |
|
|
|
|
|
|
|
| 43 |
The model learned delivery mostly from settings between about 1.7 and 2.8 for energy, 1.9 and 3.0 for valence, 1.8 and 2.7 for assertiveness, and 1.0 and 3.1 for tension. The controls are most reliable inside those ranges; further out, voices can sound strained or a style can become ambiguous.
|
| 44 |
|
| 45 |
Combining the controls gives familiar deliveries:
|
|
|
|
| 50 |
| Assertive and quick | `energy=2.6,tension=2.4,valence=2.1,assertiveness=2.8` |
|
| 51 |
| Joyful | `energy=2.4,tension=2,valence=2.8,assertiveness=2.2` |
|
| 52 |
| Angry | `energy=2.7,tension=3.1,valence=1.3,assertiveness=2.5` |
|
| 53 |
+
| Sad | `energy=1.7,tension=1.5,valence=1.4,assertiveness=2` |
|
|
|
|
| 54 |
|
| 55 |
+
Angry and sad take valence a little below the trained range so that they separate clearly from joyful and calm. These are moderate styles; how strongly each comes through varies with voice, language and text. The [voice gallery](https://lowkeytea.github.io/scyllasband/#delivery) plays each of them for all ten voices.
|
| 56 |
|
| 57 |
`--delivery auto` omits all coordinates. A per-axis `auto` omits just that coordinate; other unspecified fields in a partial request use neutral defaults. Omission is represented by a separate mask, not by the value 2. It is not an automatic text-to-performance planner.
|
| 58 |
|
| 59 |
+
The graph receives `(rating - 2) / 4` for the four continuous axes plus presence bits. Its fifth delivery input, whisper, was a training axis; it is not supported, and the runtimes always send it off. The public interface accepts the original 0–4 values. Expressiveness is an auxiliary training target, not an inference axis.
|
| 60 |
|
| 61 |
Controls are **global within each request**. This release does not support control curves, singing, or trained automatic variation over a multi-sentence passage.
|
| 62 |
|
|
|
|
| 71 |
| Duration model | Hidden size 320; 8 layers; reads the neighbouring text as context |
|
| 72 |
| Vector model | Hidden size 512; 12 layers; adaptive layer normalization and QK normalization |
|
| 73 |
| Maximum graph phones per sentence | 512 |
|
| 74 |
+
| Trained target length | 64–420 latent frames (about 1.4–9 s) per pass |
|
| 75 |
| Latent buckets | 128, 256, 384, 512, 768, 1024 frames |
|
| 76 |
+
| Sampler | Euler, 4 steps (default) |
|
| 77 |
| Voice conditioning | Fixed per-voice/per-locale identity and prosody references embedded in the graphs |
|
| 78 |
| Text frontend | Trained Scylla's Band G2P with its matched tokenizer and vocabulary |
|
| 79 |
|
| 80 |
+
The flow is distilled for few-step sampling: it was trained to reproduce the base flow's 32-step Heun output, so Euler with 4 steps, four model evaluations per passage, is the default. Heun with 8 steps costs four times as much and sounds slightly sharper.
|
| 81 |
+
|
| 82 |
Long text is spoken as passages within the trained target lengths (64 to 420 latent frames, about 1.4 to 9 seconds): a short first passage so audio starts quickly, then passages as long as the text allows, cut at a sentence end, else a clause, else between words, and measured with the requested delivery. Each passage sees the surrounding text as context and continues from the acoustics of the one before it, and consecutive passages are decoded as one continuous waveform. Durations are predicted deterministically; different controls can alter them.
|
| 83 |
|
| 84 |
## Voices and language coverage
|
|
|
|
| 91 |
|
| 92 |
- `litert/` (164 MB): LiteRT bundle; default download. Transformer and vocoder weights are dynamic-range INT8; each size bucket is a signature of one model file, sharing weights.
|
| 93 |
- `coreai/` (155 MB): Core AI bundle for apps on iOS, iPadOS and visionOS 27 (`.aimodel` assets); it also runs on macOS 27, where the runtime uses the Core ML bundle by default. INT8 weights per output channel with FP16 compute; size buckets are functions of one asset sharing weights. The flow also runs accurately on the Neural Engine (`controls.coreai.neural_engine_assets`), which is the placement for apps that speak in the background; the GPU is the default.
|
| 94 |
+
- `coreml/` (142 MB): Core ML bundle for Apple silicon with iOS 18 / visionOS 2 / macOS 15 and later (compiled `.mlmodelc` assets), with INT8 weights and FP16 compute; GPU by default, CPU in background apps.
|
| 95 |
- `onnx/`: ONNX Runtime bundle with dynamic INT8 transformer weights; the vocoder stays in full precision.
|
| 96 |
- `pytorch/`: duration, vector, adapter/vocoder and G2P weights (no training state), with the release configuration assets.
|
| 97 |
- `SHA256SUMS.json`: published-file hashes.
|
|
|
|
| 103 |
Release validation separates graph accuracy, frontend/timing behaviour and perceived speech quality:
|
| 104 |
|
| 105 |
- Component comparisons against PyTorch during export, and end-to-end comparison of full passages against the PyTorch reference path.
|
| 106 |
+
- The distilled flow at 4 Euler steps compared with the base flow at 8 Heun steps on the same passages, seeds and noise: equal distance to the 32-step output, confirmed by listening across all ten voices.
|
| 107 |
- Quantized bundles compared with full precision on real sentences: identical phonemes, phone durations and generated latents within small tolerances, followed by listening across all ten voices.
|
| 108 |
- G2P conversions compared with the full-precision G2P on multilingual text.
|
| 109 |
- Core ML and Core AI bundles compared with the PyTorch model on every graph and on real passages, on each compute unit they are used with (GPU, CPU, and for Core AI the Neural Engine): identical phonemes apart from two near-tie stress marks also seen in FP16, fewer changed phone durations than the LiteRT bundle, and smaller latent and spectral differences. The Apple exports rewrite three computations into equivalent forms that FP16 and the Neural Engine evaluate exactly (span pooling, the modifier bit decoding, the duration model's combined phone/segment index), and scale the flow's residual stream; in FP32 the rewritten graphs are bit-identical to the trained ones.
|
SHA256SUMS.json
CHANGED
|
@@ -4,241 +4,13 @@
|
|
| 4 |
"bytes": 11357
|
| 5 |
},
|
| 6 |
"README.md": {
|
| 7 |
-
"sha256": "
|
| 8 |
-
"bytes":
|
| 9 |
},
|
| 10 |
"THIRD_PARTY_NOTICES.md": {
|
| 11 |
"sha256": "3b793b8ee250cc711e4012ee42e9625a8a7e788bf12cab85a1abbd17b17644ca",
|
| 12 |
"bytes": 2818
|
| 13 |
},
|
| 14 |
-
"coreai/assets/fixed_references.json": {
|
| 15 |
-
"sha256": "d3c26e7e90d90fa719254ff1ff05dc4b391cd47231b7556c3c2ed5f63547925b",
|
| 16 |
-
"bytes": 1115042
|
| 17 |
-
},
|
| 18 |
-
"coreai/assets/g2p/export_config.json": {
|
| 19 |
-
"sha256": "0ec5ea81f346521f3a5c9c4a90b939c6b5143b1a11cc5e74b9902969db56e568",
|
| 20 |
-
"bytes": 928
|
| 21 |
-
},
|
| 22 |
-
"coreai/assets/g2p/language_map.json": {
|
| 23 |
-
"sha256": "b3db2048b492799f8746b43001e0f7411eb5d359e17cabc6bfce4a7bccbfdd99",
|
| 24 |
-
"bytes": 844
|
| 25 |
-
},
|
| 26 |
-
"coreai/assets/g2p/normalization.json": {
|
| 27 |
-
"sha256": "f9ca4fe4e4eca5e02b6f2874f5da6ede8b44b25c71c3c6ac00f96d7397024de6",
|
| 28 |
-
"bytes": 1090
|
| 29 |
-
},
|
| 30 |
-
"coreai/assets/g2p/phoneme_dict.json": {
|
| 31 |
-
"sha256": "9cfb40b2fd31d7a32351c33f90230062554a4dc0a44e89f722de211d42ed1875",
|
| 32 |
-
"bytes": 93
|
| 33 |
-
},
|
| 34 |
-
"coreai/assets/g2p/pronunciation_overrides.json": {
|
| 35 |
-
"sha256": "a1f311379b76cb44719a2242a93a4046ff5f344cdac613374288234c2817eb59",
|
| 36 |
-
"bytes": 80
|
| 37 |
-
},
|
| 38 |
-
"coreai/assets/g2p/tokenizer.json": {
|
| 39 |
-
"sha256": "4843d57a422b0a6045bbc6fc9a99afa329126a6742ff95ebcefcda660f3ee474",
|
| 40 |
-
"bytes": 7769
|
| 41 |
-
},
|
| 42 |
-
"coreai/assets/languages.json": {
|
| 43 |
-
"sha256": "f2af2233d0a1c0dbb6e6236fd57592d12da84262fdd1a336ead1ee83a657e2ae",
|
| 44 |
-
"bytes": 289
|
| 45 |
-
},
|
| 46 |
-
"coreai/assets/phone_vocab.json": {
|
| 47 |
-
"sha256": "83e6457a69948edbd9a94b404c22fd408c263eb0d0b5acaafa4926e994587721",
|
| 48 |
-
"bytes": 1793
|
| 49 |
-
},
|
| 50 |
-
"coreai/assets/voices.json": {
|
| 51 |
-
"sha256": "db9aa57e3d5f9f34fed283fb8e79f4c38e218647d33bc4a5c71ea3e8338c1a56",
|
| 52 |
-
"bytes": 433
|
| 53 |
-
},
|
| 54 |
-
"coreai/coreai/duration_predictor.aimodel/main.hash": {
|
| 55 |
-
"sha256": "ec1450950c5c92a8567b91acb3999a9d53ebcfae92401c4c9893a3ab780020af",
|
| 56 |
-
"bytes": 32
|
| 57 |
-
},
|
| 58 |
-
"coreai/coreai/duration_predictor.aimodel/main.mlirb": {
|
| 59 |
-
"sha256": "4243d405361c9ebc82a0e233a3cb1bd5d64b5389a96ddd58947f14fb84b3c949",
|
| 60 |
-
"bytes": 10884924
|
| 61 |
-
},
|
| 62 |
-
"coreai/coreai/duration_predictor.aimodel/metadata.json": {
|
| 63 |
-
"sha256": "3b825889dba08f532b2e922b099aff707fdefc53cf86716392f5867f1b667999",
|
| 64 |
-
"bytes": 105
|
| 65 |
-
},
|
| 66 |
-
"coreai/coreai/g2p.aimodel/main.hash": {
|
| 67 |
-
"sha256": "300a60ae5cd565c7207ff5877dfa8427af6868a14fb6ccfa195ca17fe0e50a3f",
|
| 68 |
-
"bytes": 32
|
| 69 |
-
},
|
| 70 |
-
"coreai/coreai/g2p.aimodel/main.mlirb": {
|
| 71 |
-
"sha256": "e7426aa159702a859176420d0c34b493da7d3dd97fa74fdeedb2ee4c4f0dce18",
|
| 72 |
-
"bytes": 28377271
|
| 73 |
-
},
|
| 74 |
-
"coreai/coreai/g2p.aimodel/metadata.json": {
|
| 75 |
-
"sha256": "07542e963b0d178a540fa3a7927bd54ac3050c4ccc959dc38defe42e33fe7066",
|
| 76 |
-
"bytes": 105
|
| 77 |
-
},
|
| 78 |
-
"coreai/coreai/vector_context_encoder.aimodel/main.hash": {
|
| 79 |
-
"sha256": "0dfa623d5496abf0b862e73ed8adc2a4e8bf5f4249b1c209543ca44312cdc5f3",
|
| 80 |
-
"bytes": 32
|
| 81 |
-
},
|
| 82 |
-
"coreai/coreai/vector_context_encoder.aimodel/main.mlirb": {
|
| 83 |
-
"sha256": "9dca40e4aa2ce1cf2099c7c4ee34bbea72f2594d88459210cfa06dfc9592f135",
|
| 84 |
-
"bytes": 8029277
|
| 85 |
-
},
|
| 86 |
-
"coreai/coreai/vector_context_encoder.aimodel/metadata.json": {
|
| 87 |
-
"sha256": "2adcb7092d18dc35b8686fc8b5a6075c09b852ce0353899bc1459cdbbfb3f6ba",
|
| 88 |
-
"bytes": 105
|
| 89 |
-
},
|
| 90 |
-
"coreai/coreai/vector_estimator.aimodel/main.hash": {
|
| 91 |
-
"sha256": "eddcebf2eca499422d841f257a6c270866151ee1b5f082ad375dda29264176c3",
|
| 92 |
-
"bytes": 32
|
| 93 |
-
},
|
| 94 |
-
"coreai/coreai/vector_estimator.aimodel/main.mlirb": {
|
| 95 |
-
"sha256": "4dc8e41c5c9de01f2d3a9fd847a30df8b27ceec9aa0894b235f49181dcd664d2",
|
| 96 |
-
"bytes": 63149068
|
| 97 |
-
},
|
| 98 |
-
"coreai/coreai/vector_estimator.aimodel/metadata.json": {
|
| 99 |
-
"sha256": "e90fa086d07ef39797bce9b6d6c82429d84b17a5ebb77380d71d94d44eb630f7",
|
| 100 |
-
"bytes": 105
|
| 101 |
-
},
|
| 102 |
-
"coreai/coreai/vocoder.aimodel/main.hash": {
|
| 103 |
-
"sha256": "62fae3f0d6ca6e5cb648e1c54d47c243d919bdb9e93e89e53f786eb318f90003",
|
| 104 |
-
"bytes": 32
|
| 105 |
-
},
|
| 106 |
-
"coreai/coreai/vocoder.aimodel/main.mlirb": {
|
| 107 |
-
"sha256": "0e0d07b91327322c55da5081c7e3301565e92c5298dd9a5dfb74b71ee6074669",
|
| 108 |
-
"bytes": 43811030
|
| 109 |
-
},
|
| 110 |
-
"coreai/coreai/vocoder.aimodel/metadata.json": {
|
| 111 |
-
"sha256": "d1169c91caecc862135efebf9a832fd956459929050ca29415db3e41197ef6b2",
|
| 112 |
-
"bytes": 105
|
| 113 |
-
},
|
| 114 |
-
"coreai/manifest.json": {
|
| 115 |
-
"sha256": "a2a3b2c822673e98ae44af5280ab3b71039609ea913d1c50392faf37ed97c19d",
|
| 116 |
-
"bytes": 21685
|
| 117 |
-
},
|
| 118 |
-
"coreml/assets/fixed_references.json": {
|
| 119 |
-
"sha256": "d3c26e7e90d90fa719254ff1ff05dc4b391cd47231b7556c3c2ed5f63547925b",
|
| 120 |
-
"bytes": 1115042
|
| 121 |
-
},
|
| 122 |
-
"coreml/assets/g2p/export_config.json": {
|
| 123 |
-
"sha256": "0ec5ea81f346521f3a5c9c4a90b939c6b5143b1a11cc5e74b9902969db56e568",
|
| 124 |
-
"bytes": 928
|
| 125 |
-
},
|
| 126 |
-
"coreml/assets/g2p/language_map.json": {
|
| 127 |
-
"sha256": "b3db2048b492799f8746b43001e0f7411eb5d359e17cabc6bfce4a7bccbfdd99",
|
| 128 |
-
"bytes": 844
|
| 129 |
-
},
|
| 130 |
-
"coreml/assets/g2p/normalization.json": {
|
| 131 |
-
"sha256": "f9ca4fe4e4eca5e02b6f2874f5da6ede8b44b25c71c3c6ac00f96d7397024de6",
|
| 132 |
-
"bytes": 1090
|
| 133 |
-
},
|
| 134 |
-
"coreml/assets/g2p/phoneme_dict.json": {
|
| 135 |
-
"sha256": "9cfb40b2fd31d7a32351c33f90230062554a4dc0a44e89f722de211d42ed1875",
|
| 136 |
-
"bytes": 93
|
| 137 |
-
},
|
| 138 |
-
"coreml/assets/g2p/pronunciation_overrides.json": {
|
| 139 |
-
"sha256": "a1f311379b76cb44719a2242a93a4046ff5f344cdac613374288234c2817eb59",
|
| 140 |
-
"bytes": 80
|
| 141 |
-
},
|
| 142 |
-
"coreml/assets/g2p/tokenizer.json": {
|
| 143 |
-
"sha256": "4843d57a422b0a6045bbc6fc9a99afa329126a6742ff95ebcefcda660f3ee474",
|
| 144 |
-
"bytes": 7769
|
| 145 |
-
},
|
| 146 |
-
"coreml/assets/languages.json": {
|
| 147 |
-
"sha256": "f2af2233d0a1c0dbb6e6236fd57592d12da84262fdd1a336ead1ee83a657e2ae",
|
| 148 |
-
"bytes": 289
|
| 149 |
-
},
|
| 150 |
-
"coreml/assets/phone_vocab.json": {
|
| 151 |
-
"sha256": "83e6457a69948edbd9a94b404c22fd408c263eb0d0b5acaafa4926e994587721",
|
| 152 |
-
"bytes": 1793
|
| 153 |
-
},
|
| 154 |
-
"coreml/assets/voices.json": {
|
| 155 |
-
"sha256": "db9aa57e3d5f9f34fed283fb8e79f4c38e218647d33bc4a5c71ea3e8338c1a56",
|
| 156 |
-
"bytes": 433
|
| 157 |
-
},
|
| 158 |
-
"coreml/coreml/duration_predictor.mlmodelc/analytics/coremldata.bin": {
|
| 159 |
-
"sha256": "953e274e93c3abfae6f04977436816dc28223ef61d4e91e4191f67837740a2e8",
|
| 160 |
-
"bytes": 243
|
| 161 |
-
},
|
| 162 |
-
"coreml/coreml/duration_predictor.mlmodelc/coremldata.bin": {
|
| 163 |
-
"sha256": "c090d28d8df68312410867a49963b5fbda00f5883178969df17b1b0c86e7eff2",
|
| 164 |
-
"bytes": 554
|
| 165 |
-
},
|
| 166 |
-
"coreml/coreml/duration_predictor.mlmodelc/model.mil": {
|
| 167 |
-
"sha256": "b342ee3bcc2acb6b8bd0de42bebfc6c3d83b40e5512156fb26f909fa9ae3d608",
|
| 168 |
-
"bytes": 138985
|
| 169 |
-
},
|
| 170 |
-
"coreml/coreml/duration_predictor.mlmodelc/weights/weight.bin": {
|
| 171 |
-
"sha256": "5383e19195d6807cf6632d2c82b51b86aaa947ba51d8042434f73b5039c70ea4",
|
| 172 |
-
"bytes": 10562880
|
| 173 |
-
},
|
| 174 |
-
"coreml/coreml/g2p.mlmodelc/analytics/coremldata.bin": {
|
| 175 |
-
"sha256": "61936fdfe11637e628b2134025bea29d673c98e93ce6f01c05e7b5da124563b8",
|
| 176 |
-
"bytes": 243
|
| 177 |
-
},
|
| 178 |
-
"coreml/coreml/g2p.mlmodelc/coremldata.bin": {
|
| 179 |
-
"sha256": "f5fc8bee0186f33fa14d35a59a58ec3393676d07bdf03802a3836d806662cd03",
|
| 180 |
-
"bytes": 377
|
| 181 |
-
},
|
| 182 |
-
"coreml/coreml/g2p.mlmodelc/model.mil": {
|
| 183 |
-
"sha256": "d464334a231d99b9a3764d50c28657d1720e25eaa45e39fa4daa401bb89452a1",
|
| 184 |
-
"bytes": 388409
|
| 185 |
-
},
|
| 186 |
-
"coreml/coreml/g2p.mlmodelc/weights/weight.bin": {
|
| 187 |
-
"sha256": "045da2991ed2a42ba027aaa6b83813054f410b6eedfdce82f2ab287ec4ca74e2",
|
| 188 |
-
"bytes": 27346752
|
| 189 |
-
},
|
| 190 |
-
"coreml/coreml/vector_context_encoder.mlmodelc/analytics/coremldata.bin": {
|
| 191 |
-
"sha256": "f89405fefad88549b521a819805c5c1781e0c930c03b8f670b1e1539aafe88c6",
|
| 192 |
-
"bytes": 243
|
| 193 |
-
},
|
| 194 |
-
"coreml/coreml/vector_context_encoder.mlmodelc/coremldata.bin": {
|
| 195 |
-
"sha256": "d031d4ef221bc846aec129114aec7366fcb6126dacae44c24c4b344c54dc6c5a",
|
| 196 |
-
"bytes": 476
|
| 197 |
-
},
|
| 198 |
-
"coreml/coreml/vector_context_encoder.mlmodelc/model.mil": {
|
| 199 |
-
"sha256": "c3c0df163512f0ed8ab4dbb927054f2cb627980c734419bd96e341540660d372",
|
| 200 |
-
"bytes": 44809
|
| 201 |
-
},
|
| 202 |
-
"coreml/coreml/vector_context_encoder.mlmodelc/weights/weight.bin": {
|
| 203 |
-
"sha256": "7120be9d216af8b1021ad92a4d3d0d136881d55e48debfb348197f12da2a21d6",
|
| 204 |
-
"bytes": 7572352
|
| 205 |
-
},
|
| 206 |
-
"coreml/coreml/vector_estimator.mlmodelc/analytics/coremldata.bin": {
|
| 207 |
-
"sha256": "4cd08db9de17f4e62caab8acf50c3c28909c28b945acb105f35e45820366621a",
|
| 208 |
-
"bytes": 243
|
| 209 |
-
},
|
| 210 |
-
"coreml/coreml/vector_estimator.mlmodelc/coremldata.bin": {
|
| 211 |
-
"sha256": "d22410a5a41fc0aae79224588c2da505cd4abae60526d06fd989749001741762",
|
| 212 |
-
"bytes": 3647
|
| 213 |
-
},
|
| 214 |
-
"coreml/coreml/vector_estimator.mlmodelc/model.mil": {
|
| 215 |
-
"sha256": "48c7230b2cee7088f5431117ea54758e6a37e5f55faa8cdea3aa7fdd34010831",
|
| 216 |
-
"bytes": 1469007
|
| 217 |
-
},
|
| 218 |
-
"coreml/coreml/vector_estimator.mlmodelc/weights/weight.bin": {
|
| 219 |
-
"sha256": "135922d329c47a98942f1ce104c3e62f9ccc6578b6866d57482839172c9bf1be",
|
| 220 |
-
"bytes": 60754048
|
| 221 |
-
},
|
| 222 |
-
"coreml/coreml/vocoder.mlmodelc/analytics/coremldata.bin": {
|
| 223 |
-
"sha256": "c8c3075b62c159b4773c0d721e911570449783db5e493eb53e2a0a78049e717e",
|
| 224 |
-
"bytes": 243
|
| 225 |
-
},
|
| 226 |
-
"coreml/coreml/vocoder.mlmodelc/coremldata.bin": {
|
| 227 |
-
"sha256": "04bf9f9de7edfc6ce58e5928a0a1d6669d09095ebc03cb5ca24dd85a416653df",
|
| 228 |
-
"bytes": 1190
|
| 229 |
-
},
|
| 230 |
-
"coreml/coreml/vocoder.mlmodelc/model.mil": {
|
| 231 |
-
"sha256": "e7b28b62c2ce75b56bb284333542585cf4abe4ebda50ce72322cbea88dcea53c",
|
| 232 |
-
"bytes": 969259
|
| 233 |
-
},
|
| 234 |
-
"coreml/coreml/vocoder.mlmodelc/weights/weight.bin": {
|
| 235 |
-
"sha256": "8d1aa1e85be960d5ad32f751b602c38601bc9517a951be5bd42c991449d3bccc",
|
| 236 |
-
"bytes": 31043584
|
| 237 |
-
},
|
| 238 |
-
"coreml/manifest.json": {
|
| 239 |
-
"sha256": "3519f7fe3c8c98e8672a99451e44ff7ef60ed35317031e82669adbb1b5acf3a0",
|
| 240 |
-
"bytes": 21577
|
| 241 |
-
},
|
| 242 |
"litert/assets/fixed_references.json": {
|
| 243 |
"sha256": "d3c26e7e90d90fa719254ff1ff05dc4b391cd47231b7556c3c2ed5f63547925b",
|
| 244 |
"bytes": 1115042
|
|
@@ -288,11 +60,11 @@
|
|
| 288 |
"bytes": 28626144
|
| 289 |
},
|
| 290 |
"litert/litert/vector_context_encoder.tflite": {
|
| 291 |
-
"sha256": "
|
| 292 |
"bytes": 7763584
|
| 293 |
},
|
| 294 |
"litert/litert/vector_estimator.tflite": {
|
| 295 |
-
"sha256": "
|
| 296 |
"bytes": 76550528
|
| 297 |
},
|
| 298 |
"litert/litert/vocoder.tflite": {
|
|
@@ -300,8 +72,8 @@
|
|
| 300 |
"bytes": 38613392
|
| 301 |
},
|
| 302 |
"litert/manifest.json": {
|
| 303 |
-
"sha256": "
|
| 304 |
-
"bytes":
|
| 305 |
},
|
| 306 |
"onnx/assets/fixed_references.json": {
|
| 307 |
"sha256": "d3c26e7e90d90fa719254ff1ff05dc4b391cd47231b7556c3c2ed5f63547925b",
|
|
@@ -344,76 +116,76 @@
|
|
| 344 |
"bytes": 433
|
| 345 |
},
|
| 346 |
"onnx/manifest.json": {
|
| 347 |
-
"sha256": "
|
| 348 |
-
"bytes":
|
| 349 |
},
|
| 350 |
"onnx/onnx/components/duration_predictor.onnx": {
|
| 351 |
-
"sha256": "
|
| 352 |
"bytes": 285227
|
| 353 |
},
|
| 354 |
"onnx/onnx/components/shared_weights.bin": {
|
| 355 |
-
"sha256": "
|
| 356 |
"bytes": 208219968
|
| 357 |
},
|
| 358 |
"onnx/onnx/components/shared_weights.json": {
|
| 359 |
-
"sha256": "
|
| 360 |
-
"bytes":
|
| 361 |
},
|
| 362 |
"onnx/onnx/components/vector_context_encoder.onnx": {
|
| 363 |
-
"sha256": "
|
| 364 |
-
"bytes":
|
| 365 |
},
|
| 366 |
"onnx/onnx/components/vector_estimator.onnx": {
|
| 367 |
-
"sha256": "
|
| 368 |
-
"bytes":
|
| 369 |
},
|
| 370 |
"onnx/onnx/components/vector_estimator_128.onnx": {
|
| 371 |
-
"sha256": "
|
| 372 |
-
"bytes":
|
| 373 |
},
|
| 374 |
"onnx/onnx/components/vector_estimator_256.onnx": {
|
| 375 |
-
"sha256": "
|
| 376 |
-
"bytes":
|
| 377 |
},
|
| 378 |
"onnx/onnx/components/vector_estimator_384.onnx": {
|
| 379 |
-
"sha256": "
|
| 380 |
-
"bytes":
|
| 381 |
},
|
| 382 |
"onnx/onnx/components/vector_estimator_512.onnx": {
|
| 383 |
-
"sha256": "
|
| 384 |
-
"bytes":
|
| 385 |
},
|
| 386 |
"onnx/onnx/components/vector_estimator_768.onnx": {
|
| 387 |
-
"sha256": "
|
| 388 |
-
"bytes":
|
| 389 |
},
|
| 390 |
"onnx/onnx/components/vocoder.onnx": {
|
| 391 |
-
"sha256": "
|
| 392 |
-
"bytes":
|
| 393 |
},
|
| 394 |
"onnx/onnx/components/vocoder_128.onnx": {
|
| 395 |
-
"sha256": "
|
| 396 |
-
"bytes":
|
| 397 |
},
|
| 398 |
"onnx/onnx/components/vocoder_256.onnx": {
|
| 399 |
-
"sha256": "
|
| 400 |
-
"bytes":
|
| 401 |
},
|
| 402 |
"onnx/onnx/components/vocoder_384.onnx": {
|
| 403 |
-
"sha256": "
|
| 404 |
-
"bytes":
|
| 405 |
},
|
| 406 |
"onnx/onnx/components/vocoder_512.onnx": {
|
| 407 |
-
"sha256": "
|
| 408 |
-
"bytes":
|
| 409 |
},
|
| 410 |
"onnx/onnx/components/vocoder_768.onnx": {
|
| 411 |
-
"sha256": "
|
| 412 |
-
"bytes":
|
| 413 |
},
|
| 414 |
"onnx/onnx/g2p/model.onnx": {
|
| 415 |
-
"sha256": "
|
| 416 |
-
"bytes":
|
| 417 |
},
|
| 418 |
"onnx/onnx/g2p/phoneme_dict.json": {
|
| 419 |
"sha256": "9cfb40b2fd31d7a32351c33f90230062554a4dc0a44e89f722de211d42ed1875",
|
|
@@ -436,7 +208,7 @@
|
|
| 436 |
"bytes": 786473
|
| 437 |
},
|
| 438 |
"pytorch/g2p.pt": {
|
| 439 |
-
"sha256": "
|
| 440 |
"bytes": 119207485
|
| 441 |
},
|
| 442 |
"pytorch/phone_vocab.json": {
|
|
@@ -444,11 +216,11 @@
|
|
| 444 |
"bytes": 1793
|
| 445 |
},
|
| 446 |
"pytorch/release_config.json": {
|
| 447 |
-
"sha256": "
|
| 448 |
-
"bytes":
|
| 449 |
},
|
| 450 |
"pytorch/vector_estimator.pt": {
|
| 451 |
-
"sha256": "
|
| 452 |
"bytes": 267318145
|
| 453 |
},
|
| 454 |
"pytorch/vocoder.pt": {
|
|
|
|
| 4 |
"bytes": 11357
|
| 5 |
},
|
| 6 |
"README.md": {
|
| 7 |
+
"sha256": "a01cb02c74bcedd0072fc82b50bf0c5a9571b2d0e04800e9247756e67387f1c5",
|
| 8 |
+
"bytes": 10066
|
| 9 |
},
|
| 10 |
"THIRD_PARTY_NOTICES.md": {
|
| 11 |
"sha256": "3b793b8ee250cc711e4012ee42e9625a8a7e788bf12cab85a1abbd17b17644ca",
|
| 12 |
"bytes": 2818
|
| 13 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"litert/assets/fixed_references.json": {
|
| 15 |
"sha256": "d3c26e7e90d90fa719254ff1ff05dc4b391cd47231b7556c3c2ed5f63547925b",
|
| 16 |
"bytes": 1115042
|
|
|
|
| 60 |
"bytes": 28626144
|
| 61 |
},
|
| 62 |
"litert/litert/vector_context_encoder.tflite": {
|
| 63 |
+
"sha256": "a7d653507b92d8a5102f4281361e8ee8f03cf001b6889e1434ad1e760fbcf057",
|
| 64 |
"bytes": 7763584
|
| 65 |
},
|
| 66 |
"litert/litert/vector_estimator.tflite": {
|
| 67 |
+
"sha256": "51f6ce100d8565fa7979718ca34ad0b19d1e14f6525c41c46112dfbd1d5b30cd",
|
| 68 |
"bytes": 76550528
|
| 69 |
},
|
| 70 |
"litert/litert/vocoder.tflite": {
|
|
|
|
| 72 |
"bytes": 38613392
|
| 73 |
},
|
| 74 |
"litert/manifest.json": {
|
| 75 |
+
"sha256": "7462b9d6ee715d8c44400994d4065b8eb635b724b6bc29ed8cbdf668e662a444",
|
| 76 |
+
"bytes": 20172
|
| 77 |
},
|
| 78 |
"onnx/assets/fixed_references.json": {
|
| 79 |
"sha256": "d3c26e7e90d90fa719254ff1ff05dc4b391cd47231b7556c3c2ed5f63547925b",
|
|
|
|
| 116 |
"bytes": 433
|
| 117 |
},
|
| 118 |
"onnx/manifest.json": {
|
| 119 |
+
"sha256": "544760ec2d22c47666d687f5f162d531a038222ac33fb8aed81042ea8ad06703",
|
| 120 |
+
"bytes": 20550
|
| 121 |
},
|
| 122 |
"onnx/onnx/components/duration_predictor.onnx": {
|
| 123 |
+
"sha256": "7f30552820354c976ba585691ab3c9d94f272df15125b36ef695343801bf6259",
|
| 124 |
"bytes": 285227
|
| 125 |
},
|
| 126 |
"onnx/onnx/components/shared_weights.bin": {
|
| 127 |
+
"sha256": "e39b8dbc01078e6d7629057ec3a092fe17a40a090fb0d2839fbbd7dbaee7fbed",
|
| 128 |
"bytes": 208219968
|
| 129 |
},
|
| 130 |
"onnx/onnx/components/shared_weights.json": {
|
| 131 |
+
"sha256": "3acfa38030535361101703f2e124ee62061d89ff11c41af1055eeea4cca67765",
|
| 132 |
+
"bytes": 990204
|
| 133 |
},
|
| 134 |
"onnx/onnx/components/vector_context_encoder.onnx": {
|
| 135 |
+
"sha256": "79b04221744e831c80516cfee5120b024b43fba573b9ab943fe2bd89376a0dfd",
|
| 136 |
+
"bytes": 66364
|
| 137 |
},
|
| 138 |
"onnx/onnx/components/vector_estimator.onnx": {
|
| 139 |
+
"sha256": "5dd555761629826c32fea6aa5e3b25aae937cbe827336b8545efb3cd39d98811",
|
| 140 |
+
"bytes": 2800846
|
| 141 |
},
|
| 142 |
"onnx/onnx/components/vector_estimator_128.onnx": {
|
| 143 |
+
"sha256": "ae45282a20cadac7663d30d2e754a60b9164a15e5fbb390a6ec21f9ab4e3d33a",
|
| 144 |
+
"bytes": 915657
|
| 145 |
},
|
| 146 |
"onnx/onnx/components/vector_estimator_256.onnx": {
|
| 147 |
+
"sha256": "007f094ad391f1d444131f84fd09aaf31c9e3a2ab2d3a70af157f9cdc9fd0c95",
|
| 148 |
+
"bytes": 1184969
|
| 149 |
},
|
| 150 |
"onnx/onnx/components/vector_estimator_384.onnx": {
|
| 151 |
+
"sha256": "dcd1337c9024c6bdcba4698f4c93a13d51fed56c5b55fced6fcefe2f6196de4a",
|
| 152 |
+
"bytes": 1454281
|
| 153 |
},
|
| 154 |
"onnx/onnx/components/vector_estimator_512.onnx": {
|
| 155 |
+
"sha256": "8d4c522cfc7d2167dbc7ec4017e14757878b52aedebf7fd522e7a0cfe0a19096",
|
| 156 |
+
"bytes": 1723593
|
| 157 |
},
|
| 158 |
"onnx/onnx/components/vector_estimator_768.onnx": {
|
| 159 |
+
"sha256": "dc186567046dc1eb017329f38f11419efc31f6749b1344fca8abb55c49b6b516",
|
| 160 |
+
"bytes": 2262218
|
| 161 |
},
|
| 162 |
"onnx/onnx/components/vocoder.onnx": {
|
| 163 |
+
"sha256": "9f2343d201977fec1ca729de290ae969ff3457d6fa14bc3daa91dbee6d0088db",
|
| 164 |
+
"bytes": 122563
|
| 165 |
},
|
| 166 |
"onnx/onnx/components/vocoder_128.onnx": {
|
| 167 |
+
"sha256": "44b23f50ed8cd49cbff3a43e435fc35780e3cb63f5169ff5f9613b31869c15e4",
|
| 168 |
+
"bytes": 122563
|
| 169 |
},
|
| 170 |
"onnx/onnx/components/vocoder_256.onnx": {
|
| 171 |
+
"sha256": "6ad741f17902a63aa17d474ad6862cdcfeba796a19f40a892f008cf4f623d884",
|
| 172 |
+
"bytes": 122562
|
| 173 |
},
|
| 174 |
"onnx/onnx/components/vocoder_384.onnx": {
|
| 175 |
+
"sha256": "2fc1a749fd557d17ca352a269dacf042f4ca1da750ef74bc5e4982d2a8f9f533",
|
| 176 |
+
"bytes": 122563
|
| 177 |
},
|
| 178 |
"onnx/onnx/components/vocoder_512.onnx": {
|
| 179 |
+
"sha256": "b7cc541079751236d3612f457c25c45748d986d715e836293cffa23336f31b80",
|
| 180 |
+
"bytes": 122563
|
| 181 |
},
|
| 182 |
"onnx/onnx/components/vocoder_768.onnx": {
|
| 183 |
+
"sha256": "4725a2e9b599a5dd393e5454413282974856224e7913aa3701b6629134bb544c",
|
| 184 |
+
"bytes": 122564
|
| 185 |
},
|
| 186 |
"onnx/onnx/g2p/model.onnx": {
|
| 187 |
+
"sha256": "b733b7cedef6ec1c1822771f8b5d7ce430fdc7b4c4d7aac0617044419d0e3296",
|
| 188 |
+
"bytes": 40420257
|
| 189 |
},
|
| 190 |
"onnx/onnx/g2p/phoneme_dict.json": {
|
| 191 |
"sha256": "9cfb40b2fd31d7a32351c33f90230062554a4dc0a44e89f722de211d42ed1875",
|
|
|
|
| 208 |
"bytes": 786473
|
| 209 |
},
|
| 210 |
"pytorch/g2p.pt": {
|
| 211 |
+
"sha256": "c1aff82582456abc7667cf471a045ebaea3296a6b74240cc5e40b4686f643950",
|
| 212 |
"bytes": 119207485
|
| 213 |
},
|
| 214 |
"pytorch/phone_vocab.json": {
|
|
|
|
| 216 |
"bytes": 1793
|
| 217 |
},
|
| 218 |
"pytorch/release_config.json": {
|
| 219 |
+
"sha256": "b8e900aad0ec09e4b2e96f0d93542df14e271ea7e57c603c542acdef0f80cc6c",
|
| 220 |
+
"bytes": 842
|
| 221 |
},
|
| 222 |
"pytorch/vector_estimator.pt": {
|
| 223 |
+
"sha256": "556caf9f64a97329679ca99b3e6b59e1ecfb8ae312ad2321d10e7ba1e979b1da",
|
| 224 |
"bytes": 267318145
|
| 225 |
},
|
| 226 |
"pytorch/vocoder.pt": {
|
coreai/assets/fixed_references.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
coreai/assets/g2p/export_config.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"batch_dynamic": true,
|
| 3 |
-
"format": "scyllasband_g2p",
|
| 4 |
-
"input_granularity": "phrase",
|
| 5 |
-
"languages": [
|
| 6 |
-
"de",
|
| 7 |
-
"en_gb",
|
| 8 |
-
"en_us",
|
| 9 |
-
"es",
|
| 10 |
-
"fr",
|
| 11 |
-
"it",
|
| 12 |
-
"vi"
|
| 13 |
-
],
|
| 14 |
-
"model_type": "transformer",
|
| 15 |
-
"onnx_export_batch_size": 4,
|
| 16 |
-
"onnx_export_layout": "batch_first",
|
| 17 |
-
"onnx_export_max_batch_size": 256,
|
| 18 |
-
"onnx_exporter": "dynamo",
|
| 19 |
-
"onnx_fp32_model": "model.onnx",
|
| 20 |
-
"onnx_model": "model.onnx",
|
| 21 |
-
"onnx_padded_output": "ctc_blank",
|
| 22 |
-
"onnx_quantization": "none",
|
| 23 |
-
"onnx_quantized_parity_tolerance": 3.0,
|
| 24 |
-
"opset": 18,
|
| 25 |
-
"phoneme_token_mode": "char",
|
| 26 |
-
"phrase_rows_per_language": 200000,
|
| 27 |
-
"preserve_commas": true,
|
| 28 |
-
"punctuation_silence_target": "explicit_silence",
|
| 29 |
-
"release_role": "fp32_bundle_frontend",
|
| 30 |
-
"source_checkpoint": "output/deepphonemizer_multilingual/model_v10_7lang/checkpoints/model_step_250k.pt",
|
| 31 |
-
"training_mix": "phrase_word_chunked_clean",
|
| 32 |
-
"word_rows_per_language": 200000
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/assets/g2p/language_map.json
DELETED
|
@@ -1,47 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"american": "en_us",
|
| 3 |
-
"american_english": "en_us",
|
| 4 |
-
"british": "en_gb",
|
| 5 |
-
"british_english": "en_gb",
|
| 6 |
-
"de": "de",
|
| 7 |
-
"de_de": "de",
|
| 8 |
-
"deu": "de",
|
| 9 |
-
"en": "en_us",
|
| 10 |
-
"en-gb": "en_gb",
|
| 11 |
-
"en-uk": "en_gb",
|
| 12 |
-
"en-us": "en_us",
|
| 13 |
-
"en_gb": "en_gb",
|
| 14 |
-
"en_uk": "en_gb",
|
| 15 |
-
"en_us": "en_us",
|
| 16 |
-
"eng": "en_us",
|
| 17 |
-
"eng_gb": "en_gb",
|
| 18 |
-
"eng_us": "en_us",
|
| 19 |
-
"english": "en_us",
|
| 20 |
-
"english_gb": "en_gb",
|
| 21 |
-
"english_uk": "en_gb",
|
| 22 |
-
"english_us": "en_us",
|
| 23 |
-
"es": "es",
|
| 24 |
-
"es_es": "es",
|
| 25 |
-
"es_mx": "es",
|
| 26 |
-
"fr": "fr",
|
| 27 |
-
"fr_fr": "fr",
|
| 28 |
-
"fra": "fr",
|
| 29 |
-
"fre": "fr",
|
| 30 |
-
"french": "fr",
|
| 31 |
-
"gb": "en_gb",
|
| 32 |
-
"ger": "de",
|
| 33 |
-
"german": "de",
|
| 34 |
-
"it": "it",
|
| 35 |
-
"it_it": "it",
|
| 36 |
-
"ita": "it",
|
| 37 |
-
"italian": "it",
|
| 38 |
-
"spa": "es",
|
| 39 |
-
"spanish": "es",
|
| 40 |
-
"uk": "en_gb",
|
| 41 |
-
"us": "en_us",
|
| 42 |
-
"vi": "vi",
|
| 43 |
-
"vi_hn": "vi",
|
| 44 |
-
"vi_vn": "vi",
|
| 45 |
-
"vie": "vi",
|
| 46 |
-
"vietnamese": "vi"
|
| 47 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/assets/g2p/normalization.json
DELETED
|
@@ -1,40 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"contract": {
|
| 3 |
-
"colon_semicolon_classes": "preserved",
|
| 4 |
-
"dot_runs_two_or_more": "ellipsis_three_dots",
|
| 5 |
-
"homogeneous_terminal_runs": "single_mark",
|
| 6 |
-
"lexical_hyphen": "space_no_pause",
|
| 7 |
-
"mixed_question_exclamation": "leading_mark",
|
| 8 |
-
"non_acoustic_modifiers": [
|
| 9 |
-
"stress",
|
| 10 |
-
"length",
|
| 11 |
-
"unicode_combining"
|
| 12 |
-
],
|
| 13 |
-
"ok_spoken_form": "okay",
|
| 14 |
-
"punctuation_silence_target": "explicit_silence",
|
| 15 |
-
"syntactic_dash": "em_dash_pause",
|
| 16 |
-
"training_phone_source": "espeak",
|
| 17 |
-
"version": "scyllasband_spoken_text_v2_2026_08_05"
|
| 18 |
-
},
|
| 19 |
-
"contract_sha256": "d8fd1b2415d0d100d1c70237a4469117ee6b73d0e4da703e4654c83192779cc4",
|
| 20 |
-
"contract_version": "scyllasband_spoken_text_v2_2026_08_05",
|
| 21 |
-
"expand_currency": true,
|
| 22 |
-
"expand_dates": true,
|
| 23 |
-
"expand_numbers": true,
|
| 24 |
-
"expand_ordinals": true,
|
| 25 |
-
"expand_percentages": true,
|
| 26 |
-
"expand_times": true,
|
| 27 |
-
"languages": [
|
| 28 |
-
"en",
|
| 29 |
-
"en_us",
|
| 30 |
-
"en_gb",
|
| 31 |
-
"es",
|
| 32 |
-
"it",
|
| 33 |
-
"fr",
|
| 34 |
-
"de",
|
| 35 |
-
"vi"
|
| 36 |
-
],
|
| 37 |
-
"normalize_at_sign": true,
|
| 38 |
-
"normalize_punctuation": true,
|
| 39 |
-
"normalizer": "SpokenTextNormalizer"
|
| 40 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/assets/g2p/phoneme_dict.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"de": {},
|
| 3 |
-
"en_gb": {},
|
| 4 |
-
"en_us": {},
|
| 5 |
-
"es": {},
|
| 6 |
-
"fr": {},
|
| 7 |
-
"it": {},
|
| 8 |
-
"vi": {}
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/assets/g2p/pronunciation_overrides.json
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"format": "scyllasband_g2p_pronunciation_overrides_v1",
|
| 3 |
-
"languages": {}
|
| 4 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/assets/g2p/tokenizer.json
DELETED
|
@@ -1,517 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"format": "deepphonemizer_forward_ctc",
|
| 3 |
-
"languages": [
|
| 4 |
-
"de",
|
| 5 |
-
"en_gb",
|
| 6 |
-
"en_us",
|
| 7 |
-
"es",
|
| 8 |
-
"fr",
|
| 9 |
-
"it",
|
| 10 |
-
"vi"
|
| 11 |
-
],
|
| 12 |
-
"char_repeats": 4,
|
| 13 |
-
"lowercase": true,
|
| 14 |
-
"phoneme_token_mode": "char",
|
| 15 |
-
"text_symbols": {
|
| 16 |
-
"_": 0,
|
| 17 |
-
"<de>": 1,
|
| 18 |
-
"<en_gb>": 2,
|
| 19 |
-
"<en_us>": 3,
|
| 20 |
-
"<es>": 4,
|
| 21 |
-
"<fr>": 5,
|
| 22 |
-
"<it>": 6,
|
| 23 |
-
"<vi>": 7,
|
| 24 |
-
"<end>": 8,
|
| 25 |
-
"\b": 9,
|
| 26 |
-
" ": 10,
|
| 27 |
-
"!": 11,
|
| 28 |
-
"\"": 12,
|
| 29 |
-
"#": 13,
|
| 30 |
-
"$": 14,
|
| 31 |
-
"%": 15,
|
| 32 |
-
"&": 16,
|
| 33 |
-
"'": 17,
|
| 34 |
-
"(": 18,
|
| 35 |
-
")": 19,
|
| 36 |
-
"*": 20,
|
| 37 |
-
"+": 21,
|
| 38 |
-
",": 22,
|
| 39 |
-
"-": 23,
|
| 40 |
-
".": 24,
|
| 41 |
-
"/": 25,
|
| 42 |
-
"0": 26,
|
| 43 |
-
"1": 27,
|
| 44 |
-
"2": 28,
|
| 45 |
-
"3": 29,
|
| 46 |
-
"4": 30,
|
| 47 |
-
"5": 31,
|
| 48 |
-
"6": 32,
|
| 49 |
-
"7": 33,
|
| 50 |
-
"8": 34,
|
| 51 |
-
"9": 35,
|
| 52 |
-
":": 36,
|
| 53 |
-
";": 37,
|
| 54 |
-
"<": 38,
|
| 55 |
-
"=": 39,
|
| 56 |
-
">": 40,
|
| 57 |
-
"?": 41,
|
| 58 |
-
"@": 42,
|
| 59 |
-
"A": 43,
|
| 60 |
-
"B": 44,
|
| 61 |
-
"C": 45,
|
| 62 |
-
"D": 46,
|
| 63 |
-
"E": 47,
|
| 64 |
-
"F": 48,
|
| 65 |
-
"G": 49,
|
| 66 |
-
"H": 50,
|
| 67 |
-
"I": 51,
|
| 68 |
-
"J": 52,
|
| 69 |
-
"K": 53,
|
| 70 |
-
"L": 54,
|
| 71 |
-
"M": 55,
|
| 72 |
-
"N": 56,
|
| 73 |
-
"O": 57,
|
| 74 |
-
"P": 58,
|
| 75 |
-
"Q": 59,
|
| 76 |
-
"R": 60,
|
| 77 |
-
"S": 61,
|
| 78 |
-
"T": 62,
|
| 79 |
-
"U": 63,
|
| 80 |
-
"V": 64,
|
| 81 |
-
"W": 65,
|
| 82 |
-
"X": 66,
|
| 83 |
-
"Y": 67,
|
| 84 |
-
"Z": 68,
|
| 85 |
-
"[": 69,
|
| 86 |
-
"\\": 70,
|
| 87 |
-
"]": 71,
|
| 88 |
-
"^": 72,
|
| 89 |
-
"`": 73,
|
| 90 |
-
"a": 74,
|
| 91 |
-
"b": 75,
|
| 92 |
-
"c": 76,
|
| 93 |
-
"d": 77,
|
| 94 |
-
"e": 78,
|
| 95 |
-
"f": 79,
|
| 96 |
-
"g": 80,
|
| 97 |
-
"h": 81,
|
| 98 |
-
"i": 82,
|
| 99 |
-
"j": 83,
|
| 100 |
-
"k": 84,
|
| 101 |
-
"l": 85,
|
| 102 |
-
"m": 86,
|
| 103 |
-
"n": 87,
|
| 104 |
-
"o": 88,
|
| 105 |
-
"p": 89,
|
| 106 |
-
"q": 90,
|
| 107 |
-
"r": 91,
|
| 108 |
-
"s": 92,
|
| 109 |
-
"t": 93,
|
| 110 |
-
"u": 94,
|
| 111 |
-
"v": 95,
|
| 112 |
-
"w": 96,
|
| 113 |
-
"x": 97,
|
| 114 |
-
"y": 98,
|
| 115 |
-
"z": 99,
|
| 116 |
-
"{": 100,
|
| 117 |
-
"|": 101,
|
| 118 |
-
"}": 102,
|
| 119 |
-
"~": 103,
|
| 120 |
-
"¡": 104,
|
| 121 |
-
"¢": 105,
|
| 122 |
-
"£": 106,
|
| 123 |
-
"¥": 107,
|
| 124 |
-
"§": 108,
|
| 125 |
-
"ª": 109,
|
| 126 |
-
"«": 110,
|
| 127 |
-
"": 111,
|
| 128 |
-
"®": 112,
|
| 129 |
-
"°": 113,
|
| 130 |
-
"±": 114,
|
| 131 |
-
"²": 115,
|
| 132 |
-
"³": 116,
|
| 133 |
-
"´": 117,
|
| 134 |
-
"¶": 118,
|
| 135 |
-
"·": 119,
|
| 136 |
-
"¹": 120,
|
| 137 |
-
"º": 121,
|
| 138 |
-
"»": 122,
|
| 139 |
-
"¼": 123,
|
| 140 |
-
"½": 124,
|
| 141 |
-
"¾": 125,
|
| 142 |
-
"¿": 126,
|
| 143 |
-
"À": 127,
|
| 144 |
-
"Á": 128,
|
| 145 |
-
"Â": 129,
|
| 146 |
-
"Ä": 130,
|
| 147 |
-
"Å": 131,
|
| 148 |
-
"Æ": 132,
|
| 149 |
-
"Ç": 133,
|
| 150 |
-
"È": 134,
|
| 151 |
-
"É": 135,
|
| 152 |
-
"Ê": 136,
|
| 153 |
-
"Í": 137,
|
| 154 |
-
"Ï": 138,
|
| 155 |
-
"Ñ": 139,
|
| 156 |
-
"Ó": 140,
|
| 157 |
-
"Ô": 141,
|
| 158 |
-
"Ö": 142,
|
| 159 |
-
"×": 143,
|
| 160 |
-
"Ù": 144,
|
| 161 |
-
"Ú": 145,
|
| 162 |
-
"Ü": 146,
|
| 163 |
-
"Ý": 147,
|
| 164 |
-
"Þ": 148,
|
| 165 |
-
"ß": 149,
|
| 166 |
-
"à": 150,
|
| 167 |
-
"á": 151,
|
| 168 |
-
"â": 152,
|
| 169 |
-
"ã": 153,
|
| 170 |
-
"ä": 154,
|
| 171 |
-
"å": 155,
|
| 172 |
-
"æ": 156,
|
| 173 |
-
"ç": 157,
|
| 174 |
-
"è": 158,
|
| 175 |
-
"é": 159,
|
| 176 |
-
"ê": 160,
|
| 177 |
-
"ë": 161,
|
| 178 |
-
"ì": 162,
|
| 179 |
-
"í": 163,
|
| 180 |
-
"î": 164,
|
| 181 |
-
"ï": 165,
|
| 182 |
-
"ð": 166,
|
| 183 |
-
"ñ": 167,
|
| 184 |
-
"ò": 168,
|
| 185 |
-
"ó": 169,
|
| 186 |
-
"ô": 170,
|
| 187 |
-
"õ": 171,
|
| 188 |
-
"ö": 172,
|
| 189 |
-
"ø": 173,
|
| 190 |
-
"ù": 174,
|
| 191 |
-
"ú": 175,
|
| 192 |
-
"û": 176,
|
| 193 |
-
"ü": 177,
|
| 194 |
-
"ý": 178,
|
| 195 |
-
"þ": 179,
|
| 196 |
-
"ÿ": 180,
|
| 197 |
-
"ā": 181,
|
| 198 |
-
"Ă": 182,
|
| 199 |
-
"ă": 183,
|
| 200 |
-
"ą": 184,
|
| 201 |
-
"ć": 185,
|
| 202 |
-
"č": 186,
|
| 203 |
-
"Đ": 187,
|
| 204 |
-
"đ": 188,
|
| 205 |
-
"ē": 189,
|
| 206 |
-
"ė": 190,
|
| 207 |
-
"ę": 191,
|
| 208 |
-
"ğ": 192,
|
| 209 |
-
"ġ": 193,
|
| 210 |
-
"ĩ": 194,
|
| 211 |
-
"ī": 195,
|
| 212 |
-
"ļ": 196,
|
| 213 |
-
"ł": 197,
|
| 214 |
-
"ń": 198,
|
| 215 |
-
"Ō": 199,
|
| 216 |
-
"ō": 200,
|
| 217 |
-
"Œ": 201,
|
| 218 |
-
"œ": 202,
|
| 219 |
-
"ŕ": 203,
|
| 220 |
-
"ś": 204,
|
| 221 |
-
"ş": 205,
|
| 222 |
-
"š": 206,
|
| 223 |
-
"ŧ": 207,
|
| 224 |
-
"ũ": 208,
|
| 225 |
-
"ū": 209,
|
| 226 |
-
"ŭ": 210,
|
| 227 |
-
"ů": 211,
|
| 228 |
-
"ű": 212,
|
| 229 |
-
"ż": 213,
|
| 230 |
-
"Ž": 214,
|
| 231 |
-
"ž": 215,
|
| 232 |
-
"ſ": 216,
|
| 233 |
-
"Ơ": 217,
|
| 234 |
-
"ơ": 218,
|
| 235 |
-
"Ư": 219,
|
| 236 |
-
"ư": 220,
|
| 237 |
-
"ǁ": 221,
|
| 238 |
-
"ǂ": 222,
|
| 239 |
-
"ǐ": 223,
|
| 240 |
-
"ǘ": 224,
|
| 241 |
-
"ǧ": 225,
|
| 242 |
-
"ș": 226,
|
| 243 |
-
"Ȝ": 227,
|
| 244 |
-
"ȝ": 228,
|
| 245 |
-
"ȟ": 229,
|
| 246 |
-
"ɛ": 230,
|
| 247 |
-
"ʰ": 231,
|
| 248 |
-
"ˆ": 232,
|
| 249 |
-
"ˈ": 233,
|
| 250 |
-
"ˢ": 234,
|
| 251 |
-
"̃": 235,
|
| 252 |
-
"̍": 236,
|
| 253 |
-
"̣": 237,
|
| 254 |
-
"̱": 238,
|
| 255 |
-
"͈": 239,
|
| 256 |
-
"α": 240,
|
| 257 |
-
"β": 241,
|
| 258 |
-
"γ": 242,
|
| 259 |
-
"δ": 243,
|
| 260 |
-
"ε": 244,
|
| 261 |
-
"η": 245,
|
| 262 |
-
"κ": 246,
|
| 263 |
-
"μ": 247,
|
| 264 |
-
"ξ": 248,
|
| 265 |
-
"π": 249,
|
| 266 |
-
"ς": 250,
|
| 267 |
-
"σ": 251,
|
| 268 |
-
"χ": 252,
|
| 269 |
-
"ψ": 253,
|
| 270 |
-
"а": 254,
|
| 271 |
-
"д": 255,
|
| 272 |
-
"е": 256,
|
| 273 |
-
"з": 257,
|
| 274 |
-
"и": 258,
|
| 275 |
-
"к": 259,
|
| 276 |
-
"л": 260,
|
| 277 |
-
"о": 261,
|
| 278 |
-
"п": 262,
|
| 279 |
-
"р": 263,
|
| 280 |
-
"с": 264,
|
| 281 |
-
"т": 265,
|
| 282 |
-
"ч": 266,
|
| 283 |
-
"ь": 267,
|
| 284 |
-
"ง": 268,
|
| 285 |
-
"ย": 269,
|
| 286 |
-
"า": 270,
|
| 287 |
-
"่": 271,
|
| 288 |
-
"ည": 272,
|
| 289 |
-
"လ": 273,
|
| 290 |
-
"း": 274,
|
| 291 |
-
"်": 275,
|
| 292 |
-
"ᵈ": 276,
|
| 293 |
-
"ᵗ": 277,
|
| 294 |
-
"ḅ": 278,
|
| 295 |
-
"ḍ": 279,
|
| 296 |
-
"ḳ": 280,
|
| 297 |
-
"ṅ": 281,
|
| 298 |
-
"Ṭ": 282,
|
| 299 |
-
"ẓ": 283,
|
| 300 |
-
"ạ": 284,
|
| 301 |
-
"Ả": 285,
|
| 302 |
-
"ả": 286,
|
| 303 |
-
"Ấ": 287,
|
| 304 |
-
"ấ": 288,
|
| 305 |
-
"ầ": 289,
|
| 306 |
-
"ẩ": 290,
|
| 307 |
-
"ẫ": 291,
|
| 308 |
-
"ậ": 292,
|
| 309 |
-
"ắ": 293,
|
| 310 |
-
"ằ": 294,
|
| 311 |
-
"ẳ": 295,
|
| 312 |
-
"ẵ": 296,
|
| 313 |
-
"ặ": 297,
|
| 314 |
-
"ẹ": 298,
|
| 315 |
-
"ẻ": 299,
|
| 316 |
-
"ẽ": 300,
|
| 317 |
-
"Ế": 301,
|
| 318 |
-
"ế": 302,
|
| 319 |
-
"Ề": 303,
|
| 320 |
-
"ề": 304,
|
| 321 |
-
"ể": 305,
|
| 322 |
-
"ễ": 306,
|
| 323 |
-
"ệ": 307,
|
| 324 |
-
"ỉ": 308,
|
| 325 |
-
"ị": 309,
|
| 326 |
-
"ọ": 310,
|
| 327 |
-
"ỏ": 311,
|
| 328 |
-
"Ố": 312,
|
| 329 |
-
"ố": 313,
|
| 330 |
-
"Ồ": 314,
|
| 331 |
-
"ồ": 315,
|
| 332 |
-
"Ổ": 316,
|
| 333 |
-
"ổ": 317,
|
| 334 |
-
"ỗ": 318,
|
| 335 |
-
"Ộ": 319,
|
| 336 |
-
"ộ": 320,
|
| 337 |
-
"ớ": 321,
|
| 338 |
-
"Ờ": 322,
|
| 339 |
-
"ờ": 323,
|
| 340 |
-
"Ở": 324,
|
| 341 |
-
"ở": 325,
|
| 342 |
-
"ỡ": 326,
|
| 343 |
-
"ợ": 327,
|
| 344 |
-
"ụ": 328,
|
| 345 |
-
"ủ": 329,
|
| 346 |
-
"Ứ": 330,
|
| 347 |
-
"ứ": 331,
|
| 348 |
-
"Ừ": 332,
|
| 349 |
-
"ừ": 333,
|
| 350 |
-
"ử": 334,
|
| 351 |
-
"ữ": 335,
|
| 352 |
-
"ự": 336,
|
| 353 |
-
"ỳ": 337,
|
| 354 |
-
"ỵ": 338,
|
| 355 |
-
"Ỷ": 339,
|
| 356 |
-
"ỷ": 340,
|
| 357 |
-
"ỹ": 341,
|
| 358 |
-
"ὖ": 342,
|
| 359 |
-
"ὼ": 343,
|
| 360 |
-
"ῆ": 344,
|
| 361 |
-
"": 345,
|
| 362 |
-
"‐": 346,
|
| 363 |
-
"—": 347,
|
| 364 |
-
"―": 348,
|
| 365 |
-
"†": 349,
|
| 366 |
-
"•": 350,
|
| 367 |
-
"…": 351,
|
| 368 |
-
"‰": 352,
|
| 369 |
-
"′": 353,
|
| 370 |
-
"″": 354,
|
| 371 |
-
"⁄": 355,
|
| 372 |
-
"⁷": 356,
|
| 373 |
-
"⁻": 357,
|
| 374 |
-
"₀": 358,
|
| 375 |
-
"₁": 359,
|
| 376 |
-
"₂": 360,
|
| 377 |
-
"₃": 361,
|
| 378 |
-
"₄": 362,
|
| 379 |
-
"₅": 363,
|
| 380 |
-
"₆": 364,
|
| 381 |
-
"₇": 365,
|
| 382 |
-
"₈": 366,
|
| 383 |
-
"€": 367,
|
| 384 |
-
"₹": 368,
|
| 385 |
-
"⅓": 369,
|
| 386 |
-
"⅔": 370,
|
| 387 |
-
"⅖": 371,
|
| 388 |
-
"⅙": 372,
|
| 389 |
-
"⅛": 373,
|
| 390 |
-
"⅝": 374,
|
| 391 |
-
"√": 375,
|
| 392 |
-
"│": 376,
|
| 393 |
-
"♦": 377,
|
| 394 |
-
"⚓": 378,
|
| 395 |
-
"✈": 379,
|
| 396 |
-
"✠": 380,
|
| 397 |
-
"✨": 381,
|
| 398 |
-
"⟙": 382,
|
| 399 |
-
"⸺": 383,
|
| 400 |
-
"。": 384,
|
| 401 |
-
"〈": 385,
|
| 402 |
-
"な": 386,
|
| 403 |
-
"三": 387,
|
| 404 |
-
"次": 388,
|
| 405 |
-
"肿": 389,
|
| 406 |
-
"臃": 390,
|
| 407 |
-
"구": 391,
|
| 408 |
-
"로": 392,
|
| 409 |
-
"요": 393,
|
| 410 |
-
"ﷺ": 394,
|
| 411 |
-
"️": 395,
|
| 412 |
-
"𝑥": 396,
|
| 413 |
-
"𝑦": 397,
|
| 414 |
-
"🌊": 398,
|
| 415 |
-
"🌿": 399,
|
| 416 |
-
"💦": 400,
|
| 417 |
-
"💨": 401
|
| 418 |
-
},
|
| 419 |
-
"phoneme_symbols": {
|
| 420 |
-
"0": "_",
|
| 421 |
-
"1": "<de>",
|
| 422 |
-
"2": "<en_gb>",
|
| 423 |
-
"3": "<en_us>",
|
| 424 |
-
"4": "<es>",
|
| 425 |
-
"5": "<fr>",
|
| 426 |
-
"6": "<it>",
|
| 427 |
-
"7": "<vi>",
|
| 428 |
-
"8": "<end>",
|
| 429 |
-
"9": " ",
|
| 430 |
-
"10": "!",
|
| 431 |
-
"11": ",",
|
| 432 |
-
"12": "-",
|
| 433 |
-
"13": ".",
|
| 434 |
-
"14": "1",
|
| 435 |
-
"15": "2",
|
| 436 |
-
"16": "4",
|
| 437 |
-
"17": "5",
|
| 438 |
-
"18": "6",
|
| 439 |
-
"19": "7",
|
| 440 |
-
"20": ":",
|
| 441 |
-
"21": ";",
|
| 442 |
-
"22": "?",
|
| 443 |
-
"23": "a",
|
| 444 |
-
"24": "b",
|
| 445 |
-
"25": "c",
|
| 446 |
-
"26": "d",
|
| 447 |
-
"27": "e",
|
| 448 |
-
"28": "f",
|
| 449 |
-
"29": "h",
|
| 450 |
-
"30": "i",
|
| 451 |
-
"31": "j",
|
| 452 |
-
"32": "k",
|
| 453 |
-
"33": "l",
|
| 454 |
-
"34": "m",
|
| 455 |
-
"35": "n",
|
| 456 |
-
"36": "o",
|
| 457 |
-
"37": "p",
|
| 458 |
-
"38": "q",
|
| 459 |
-
"39": "r",
|
| 460 |
-
"40": "s",
|
| 461 |
-
"41": "t",
|
| 462 |
-
"42": "u",
|
| 463 |
-
"43": "v",
|
| 464 |
-
"44": "w",
|
| 465 |
-
"45": "x",
|
| 466 |
-
"46": "y",
|
| 467 |
-
"47": "z",
|
| 468 |
-
"48": "«",
|
| 469 |
-
"49": "»",
|
| 470 |
-
"50": "æ",
|
| 471 |
-
"51": "ç",
|
| 472 |
-
"52": "ð",
|
| 473 |
-
"53": "ø",
|
| 474 |
-
"54": "ŋ",
|
| 475 |
-
"55": "œ",
|
| 476 |
-
"56": "ɐ",
|
| 477 |
-
"57": "ɑ",
|
| 478 |
-
"58": "ɒ",
|
| 479 |
-
"59": "ɔ",
|
| 480 |
-
"60": "ɗ",
|
| 481 |
-
"61": "ə",
|
| 482 |
-
"62": "ɚ",
|
| 483 |
-
"63": "ɛ",
|
| 484 |
-
"64": "ɜ",
|
| 485 |
-
"65": "ɟ",
|
| 486 |
-
"66": "ɡ",
|
| 487 |
-
"67": "ɣ",
|
| 488 |
-
"68": "ɨ",
|
| 489 |
-
"69": "ɪ",
|
| 490 |
-
"70": "ɬ",
|
| 491 |
-
"71": "ɯ",
|
| 492 |
-
"72": "ɲ",
|
| 493 |
-
"73": "ɹ",
|
| 494 |
-
"74": "ɾ",
|
| 495 |
-
"75": "ʁ",
|
| 496 |
-
"76": "ʃ",
|
| 497 |
-
"77": "ʊ",
|
| 498 |
-
"78": "ʌ",
|
| 499 |
-
"79": "ʎ",
|
| 500 |
-
"80": "ʐ",
|
| 501 |
-
"81": "ʒ",
|
| 502 |
-
"82": "ʔ",
|
| 503 |
-
"83": "ʝ",
|
| 504 |
-
"84": "ʲ",
|
| 505 |
-
"85": "ˈ",
|
| 506 |
-
"86": "ˌ",
|
| 507 |
-
"87": "ː",
|
| 508 |
-
"88": "̃",
|
| 509 |
-
"89": "̩",
|
| 510 |
-
"90": "̪",
|
| 511 |
-
"91": "β",
|
| 512 |
-
"92": "θ",
|
| 513 |
-
"93": "ᵻ",
|
| 514 |
-
"94": "—",
|
| 515 |
-
"95": "…"
|
| 516 |
-
}
|
| 517 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/assets/languages.json
DELETED
|
@@ -1,30 +0,0 @@
|
|
| 1 |
-
[
|
| 2 |
-
{
|
| 3 |
-
"id": "en_us",
|
| 4 |
-
"index": 0
|
| 5 |
-
},
|
| 6 |
-
{
|
| 7 |
-
"id": "en_gb",
|
| 8 |
-
"index": 1
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"id": "es",
|
| 12 |
-
"index": 2
|
| 13 |
-
},
|
| 14 |
-
{
|
| 15 |
-
"id": "it",
|
| 16 |
-
"index": 3
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"id": "fr",
|
| 20 |
-
"index": 4
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"id": "de",
|
| 24 |
-
"index": 5
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"id": "vi",
|
| 28 |
-
"index": 6
|
| 29 |
-
}
|
| 30 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/assets/phone_vocab.json
DELETED
|
@@ -1,111 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"schema_version": 1,
|
| 3 |
-
"mode": "scyllasband_ipa_phone_symbols",
|
| 4 |
-
"special_tokens": [
|
| 5 |
-
"<pad>",
|
| 6 |
-
"<unk>",
|
| 7 |
-
"<sil>",
|
| 8 |
-
"<pause_comma>",
|
| 9 |
-
"<pause_semicolon>",
|
| 10 |
-
"<pause_colon>",
|
| 11 |
-
"<pause_dash>",
|
| 12 |
-
"<ellipsis>",
|
| 13 |
-
"<end_stmt>",
|
| 14 |
-
"<end_question>",
|
| 15 |
-
"<end_exclaim>",
|
| 16 |
-
"<ctx_sentence_start>",
|
| 17 |
-
"<ctx_continuation>",
|
| 18 |
-
"<ctx_sentence_end>",
|
| 19 |
-
"<ctx_chunk_continue>"
|
| 20 |
-
],
|
| 21 |
-
"vocab_size": 87,
|
| 22 |
-
"token_to_id": {
|
| 23 |
-
"<pad>": 0,
|
| 24 |
-
"<unk>": 1,
|
| 25 |
-
"<sil>": 2,
|
| 26 |
-
"<pause_comma>": 3,
|
| 27 |
-
"<pause_semicolon>": 4,
|
| 28 |
-
"<pause_colon>": 5,
|
| 29 |
-
"<pause_dash>": 6,
|
| 30 |
-
"<ellipsis>": 7,
|
| 31 |
-
"<end_stmt>": 8,
|
| 32 |
-
"<end_question>": 9,
|
| 33 |
-
"<end_exclaim>": 10,
|
| 34 |
-
"<ctx_sentence_start>": 11,
|
| 35 |
-
"<ctx_continuation>": 12,
|
| 36 |
-
"<ctx_sentence_end>": 13,
|
| 37 |
-
"<ctx_chunk_continue>": 14,
|
| 38 |
-
"1": 15,
|
| 39 |
-
"2": 16,
|
| 40 |
-
"4": 17,
|
| 41 |
-
"5": 18,
|
| 42 |
-
"6": 19,
|
| 43 |
-
"7": 20,
|
| 44 |
-
"a": 21,
|
| 45 |
-
"b": 22,
|
| 46 |
-
"c": 23,
|
| 47 |
-
"d": 24,
|
| 48 |
-
"e": 25,
|
| 49 |
-
"f": 26,
|
| 50 |
-
"h": 27,
|
| 51 |
-
"i": 28,
|
| 52 |
-
"j": 29,
|
| 53 |
-
"k": 30,
|
| 54 |
-
"l": 31,
|
| 55 |
-
"m": 32,
|
| 56 |
-
"n": 33,
|
| 57 |
-
"o": 34,
|
| 58 |
-
"p": 35,
|
| 59 |
-
"r": 36,
|
| 60 |
-
"s": 37,
|
| 61 |
-
"t": 38,
|
| 62 |
-
"u": 39,
|
| 63 |
-
"v": 40,
|
| 64 |
-
"w": 41,
|
| 65 |
-
"x": 42,
|
| 66 |
-
"y": 43,
|
| 67 |
-
"z": 44,
|
| 68 |
-
"æ": 45,
|
| 69 |
-
"ç": 46,
|
| 70 |
-
"ð": 47,
|
| 71 |
-
"ø": 48,
|
| 72 |
-
"ŋ": 49,
|
| 73 |
-
"œ": 50,
|
| 74 |
-
"ɐ": 51,
|
| 75 |
-
"ɑ": 52,
|
| 76 |
-
"ɒ": 53,
|
| 77 |
-
"ɔ": 54,
|
| 78 |
-
"ɗ": 55,
|
| 79 |
-
"ə": 56,
|
| 80 |
-
"ɚ": 57,
|
| 81 |
-
"ɛ": 58,
|
| 82 |
-
"ɜ": 59,
|
| 83 |
-
"ɟ": 60,
|
| 84 |
-
"ɡ": 61,
|
| 85 |
-
"ɣ": 62,
|
| 86 |
-
"ɪ": 63,
|
| 87 |
-
"ɯ": 64,
|
| 88 |
-
"ɲ": 65,
|
| 89 |
-
"ɹ": 66,
|
| 90 |
-
"ɾ": 67,
|
| 91 |
-
"ʁ": 68,
|
| 92 |
-
"ʃ": 69,
|
| 93 |
-
"ʊ": 70,
|
| 94 |
-
"ʌ": 71,
|
| 95 |
-
"ʎ": 72,
|
| 96 |
-
"ʐ": 73,
|
| 97 |
-
"ʒ": 74,
|
| 98 |
-
"ʔ": 75,
|
| 99 |
-
"ʝ": 76,
|
| 100 |
-
"ʲ": 77,
|
| 101 |
-
"ˈ": 78,
|
| 102 |
-
"ˌ": 79,
|
| 103 |
-
"ː": 80,
|
| 104 |
-
"̃": 81,
|
| 105 |
-
"̩": 82,
|
| 106 |
-
"̪": 83,
|
| 107 |
-
"β": 84,
|
| 108 |
-
"θ": 85,
|
| 109 |
-
"ᵻ": 86
|
| 110 |
-
}
|
| 111 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/assets/voices.json
DELETED
|
@@ -1,42 +0,0 @@
|
|
| 1 |
-
[
|
| 2 |
-
{
|
| 3 |
-
"id": "ariadne",
|
| 4 |
-
"index": 0
|
| 5 |
-
},
|
| 6 |
-
{
|
| 7 |
-
"id": "felix",
|
| 8 |
-
"index": 1
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"id": "gwen",
|
| 12 |
-
"index": 2
|
| 13 |
-
},
|
| 14 |
-
{
|
| 15 |
-
"id": "ink",
|
| 16 |
-
"index": 3
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"id": "max",
|
| 20 |
-
"index": 4
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"id": "orpheus",
|
| 24 |
-
"index": 5
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"id": "rex",
|
| 28 |
-
"index": 6
|
| 29 |
-
},
|
| 30 |
-
{
|
| 31 |
-
"id": "scylla",
|
| 32 |
-
"index": 7
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"id": "stone",
|
| 36 |
-
"index": 8
|
| 37 |
-
},
|
| 38 |
-
{
|
| 39 |
-
"id": "tuesday",
|
| 40 |
-
"index": 9
|
| 41 |
-
}
|
| 42 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/coreai/duration_predictor.aimodel/main.hash
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
BC�6 �����3����KS��m�X�����I
|
|
|
|
|
|
coreai/coreai/duration_predictor.aimodel/main.mlirb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4243d405361c9ebc82a0e233a3cb1bd5d64b5389a96ddd58947f14fb84b3c949
|
| 3 |
-
size 10884924
|
|
|
|
|
|
|
|
|
|
|
|
coreai/coreai/duration_predictor.aimodel/metadata.json
DELETED
|
@@ -1,5 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"assetVersion" : "2.0",
|
| 3 |
-
"producer" : "coreai-core 1.0.0b3",
|
| 4 |
-
"creationDate" : "20261005T221157Z"
|
| 5 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/coreai/g2p.aimodel/main.hash
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
�Bj�Yp*��vB
|
|
|
|
|
|
coreai/coreai/g2p.aimodel/main.mlirb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e7426aa159702a859176420d0c34b493da7d3dd97fa74fdeedb2ee4c4f0dce18
|
| 3 |
-
size 28377271
|
|
|
|
|
|
|
|
|
|
|
|
coreai/coreai/g2p.aimodel/metadata.json
DELETED
|
@@ -1,5 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"producer" : "coreai-core 1.0.0b3",
|
| 3 |
-
"creationDate" : "20261005T221156Z",
|
| 4 |
-
"assetVersion" : "2.0"
|
| 5 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/coreai/vector_context_encoder.aimodel/main.hash
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
��@�,�� ����4��r�YM�E�Ϡm����5
|
|
|
|
|
|
coreai/coreai/vector_context_encoder.aimodel/main.mlirb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9dca40e4aa2ce1cf2099c7c4ee34bbea72f2594d88459210cfa06dfc9592f135
|
| 3 |
-
size 8029277
|
|
|
|
|
|
|
|
|
|
|
|
coreai/coreai/vector_context_encoder.aimodel/metadata.json
DELETED
|
@@ -1,5 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"creationDate" : "20261005T221159Z",
|
| 3 |
-
"assetVersion" : "2.0",
|
| 4 |
-
"producer" : "coreai-core 1.0.0b3"
|
| 5 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/coreai/vector_estimator.aimodel/main.hash
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
M�� \�� -:��G�
|
|
|
|
|
|
coreai/coreai/vector_estimator.aimodel/main.mlirb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4dc8e41c5c9de01f2d3a9fd847a30df8b27ceec9aa0894b235f49181dcd664d2
|
| 3 |
-
size 63149068
|
|
|
|
|
|
|
|
|
|
|
|
coreai/coreai/vector_estimator.aimodel/metadata.json
DELETED
|
@@ -1,5 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"assetVersion" : "2.0",
|
| 3 |
-
"creationDate" : "20261005T221212Z",
|
| 4 |
-
"producer" : "coreai-core 1.0.0b3"
|
| 5 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/coreai/vocoder.aimodel/main.hash
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
|
|
|
|
|
|
coreai/coreai/vocoder.aimodel/main.mlirb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0e0d07b91327322c55da5081c7e3301565e92c5298dd9a5dfb74b71ee6074669
|
| 3 |
-
size 43811030
|
|
|
|
|
|
|
|
|
|
|
|
coreai/coreai/vocoder.aimodel/metadata.json
DELETED
|
@@ -1,5 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"creationDate" : "20261005T221220Z",
|
| 3 |
-
"producer" : "coreai-core 1.0.0b3",
|
| 4 |
-
"assetVersion" : "2.0"
|
| 5 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreai/manifest.json
DELETED
|
@@ -1,1003 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architecture": "scyllasband-duration-flow",
|
| 3 |
-
"assets": {
|
| 4 |
-
"fixed_delivery_references": "assets/fixed_references.json",
|
| 5 |
-
"g2p_config": "assets/g2p/export_config.json",
|
| 6 |
-
"g2p_language_map": "assets/g2p/language_map.json",
|
| 7 |
-
"g2p_normalization": "assets/g2p/normalization.json",
|
| 8 |
-
"g2p_phoneme_dict": "assets/g2p/phoneme_dict.json",
|
| 9 |
-
"g2p_pronunciation_overrides": "assets/g2p/pronunciation_overrides.json",
|
| 10 |
-
"g2p_tokenizer": "assets/g2p/tokenizer.json",
|
| 11 |
-
"language_index": "assets/languages.json",
|
| 12 |
-
"phone_vocab": "assets/phone_vocab.json",
|
| 13 |
-
"voice_index": "assets/voices.json"
|
| 14 |
-
},
|
| 15 |
-
"audio": {
|
| 16 |
-
"hop_length": 256,
|
| 17 |
-
"latent_dim": 24,
|
| 18 |
-
"latent_hop_length": 512,
|
| 19 |
-
"n_mels": 100,
|
| 20 |
-
"sample_rate": 24000
|
| 21 |
-
},
|
| 22 |
-
"components": {
|
| 23 |
-
"g2p_64": {
|
| 24 |
-
"artifacts": {
|
| 25 |
-
"coreai": {
|
| 26 |
-
"format": "coreai",
|
| 27 |
-
"path": "coreai/g2p.aimodel",
|
| 28 |
-
"function": "g2p_64"
|
| 29 |
-
}
|
| 30 |
-
},
|
| 31 |
-
"inputs": [
|
| 32 |
-
"text"
|
| 33 |
-
],
|
| 34 |
-
"outputs": [
|
| 35 |
-
"logits"
|
| 36 |
-
],
|
| 37 |
-
"required": false
|
| 38 |
-
},
|
| 39 |
-
"g2p_128": {
|
| 40 |
-
"artifacts": {
|
| 41 |
-
"coreai": {
|
| 42 |
-
"format": "coreai",
|
| 43 |
-
"path": "coreai/g2p.aimodel",
|
| 44 |
-
"function": "g2p_128"
|
| 45 |
-
}
|
| 46 |
-
},
|
| 47 |
-
"inputs": [
|
| 48 |
-
"text"
|
| 49 |
-
],
|
| 50 |
-
"outputs": [
|
| 51 |
-
"logits"
|
| 52 |
-
],
|
| 53 |
-
"required": false
|
| 54 |
-
},
|
| 55 |
-
"g2p_256": {
|
| 56 |
-
"artifacts": {
|
| 57 |
-
"coreai": {
|
| 58 |
-
"format": "coreai",
|
| 59 |
-
"path": "coreai/g2p.aimodel",
|
| 60 |
-
"function": "g2p_256"
|
| 61 |
-
}
|
| 62 |
-
},
|
| 63 |
-
"inputs": [
|
| 64 |
-
"text"
|
| 65 |
-
],
|
| 66 |
-
"outputs": [
|
| 67 |
-
"logits"
|
| 68 |
-
],
|
| 69 |
-
"required": false
|
| 70 |
-
},
|
| 71 |
-
"g2p": {
|
| 72 |
-
"artifacts": {
|
| 73 |
-
"coreai": {
|
| 74 |
-
"format": "coreai",
|
| 75 |
-
"path": "coreai/g2p.aimodel",
|
| 76 |
-
"function": "g2p"
|
| 77 |
-
}
|
| 78 |
-
},
|
| 79 |
-
"inputs": [
|
| 80 |
-
"text"
|
| 81 |
-
],
|
| 82 |
-
"outputs": [
|
| 83 |
-
"logits"
|
| 84 |
-
],
|
| 85 |
-
"required": true
|
| 86 |
-
},
|
| 87 |
-
"duration_predictor": {
|
| 88 |
-
"artifacts": {
|
| 89 |
-
"coreai": {
|
| 90 |
-
"format": "coreai",
|
| 91 |
-
"path": "coreai/duration_predictor.aimodel",
|
| 92 |
-
"function": "duration_predictor"
|
| 93 |
-
}
|
| 94 |
-
},
|
| 95 |
-
"inputs": [
|
| 96 |
-
"span_phone_ids",
|
| 97 |
-
"span_segment_ids",
|
| 98 |
-
"span_mask",
|
| 99 |
-
"voice_id",
|
| 100 |
-
"language_id",
|
| 101 |
-
"delivery_values",
|
| 102 |
-
"delivery_present"
|
| 103 |
-
],
|
| 104 |
-
"outputs": [
|
| 105 |
-
"durations"
|
| 106 |
-
],
|
| 107 |
-
"required": true
|
| 108 |
-
},
|
| 109 |
-
"vector_context_encoder": {
|
| 110 |
-
"artifacts": {
|
| 111 |
-
"coreai": {
|
| 112 |
-
"format": "coreai",
|
| 113 |
-
"path": "coreai/vector_context_encoder.aimodel",
|
| 114 |
-
"function": "vector_context_encoder"
|
| 115 |
-
}
|
| 116 |
-
},
|
| 117 |
-
"inputs": [
|
| 118 |
-
"span_context_phone_ids",
|
| 119 |
-
"span_context_segment_ids",
|
| 120 |
-
"span_context_mask"
|
| 121 |
-
],
|
| 122 |
-
"outputs": [
|
| 123 |
-
"span_context_hidden"
|
| 124 |
-
],
|
| 125 |
-
"required": true
|
| 126 |
-
},
|
| 127 |
-
"vector_estimator_128": {
|
| 128 |
-
"artifacts": {
|
| 129 |
-
"coreai": {
|
| 130 |
-
"format": "coreai",
|
| 131 |
-
"path": "coreai/vector_estimator.aimodel",
|
| 132 |
-
"function": "vector_estimator_128"
|
| 133 |
-
}
|
| 134 |
-
},
|
| 135 |
-
"inputs": [
|
| 136 |
-
"noise",
|
| 137 |
-
"time",
|
| 138 |
-
"expanded_phone_ids",
|
| 139 |
-
"voice_id",
|
| 140 |
-
"language_id",
|
| 141 |
-
"delivery_values",
|
| 142 |
-
"delivery_present",
|
| 143 |
-
"latent_mask",
|
| 144 |
-
"span_context_hidden",
|
| 145 |
-
"prefix_latents",
|
| 146 |
-
"prefix_mask",
|
| 147 |
-
"expanded_boundary_event_ids",
|
| 148 |
-
"expanded_modifier_event_ids",
|
| 149 |
-
"expanded_phone_phase",
|
| 150 |
-
"expanded_phone_log_duration",
|
| 151 |
-
"expanded_sentence_type_ids"
|
| 152 |
-
],
|
| 153 |
-
"outputs": [
|
| 154 |
-
"velocity"
|
| 155 |
-
],
|
| 156 |
-
"required": false
|
| 157 |
-
},
|
| 158 |
-
"vocoder_128": {
|
| 159 |
-
"artifacts": {
|
| 160 |
-
"coreai": {
|
| 161 |
-
"format": "coreai",
|
| 162 |
-
"path": "coreai/vocoder.aimodel",
|
| 163 |
-
"function": "vocoder_128"
|
| 164 |
-
}
|
| 165 |
-
},
|
| 166 |
-
"inputs": [
|
| 167 |
-
"latents",
|
| 168 |
-
"latent_mask",
|
| 169 |
-
"voice_id",
|
| 170 |
-
"language_id",
|
| 171 |
-
"emotion_id"
|
| 172 |
-
],
|
| 173 |
-
"outputs": [
|
| 174 |
-
"audio"
|
| 175 |
-
],
|
| 176 |
-
"required": false
|
| 177 |
-
},
|
| 178 |
-
"vector_estimator_256": {
|
| 179 |
-
"artifacts": {
|
| 180 |
-
"coreai": {
|
| 181 |
-
"format": "coreai",
|
| 182 |
-
"path": "coreai/vector_estimator.aimodel",
|
| 183 |
-
"function": "vector_estimator_256"
|
| 184 |
-
}
|
| 185 |
-
},
|
| 186 |
-
"inputs": [
|
| 187 |
-
"noise",
|
| 188 |
-
"time",
|
| 189 |
-
"expanded_phone_ids",
|
| 190 |
-
"voice_id",
|
| 191 |
-
"language_id",
|
| 192 |
-
"delivery_values",
|
| 193 |
-
"delivery_present",
|
| 194 |
-
"latent_mask",
|
| 195 |
-
"span_context_hidden",
|
| 196 |
-
"prefix_latents",
|
| 197 |
-
"prefix_mask",
|
| 198 |
-
"expanded_boundary_event_ids",
|
| 199 |
-
"expanded_modifier_event_ids",
|
| 200 |
-
"expanded_phone_phase",
|
| 201 |
-
"expanded_phone_log_duration",
|
| 202 |
-
"expanded_sentence_type_ids"
|
| 203 |
-
],
|
| 204 |
-
"outputs": [
|
| 205 |
-
"velocity"
|
| 206 |
-
],
|
| 207 |
-
"required": false
|
| 208 |
-
},
|
| 209 |
-
"vocoder_256": {
|
| 210 |
-
"artifacts": {
|
| 211 |
-
"coreai": {
|
| 212 |
-
"format": "coreai",
|
| 213 |
-
"path": "coreai/vocoder.aimodel",
|
| 214 |
-
"function": "vocoder_256"
|
| 215 |
-
}
|
| 216 |
-
},
|
| 217 |
-
"inputs": [
|
| 218 |
-
"latents",
|
| 219 |
-
"latent_mask",
|
| 220 |
-
"voice_id",
|
| 221 |
-
"language_id",
|
| 222 |
-
"emotion_id"
|
| 223 |
-
],
|
| 224 |
-
"outputs": [
|
| 225 |
-
"audio"
|
| 226 |
-
],
|
| 227 |
-
"required": false
|
| 228 |
-
},
|
| 229 |
-
"vector_estimator_384": {
|
| 230 |
-
"artifacts": {
|
| 231 |
-
"coreai": {
|
| 232 |
-
"format": "coreai",
|
| 233 |
-
"path": "coreai/vector_estimator.aimodel",
|
| 234 |
-
"function": "vector_estimator_384"
|
| 235 |
-
}
|
| 236 |
-
},
|
| 237 |
-
"inputs": [
|
| 238 |
-
"noise",
|
| 239 |
-
"time",
|
| 240 |
-
"expanded_phone_ids",
|
| 241 |
-
"voice_id",
|
| 242 |
-
"language_id",
|
| 243 |
-
"delivery_values",
|
| 244 |
-
"delivery_present",
|
| 245 |
-
"latent_mask",
|
| 246 |
-
"span_context_hidden",
|
| 247 |
-
"prefix_latents",
|
| 248 |
-
"prefix_mask",
|
| 249 |
-
"expanded_boundary_event_ids",
|
| 250 |
-
"expanded_modifier_event_ids",
|
| 251 |
-
"expanded_phone_phase",
|
| 252 |
-
"expanded_phone_log_duration",
|
| 253 |
-
"expanded_sentence_type_ids"
|
| 254 |
-
],
|
| 255 |
-
"outputs": [
|
| 256 |
-
"velocity"
|
| 257 |
-
],
|
| 258 |
-
"required": false
|
| 259 |
-
},
|
| 260 |
-
"vocoder_384": {
|
| 261 |
-
"artifacts": {
|
| 262 |
-
"coreai": {
|
| 263 |
-
"format": "coreai",
|
| 264 |
-
"path": "coreai/vocoder.aimodel",
|
| 265 |
-
"function": "vocoder_384"
|
| 266 |
-
}
|
| 267 |
-
},
|
| 268 |
-
"inputs": [
|
| 269 |
-
"latents",
|
| 270 |
-
"latent_mask",
|
| 271 |
-
"voice_id",
|
| 272 |
-
"language_id",
|
| 273 |
-
"emotion_id"
|
| 274 |
-
],
|
| 275 |
-
"outputs": [
|
| 276 |
-
"audio"
|
| 277 |
-
],
|
| 278 |
-
"required": false
|
| 279 |
-
},
|
| 280 |
-
"vector_estimator_512": {
|
| 281 |
-
"artifacts": {
|
| 282 |
-
"coreai": {
|
| 283 |
-
"format": "coreai",
|
| 284 |
-
"path": "coreai/vector_estimator.aimodel",
|
| 285 |
-
"function": "vector_estimator_512"
|
| 286 |
-
}
|
| 287 |
-
},
|
| 288 |
-
"inputs": [
|
| 289 |
-
"noise",
|
| 290 |
-
"time",
|
| 291 |
-
"expanded_phone_ids",
|
| 292 |
-
"voice_id",
|
| 293 |
-
"language_id",
|
| 294 |
-
"delivery_values",
|
| 295 |
-
"delivery_present",
|
| 296 |
-
"latent_mask",
|
| 297 |
-
"span_context_hidden",
|
| 298 |
-
"prefix_latents",
|
| 299 |
-
"prefix_mask",
|
| 300 |
-
"expanded_boundary_event_ids",
|
| 301 |
-
"expanded_modifier_event_ids",
|
| 302 |
-
"expanded_phone_phase",
|
| 303 |
-
"expanded_phone_log_duration",
|
| 304 |
-
"expanded_sentence_type_ids"
|
| 305 |
-
],
|
| 306 |
-
"outputs": [
|
| 307 |
-
"velocity"
|
| 308 |
-
],
|
| 309 |
-
"required": false
|
| 310 |
-
},
|
| 311 |
-
"vocoder_512": {
|
| 312 |
-
"artifacts": {
|
| 313 |
-
"coreai": {
|
| 314 |
-
"format": "coreai",
|
| 315 |
-
"path": "coreai/vocoder.aimodel",
|
| 316 |
-
"function": "vocoder_512"
|
| 317 |
-
}
|
| 318 |
-
},
|
| 319 |
-
"inputs": [
|
| 320 |
-
"latents",
|
| 321 |
-
"latent_mask",
|
| 322 |
-
"voice_id",
|
| 323 |
-
"language_id",
|
| 324 |
-
"emotion_id"
|
| 325 |
-
],
|
| 326 |
-
"outputs": [
|
| 327 |
-
"audio"
|
| 328 |
-
],
|
| 329 |
-
"required": false
|
| 330 |
-
},
|
| 331 |
-
"vector_estimator_768": {
|
| 332 |
-
"artifacts": {
|
| 333 |
-
"coreai": {
|
| 334 |
-
"format": "coreai",
|
| 335 |
-
"path": "coreai/vector_estimator.aimodel",
|
| 336 |
-
"function": "vector_estimator_768"
|
| 337 |
-
}
|
| 338 |
-
},
|
| 339 |
-
"inputs": [
|
| 340 |
-
"noise",
|
| 341 |
-
"time",
|
| 342 |
-
"expanded_phone_ids",
|
| 343 |
-
"voice_id",
|
| 344 |
-
"language_id",
|
| 345 |
-
"delivery_values",
|
| 346 |
-
"delivery_present",
|
| 347 |
-
"latent_mask",
|
| 348 |
-
"span_context_hidden",
|
| 349 |
-
"prefix_latents",
|
| 350 |
-
"prefix_mask",
|
| 351 |
-
"expanded_boundary_event_ids",
|
| 352 |
-
"expanded_modifier_event_ids",
|
| 353 |
-
"expanded_phone_phase",
|
| 354 |
-
"expanded_phone_log_duration",
|
| 355 |
-
"expanded_sentence_type_ids"
|
| 356 |
-
],
|
| 357 |
-
"outputs": [
|
| 358 |
-
"velocity"
|
| 359 |
-
],
|
| 360 |
-
"required": false
|
| 361 |
-
},
|
| 362 |
-
"vocoder_768": {
|
| 363 |
-
"artifacts": {
|
| 364 |
-
"coreai": {
|
| 365 |
-
"format": "coreai",
|
| 366 |
-
"path": "coreai/vocoder.aimodel",
|
| 367 |
-
"function": "vocoder_768"
|
| 368 |
-
}
|
| 369 |
-
},
|
| 370 |
-
"inputs": [
|
| 371 |
-
"latents",
|
| 372 |
-
"latent_mask",
|
| 373 |
-
"voice_id",
|
| 374 |
-
"language_id",
|
| 375 |
-
"emotion_id"
|
| 376 |
-
],
|
| 377 |
-
"outputs": [
|
| 378 |
-
"audio"
|
| 379 |
-
],
|
| 380 |
-
"required": false
|
| 381 |
-
},
|
| 382 |
-
"vector_estimator": {
|
| 383 |
-
"artifacts": {
|
| 384 |
-
"coreai": {
|
| 385 |
-
"format": "coreai",
|
| 386 |
-
"path": "coreai/vector_estimator.aimodel",
|
| 387 |
-
"function": "vector_estimator"
|
| 388 |
-
}
|
| 389 |
-
},
|
| 390 |
-
"inputs": [
|
| 391 |
-
"noise",
|
| 392 |
-
"time",
|
| 393 |
-
"expanded_phone_ids",
|
| 394 |
-
"voice_id",
|
| 395 |
-
"language_id",
|
| 396 |
-
"delivery_values",
|
| 397 |
-
"delivery_present",
|
| 398 |
-
"latent_mask",
|
| 399 |
-
"span_context_hidden",
|
| 400 |
-
"prefix_latents",
|
| 401 |
-
"prefix_mask",
|
| 402 |
-
"expanded_boundary_event_ids",
|
| 403 |
-
"expanded_modifier_event_ids",
|
| 404 |
-
"expanded_phone_phase",
|
| 405 |
-
"expanded_phone_log_duration",
|
| 406 |
-
"expanded_sentence_type_ids"
|
| 407 |
-
],
|
| 408 |
-
"outputs": [
|
| 409 |
-
"velocity"
|
| 410 |
-
],
|
| 411 |
-
"required": true
|
| 412 |
-
},
|
| 413 |
-
"vocoder": {
|
| 414 |
-
"artifacts": {
|
| 415 |
-
"coreai": {
|
| 416 |
-
"format": "coreai",
|
| 417 |
-
"path": "coreai/vocoder.aimodel",
|
| 418 |
-
"function": "vocoder"
|
| 419 |
-
}
|
| 420 |
-
},
|
| 421 |
-
"inputs": [
|
| 422 |
-
"latents",
|
| 423 |
-
"latent_mask",
|
| 424 |
-
"voice_id",
|
| 425 |
-
"language_id",
|
| 426 |
-
"emotion_id"
|
| 427 |
-
],
|
| 428 |
-
"outputs": [
|
| 429 |
-
"audio"
|
| 430 |
-
],
|
| 431 |
-
"required": true
|
| 432 |
-
}
|
| 433 |
-
},
|
| 434 |
-
"contract_version": "1.0.0",
|
| 435 |
-
"controls": {
|
| 436 |
-
"chunk_context": {
|
| 437 |
-
"artificial_continuation_boundaries": [
|
| 438 |
-
"chunk_continue"
|
| 439 |
-
],
|
| 440 |
-
"artificial_continuation_phone": null,
|
| 441 |
-
"boundary_after_values": [
|
| 442 |
-
"sentence_end",
|
| 443 |
-
"paragraph_end",
|
| 444 |
-
"clause_continue",
|
| 445 |
-
"chunk_continue"
|
| 446 |
-
],
|
| 447 |
-
"boundary_before_values": [
|
| 448 |
-
"sentence_start",
|
| 449 |
-
"paragraph_start",
|
| 450 |
-
"clause_continue",
|
| 451 |
-
"chunk_continue"
|
| 452 |
-
],
|
| 453 |
-
"clause_continuation_fallback_phone": "<pause_comma>",
|
| 454 |
-
"conditioning": "boundary_embeddings",
|
| 455 |
-
"context_phone_tokens": {
|
| 456 |
-
"continuation": "<ctx_continuation>",
|
| 457 |
-
"sentence_end": "<ctx_sentence_end>",
|
| 458 |
-
"sentence_start": "<ctx_sentence_start>"
|
| 459 |
-
},
|
| 460 |
-
"default_boundary_after": "sentence_end",
|
| 461 |
-
"default_boundary_before": "sentence_start",
|
| 462 |
-
"emit_context_phone_tokens": false,
|
| 463 |
-
"linguistic_continuation_boundaries": [
|
| 464 |
-
"clause_continue"
|
| 465 |
-
],
|
| 466 |
-
"schema_version": 2
|
| 467 |
-
},
|
| 468 |
-
"chunking": {
|
| 469 |
-
"shared_split_phone": "<sil>",
|
| 470 |
-
"split_after": [
|
| 471 |
-
"<end_stmt>",
|
| 472 |
-
"<end_question>",
|
| 473 |
-
"<end_exclaim>",
|
| 474 |
-
"<ellipsis>"
|
| 475 |
-
],
|
| 476 |
-
"unit": "sentence"
|
| 477 |
-
},
|
| 478 |
-
"decoding": {
|
| 479 |
-
"context_frames": 48,
|
| 480 |
-
"mode": "overlap"
|
| 481 |
-
},
|
| 482 |
-
"delivery": {
|
| 483 |
-
"axes": [
|
| 484 |
-
"energy",
|
| 485 |
-
"tension",
|
| 486 |
-
"valence",
|
| 487 |
-
"assertiveness"
|
| 488 |
-
],
|
| 489 |
-
"default": "neutral",
|
| 490 |
-
"enabled": true,
|
| 491 |
-
"neutral": 2.0,
|
| 492 |
-
"normalization": "(rating-2)/4",
|
| 493 |
-
"presence_mask": true,
|
| 494 |
-
"range": [
|
| 495 |
-
0.0,
|
| 496 |
-
4.0
|
| 497 |
-
],
|
| 498 |
-
"release_id": "v2-20261005",
|
| 499 |
-
"scope": "utterance",
|
| 500 |
-
"timeline_conditioning": false,
|
| 501 |
-
"voice_locales": {
|
| 502 |
-
"ariadne": [
|
| 503 |
-
"de",
|
| 504 |
-
"en_us",
|
| 505 |
-
"es",
|
| 506 |
-
"fr",
|
| 507 |
-
"it",
|
| 508 |
-
"vi"
|
| 509 |
-
],
|
| 510 |
-
"felix": [
|
| 511 |
-
"de",
|
| 512 |
-
"en_us",
|
| 513 |
-
"es",
|
| 514 |
-
"fr",
|
| 515 |
-
"it",
|
| 516 |
-
"vi"
|
| 517 |
-
],
|
| 518 |
-
"gwen": [
|
| 519 |
-
"de",
|
| 520 |
-
"en_us",
|
| 521 |
-
"es",
|
| 522 |
-
"fr",
|
| 523 |
-
"it",
|
| 524 |
-
"vi"
|
| 525 |
-
],
|
| 526 |
-
"ink": [
|
| 527 |
-
"de",
|
| 528 |
-
"en_gb",
|
| 529 |
-
"es",
|
| 530 |
-
"fr",
|
| 531 |
-
"it",
|
| 532 |
-
"vi"
|
| 533 |
-
],
|
| 534 |
-
"max": [
|
| 535 |
-
"de",
|
| 536 |
-
"en_us",
|
| 537 |
-
"es",
|
| 538 |
-
"fr",
|
| 539 |
-
"it",
|
| 540 |
-
"vi"
|
| 541 |
-
],
|
| 542 |
-
"orpheus": [
|
| 543 |
-
"de",
|
| 544 |
-
"en_gb",
|
| 545 |
-
"es",
|
| 546 |
-
"fr",
|
| 547 |
-
"it",
|
| 548 |
-
"vi"
|
| 549 |
-
],
|
| 550 |
-
"rex": [
|
| 551 |
-
"de",
|
| 552 |
-
"en_us",
|
| 553 |
-
"es",
|
| 554 |
-
"fr",
|
| 555 |
-
"it",
|
| 556 |
-
"vi"
|
| 557 |
-
],
|
| 558 |
-
"scylla": [
|
| 559 |
-
"de",
|
| 560 |
-
"en_us",
|
| 561 |
-
"es",
|
| 562 |
-
"fr",
|
| 563 |
-
"it",
|
| 564 |
-
"vi"
|
| 565 |
-
],
|
| 566 |
-
"stone": [
|
| 567 |
-
"de",
|
| 568 |
-
"en_us",
|
| 569 |
-
"es",
|
| 570 |
-
"fr",
|
| 571 |
-
"it",
|
| 572 |
-
"vi"
|
| 573 |
-
],
|
| 574 |
-
"tuesday": [
|
| 575 |
-
"de",
|
| 576 |
-
"en_gb",
|
| 577 |
-
"es",
|
| 578 |
-
"fr",
|
| 579 |
-
"it",
|
| 580 |
-
"vi"
|
| 581 |
-
]
|
| 582 |
-
},
|
| 583 |
-
"whisper": "binary"
|
| 584 |
-
},
|
| 585 |
-
"durations": {
|
| 586 |
-
"rounding": "half_even",
|
| 587 |
-
"silence_min_frames": 0,
|
| 588 |
-
"speech_min_frames": 1,
|
| 589 |
-
"zero_frame_phones": "punctuation_and_modifiers"
|
| 590 |
-
},
|
| 591 |
-
"emotions": {
|
| 592 |
-
"enabled": false
|
| 593 |
-
},
|
| 594 |
-
"energy": {
|
| 595 |
-
"default": 1.0,
|
| 596 |
-
"max": 1.5,
|
| 597 |
-
"min": 0.5
|
| 598 |
-
},
|
| 599 |
-
"fixed_shapes": {
|
| 600 |
-
"g2p_text_tokens": 512,
|
| 601 |
-
"latent_frames": 1024,
|
| 602 |
-
"phone_frames": 512
|
| 603 |
-
},
|
| 604 |
-
"graph_input_contract": "scyllasband_measured_delivery_v2",
|
| 605 |
-
"pitch": {
|
| 606 |
-
"default": 0.0,
|
| 607 |
-
"max": 4.0,
|
| 608 |
-
"min": -4.0
|
| 609 |
-
},
|
| 610 |
-
"prefix_conditioning": {
|
| 611 |
-
"alignment": "right",
|
| 612 |
-
"enabled": true,
|
| 613 |
-
"max_frames": 96,
|
| 614 |
-
"source": "previous_latents_tail"
|
| 615 |
-
},
|
| 616 |
-
"punctuation_silence": {
|
| 617 |
-
"calibrated_floors": false,
|
| 618 |
-
"floor_table_ms": {},
|
| 619 |
-
"silence_phone": "<sil>",
|
| 620 |
-
"target": "explicit_silence"
|
| 621 |
-
},
|
| 622 |
-
"reference_packs": {
|
| 623 |
-
"enabled": false,
|
| 624 |
-
"fixed_in_graph": true
|
| 625 |
-
},
|
| 626 |
-
"sampler": {
|
| 627 |
-
"choices": [
|
| 628 |
-
"euler",
|
| 629 |
-
"heun"
|
| 630 |
-
],
|
| 631 |
-
"default": "heun"
|
| 632 |
-
},
|
| 633 |
-
"span_conditioning": {
|
| 634 |
-
"context_max_phones": 512,
|
| 635 |
-
"context_phones_each_side": 180,
|
| 636 |
-
"duration_inputs": [
|
| 637 |
-
"span_phone_ids",
|
| 638 |
-
"span_segment_ids",
|
| 639 |
-
"span_mask"
|
| 640 |
-
],
|
| 641 |
-
"enabled": true,
|
| 642 |
-
"encoder_component": "vector_context_encoder",
|
| 643 |
-
"encoder_inputs": [
|
| 644 |
-
"span_context_phone_ids",
|
| 645 |
-
"span_context_segment_ids",
|
| 646 |
-
"span_context_mask"
|
| 647 |
-
],
|
| 648 |
-
"exclude_context_phones": [
|
| 649 |
-
"<sil>"
|
| 650 |
-
],
|
| 651 |
-
"hidden_size": 512,
|
| 652 |
-
"layout": "balanced_before_target_after",
|
| 653 |
-
"scope": "passage",
|
| 654 |
-
"segments": 3,
|
| 655 |
-
"solver_input": "span_context_hidden"
|
| 656 |
-
},
|
| 657 |
-
"speed": {
|
| 658 |
-
"default": 1.0,
|
| 659 |
-
"max": 1.25,
|
| 660 |
-
"min": 0.75
|
| 661 |
-
},
|
| 662 |
-
"steps": {
|
| 663 |
-
"default": 8,
|
| 664 |
-
"max": 64,
|
| 665 |
-
"min": 1
|
| 666 |
-
},
|
| 667 |
-
"target_buckets": {
|
| 668 |
-
"bucket_margin_frames": 0,
|
| 669 |
-
"buckets": [
|
| 670 |
-
{
|
| 671 |
-
"default": false,
|
| 672 |
-
"latent_frames": 128,
|
| 673 |
-
"vector_estimator": "vector_estimator_128",
|
| 674 |
-
"vocoder": "vocoder_128"
|
| 675 |
-
},
|
| 676 |
-
{
|
| 677 |
-
"default": false,
|
| 678 |
-
"latent_frames": 256,
|
| 679 |
-
"vector_estimator": "vector_estimator_256",
|
| 680 |
-
"vocoder": "vocoder_256"
|
| 681 |
-
},
|
| 682 |
-
{
|
| 683 |
-
"default": false,
|
| 684 |
-
"latent_frames": 384,
|
| 685 |
-
"vector_estimator": "vector_estimator_384",
|
| 686 |
-
"vocoder": "vocoder_384"
|
| 687 |
-
},
|
| 688 |
-
{
|
| 689 |
-
"default": false,
|
| 690 |
-
"latent_frames": 512,
|
| 691 |
-
"vector_estimator": "vector_estimator_512",
|
| 692 |
-
"vocoder": "vocoder_512"
|
| 693 |
-
},
|
| 694 |
-
{
|
| 695 |
-
"default": false,
|
| 696 |
-
"latent_frames": 768,
|
| 697 |
-
"vector_estimator": "vector_estimator_768",
|
| 698 |
-
"vocoder": "vocoder_768"
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"default": true,
|
| 702 |
-
"latent_frames": 1024,
|
| 703 |
-
"vector_estimator": "vector_estimator",
|
| 704 |
-
"vocoder": "vocoder"
|
| 705 |
-
}
|
| 706 |
-
],
|
| 707 |
-
"default_latent_frames": 1024,
|
| 708 |
-
"enabled": true,
|
| 709 |
-
"policy": "smallest_fit"
|
| 710 |
-
},
|
| 711 |
-
"text_normalizer": {
|
| 712 |
-
"prepared_contract_recorded": true,
|
| 713 |
-
"sha256": "d8fd1b2415d0d100d1c70237a4469117ee6b73d0e4da703e4654c83192779cc4",
|
| 714 |
-
"version": "scyllasband_spoken_text_v2_2026_08_05"
|
| 715 |
-
},
|
| 716 |
-
"timing_events": {
|
| 717 |
-
"enabled": true,
|
| 718 |
-
"inputs": [
|
| 719 |
-
"expanded_boundary_event_ids",
|
| 720 |
-
"expanded_modifier_event_ids",
|
| 721 |
-
"expanded_phone_phase",
|
| 722 |
-
"expanded_phone_log_duration",
|
| 723 |
-
"expanded_sentence_type_ids"
|
| 724 |
-
],
|
| 725 |
-
"modifier_bits": {
|
| 726 |
-
"ˈ": 1,
|
| 727 |
-
"ˌ": 2,
|
| 728 |
-
"ː": 4,
|
| 729 |
-
"̃": 8,
|
| 730 |
-
"̩": 16,
|
| 731 |
-
"̪": 32
|
| 732 |
-
},
|
| 733 |
-
"punctuation_owner": "following_silence_else_first_frame_of_next_phone",
|
| 734 |
-
"sentence_type_count": 5,
|
| 735 |
-
"sentence_type_lookahead": "following_context",
|
| 736 |
-
"sentence_types": {
|
| 737 |
-
"<ellipsis>": 4,
|
| 738 |
-
"<end_exclaim>": 3,
|
| 739 |
-
"<end_question>": 2,
|
| 740 |
-
"<end_stmt>": 1
|
| 741 |
-
},
|
| 742 |
-
"word_start_event_id": 87,
|
| 743 |
-
"word_start_owner": "first_phone_of_word_after_chunk_first_word"
|
| 744 |
-
},
|
| 745 |
-
"word_boundaries": {
|
| 746 |
-
"duration_phone": "<sil>",
|
| 747 |
-
"enabled": true,
|
| 748 |
-
"g2p_output_symbol": " ",
|
| 749 |
-
"zero_frames_allowed": true
|
| 750 |
-
},
|
| 751 |
-
"g2p_buckets": [
|
| 752 |
-
{
|
| 753 |
-
"text_tokens": 64,
|
| 754 |
-
"component": "g2p_64"
|
| 755 |
-
},
|
| 756 |
-
{
|
| 757 |
-
"text_tokens": 128,
|
| 758 |
-
"component": "g2p_128"
|
| 759 |
-
},
|
| 760 |
-
{
|
| 761 |
-
"text_tokens": 256,
|
| 762 |
-
"component": "g2p_256"
|
| 763 |
-
},
|
| 764 |
-
{
|
| 765 |
-
"text_tokens": 512,
|
| 766 |
-
"component": "g2p"
|
| 767 |
-
}
|
| 768 |
-
],
|
| 769 |
-
"coreai": {
|
| 770 |
-
"minimum_os": {
|
| 771 |
-
"ios": "27.0",
|
| 772 |
-
"macos": "27.0"
|
| 773 |
-
},
|
| 774 |
-
"io": {
|
| 775 |
-
"ids": "int32",
|
| 776 |
-
"masks": "int32",
|
| 777 |
-
"values": "float32"
|
| 778 |
-
},
|
| 779 |
-
"assets": {
|
| 780 |
-
"g2p": {
|
| 781 |
-
"precision": "fp16",
|
| 782 |
-
"weights": "w8",
|
| 783 |
-
"bytes": 28377408
|
| 784 |
-
},
|
| 785 |
-
"duration_predictor": {
|
| 786 |
-
"precision": "fp16",
|
| 787 |
-
"weights": "w8",
|
| 788 |
-
"bytes": 10885061
|
| 789 |
-
},
|
| 790 |
-
"vector_context_encoder": {
|
| 791 |
-
"precision": "fp16",
|
| 792 |
-
"weights": "w8",
|
| 793 |
-
"bytes": 8029414
|
| 794 |
-
},
|
| 795 |
-
"vector_estimator": {
|
| 796 |
-
"precision": "fp16",
|
| 797 |
-
"weights": "w8",
|
| 798 |
-
"bytes": 63149205
|
| 799 |
-
},
|
| 800 |
-
"vocoder": {
|
| 801 |
-
"precision": "fp16",
|
| 802 |
-
"weights": "w8",
|
| 803 |
-
"bytes": 43811167
|
| 804 |
-
}
|
| 805 |
-
},
|
| 806 |
-
"compute_units": "gpu",
|
| 807 |
-
"neural_engine_assets": [
|
| 808 |
-
"vector_estimator"
|
| 809 |
-
]
|
| 810 |
-
}
|
| 811 |
-
},
|
| 812 |
-
"dataset_summary": {
|
| 813 |
-
"controls": "measured_four_axes_plus_binary_whisper",
|
| 814 |
-
"voice_locale_pairs": 60
|
| 815 |
-
},
|
| 816 |
-
"default_language": "en_us",
|
| 817 |
-
"languages": [
|
| 818 |
-
"en_us",
|
| 819 |
-
"en_gb",
|
| 820 |
-
"es",
|
| 821 |
-
"it",
|
| 822 |
-
"fr",
|
| 823 |
-
"de",
|
| 824 |
-
"vi"
|
| 825 |
-
],
|
| 826 |
-
"model_name": "Scylla's Band",
|
| 827 |
-
"model_version": "2",
|
| 828 |
-
"preferred_backends": [
|
| 829 |
-
"coreai"
|
| 830 |
-
],
|
| 831 |
-
"voices": [
|
| 832 |
-
{
|
| 833 |
-
"default_language": "en_us",
|
| 834 |
-
"embedding_path": null,
|
| 835 |
-
"id": "ariadne",
|
| 836 |
-
"languages": [
|
| 837 |
-
"de",
|
| 838 |
-
"en_us",
|
| 839 |
-
"es",
|
| 840 |
-
"fr",
|
| 841 |
-
"it",
|
| 842 |
-
"vi"
|
| 843 |
-
],
|
| 844 |
-
"name": "ariadne",
|
| 845 |
-
"styles": [
|
| 846 |
-
"default"
|
| 847 |
-
]
|
| 848 |
-
},
|
| 849 |
-
{
|
| 850 |
-
"default_language": "en_us",
|
| 851 |
-
"embedding_path": null,
|
| 852 |
-
"id": "felix",
|
| 853 |
-
"languages": [
|
| 854 |
-
"de",
|
| 855 |
-
"en_us",
|
| 856 |
-
"es",
|
| 857 |
-
"fr",
|
| 858 |
-
"it",
|
| 859 |
-
"vi"
|
| 860 |
-
],
|
| 861 |
-
"name": "felix",
|
| 862 |
-
"styles": [
|
| 863 |
-
"default"
|
| 864 |
-
]
|
| 865 |
-
},
|
| 866 |
-
{
|
| 867 |
-
"default_language": "en_us",
|
| 868 |
-
"embedding_path": null,
|
| 869 |
-
"id": "gwen",
|
| 870 |
-
"languages": [
|
| 871 |
-
"de",
|
| 872 |
-
"en_us",
|
| 873 |
-
"es",
|
| 874 |
-
"fr",
|
| 875 |
-
"it",
|
| 876 |
-
"vi"
|
| 877 |
-
],
|
| 878 |
-
"name": "gwen",
|
| 879 |
-
"styles": [
|
| 880 |
-
"default"
|
| 881 |
-
]
|
| 882 |
-
},
|
| 883 |
-
{
|
| 884 |
-
"default_language": "en_gb",
|
| 885 |
-
"embedding_path": null,
|
| 886 |
-
"id": "ink",
|
| 887 |
-
"languages": [
|
| 888 |
-
"de",
|
| 889 |
-
"en_gb",
|
| 890 |
-
"es",
|
| 891 |
-
"fr",
|
| 892 |
-
"it",
|
| 893 |
-
"vi"
|
| 894 |
-
],
|
| 895 |
-
"name": "ink",
|
| 896 |
-
"styles": [
|
| 897 |
-
"default"
|
| 898 |
-
]
|
| 899 |
-
},
|
| 900 |
-
{
|
| 901 |
-
"default_language": "en_us",
|
| 902 |
-
"embedding_path": null,
|
| 903 |
-
"id": "max",
|
| 904 |
-
"languages": [
|
| 905 |
-
"de",
|
| 906 |
-
"en_us",
|
| 907 |
-
"es",
|
| 908 |
-
"fr",
|
| 909 |
-
"it",
|
| 910 |
-
"vi"
|
| 911 |
-
],
|
| 912 |
-
"name": "max",
|
| 913 |
-
"styles": [
|
| 914 |
-
"default"
|
| 915 |
-
]
|
| 916 |
-
},
|
| 917 |
-
{
|
| 918 |
-
"default_language": "en_gb",
|
| 919 |
-
"embedding_path": null,
|
| 920 |
-
"id": "orpheus",
|
| 921 |
-
"languages": [
|
| 922 |
-
"de",
|
| 923 |
-
"en_gb",
|
| 924 |
-
"es",
|
| 925 |
-
"fr",
|
| 926 |
-
"it",
|
| 927 |
-
"vi"
|
| 928 |
-
],
|
| 929 |
-
"name": "orpheus",
|
| 930 |
-
"styles": [
|
| 931 |
-
"default"
|
| 932 |
-
]
|
| 933 |
-
},
|
| 934 |
-
{
|
| 935 |
-
"default_language": "en_us",
|
| 936 |
-
"embedding_path": null,
|
| 937 |
-
"id": "rex",
|
| 938 |
-
"languages": [
|
| 939 |
-
"de",
|
| 940 |
-
"en_us",
|
| 941 |
-
"es",
|
| 942 |
-
"fr",
|
| 943 |
-
"it",
|
| 944 |
-
"vi"
|
| 945 |
-
],
|
| 946 |
-
"name": "rex",
|
| 947 |
-
"styles": [
|
| 948 |
-
"default"
|
| 949 |
-
]
|
| 950 |
-
},
|
| 951 |
-
{
|
| 952 |
-
"default_language": "en_us",
|
| 953 |
-
"embedding_path": null,
|
| 954 |
-
"id": "scylla",
|
| 955 |
-
"languages": [
|
| 956 |
-
"de",
|
| 957 |
-
"en_us",
|
| 958 |
-
"es",
|
| 959 |
-
"fr",
|
| 960 |
-
"it",
|
| 961 |
-
"vi"
|
| 962 |
-
],
|
| 963 |
-
"name": "scylla",
|
| 964 |
-
"styles": [
|
| 965 |
-
"default"
|
| 966 |
-
]
|
| 967 |
-
},
|
| 968 |
-
{
|
| 969 |
-
"default_language": "en_us",
|
| 970 |
-
"embedding_path": null,
|
| 971 |
-
"id": "stone",
|
| 972 |
-
"languages": [
|
| 973 |
-
"de",
|
| 974 |
-
"en_us",
|
| 975 |
-
"es",
|
| 976 |
-
"fr",
|
| 977 |
-
"it",
|
| 978 |
-
"vi"
|
| 979 |
-
],
|
| 980 |
-
"name": "stone",
|
| 981 |
-
"styles": [
|
| 982 |
-
"default"
|
| 983 |
-
]
|
| 984 |
-
},
|
| 985 |
-
{
|
| 986 |
-
"default_language": "en_gb",
|
| 987 |
-
"embedding_path": null,
|
| 988 |
-
"id": "tuesday",
|
| 989 |
-
"languages": [
|
| 990 |
-
"de",
|
| 991 |
-
"en_gb",
|
| 992 |
-
"es",
|
| 993 |
-
"fr",
|
| 994 |
-
"it",
|
| 995 |
-
"vi"
|
| 996 |
-
],
|
| 997 |
-
"name": "tuesday",
|
| 998 |
-
"styles": [
|
| 999 |
-
"default"
|
| 1000 |
-
]
|
| 1001 |
-
}
|
| 1002 |
-
]
|
| 1003 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreml/assets/fixed_references.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
coreml/assets/g2p/export_config.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"batch_dynamic": true,
|
| 3 |
-
"format": "scyllasband_g2p",
|
| 4 |
-
"input_granularity": "phrase",
|
| 5 |
-
"languages": [
|
| 6 |
-
"de",
|
| 7 |
-
"en_gb",
|
| 8 |
-
"en_us",
|
| 9 |
-
"es",
|
| 10 |
-
"fr",
|
| 11 |
-
"it",
|
| 12 |
-
"vi"
|
| 13 |
-
],
|
| 14 |
-
"model_type": "transformer",
|
| 15 |
-
"onnx_export_batch_size": 4,
|
| 16 |
-
"onnx_export_layout": "batch_first",
|
| 17 |
-
"onnx_export_max_batch_size": 256,
|
| 18 |
-
"onnx_exporter": "dynamo",
|
| 19 |
-
"onnx_fp32_model": "model.onnx",
|
| 20 |
-
"onnx_model": "model.onnx",
|
| 21 |
-
"onnx_padded_output": "ctc_blank",
|
| 22 |
-
"onnx_quantization": "none",
|
| 23 |
-
"onnx_quantized_parity_tolerance": 3.0,
|
| 24 |
-
"opset": 18,
|
| 25 |
-
"phoneme_token_mode": "char",
|
| 26 |
-
"phrase_rows_per_language": 200000,
|
| 27 |
-
"preserve_commas": true,
|
| 28 |
-
"punctuation_silence_target": "explicit_silence",
|
| 29 |
-
"release_role": "fp32_bundle_frontend",
|
| 30 |
-
"source_checkpoint": "output/deepphonemizer_multilingual/model_v10_7lang/checkpoints/model_step_250k.pt",
|
| 31 |
-
"training_mix": "phrase_word_chunked_clean",
|
| 32 |
-
"word_rows_per_language": 200000
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreml/assets/g2p/language_map.json
DELETED
|
@@ -1,47 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"american": "en_us",
|
| 3 |
-
"american_english": "en_us",
|
| 4 |
-
"british": "en_gb",
|
| 5 |
-
"british_english": "en_gb",
|
| 6 |
-
"de": "de",
|
| 7 |
-
"de_de": "de",
|
| 8 |
-
"deu": "de",
|
| 9 |
-
"en": "en_us",
|
| 10 |
-
"en-gb": "en_gb",
|
| 11 |
-
"en-uk": "en_gb",
|
| 12 |
-
"en-us": "en_us",
|
| 13 |
-
"en_gb": "en_gb",
|
| 14 |
-
"en_uk": "en_gb",
|
| 15 |
-
"en_us": "en_us",
|
| 16 |
-
"eng": "en_us",
|
| 17 |
-
"eng_gb": "en_gb",
|
| 18 |
-
"eng_us": "en_us",
|
| 19 |
-
"english": "en_us",
|
| 20 |
-
"english_gb": "en_gb",
|
| 21 |
-
"english_uk": "en_gb",
|
| 22 |
-
"english_us": "en_us",
|
| 23 |
-
"es": "es",
|
| 24 |
-
"es_es": "es",
|
| 25 |
-
"es_mx": "es",
|
| 26 |
-
"fr": "fr",
|
| 27 |
-
"fr_fr": "fr",
|
| 28 |
-
"fra": "fr",
|
| 29 |
-
"fre": "fr",
|
| 30 |
-
"french": "fr",
|
| 31 |
-
"gb": "en_gb",
|
| 32 |
-
"ger": "de",
|
| 33 |
-
"german": "de",
|
| 34 |
-
"it": "it",
|
| 35 |
-
"it_it": "it",
|
| 36 |
-
"ita": "it",
|
| 37 |
-
"italian": "it",
|
| 38 |
-
"spa": "es",
|
| 39 |
-
"spanish": "es",
|
| 40 |
-
"uk": "en_gb",
|
| 41 |
-
"us": "en_us",
|
| 42 |
-
"vi": "vi",
|
| 43 |
-
"vi_hn": "vi",
|
| 44 |
-
"vi_vn": "vi",
|
| 45 |
-
"vie": "vi",
|
| 46 |
-
"vietnamese": "vi"
|
| 47 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreml/assets/g2p/normalization.json
DELETED
|
@@ -1,40 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"contract": {
|
| 3 |
-
"colon_semicolon_classes": "preserved",
|
| 4 |
-
"dot_runs_two_or_more": "ellipsis_three_dots",
|
| 5 |
-
"homogeneous_terminal_runs": "single_mark",
|
| 6 |
-
"lexical_hyphen": "space_no_pause",
|
| 7 |
-
"mixed_question_exclamation": "leading_mark",
|
| 8 |
-
"non_acoustic_modifiers": [
|
| 9 |
-
"stress",
|
| 10 |
-
"length",
|
| 11 |
-
"unicode_combining"
|
| 12 |
-
],
|
| 13 |
-
"ok_spoken_form": "okay",
|
| 14 |
-
"punctuation_silence_target": "explicit_silence",
|
| 15 |
-
"syntactic_dash": "em_dash_pause",
|
| 16 |
-
"training_phone_source": "espeak",
|
| 17 |
-
"version": "scyllasband_spoken_text_v2_2026_08_05"
|
| 18 |
-
},
|
| 19 |
-
"contract_sha256": "d8fd1b2415d0d100d1c70237a4469117ee6b73d0e4da703e4654c83192779cc4",
|
| 20 |
-
"contract_version": "scyllasband_spoken_text_v2_2026_08_05",
|
| 21 |
-
"expand_currency": true,
|
| 22 |
-
"expand_dates": true,
|
| 23 |
-
"expand_numbers": true,
|
| 24 |
-
"expand_ordinals": true,
|
| 25 |
-
"expand_percentages": true,
|
| 26 |
-
"expand_times": true,
|
| 27 |
-
"languages": [
|
| 28 |
-
"en",
|
| 29 |
-
"en_us",
|
| 30 |
-
"en_gb",
|
| 31 |
-
"es",
|
| 32 |
-
"it",
|
| 33 |
-
"fr",
|
| 34 |
-
"de",
|
| 35 |
-
"vi"
|
| 36 |
-
],
|
| 37 |
-
"normalize_at_sign": true,
|
| 38 |
-
"normalize_punctuation": true,
|
| 39 |
-
"normalizer": "SpokenTextNormalizer"
|
| 40 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreml/assets/g2p/phoneme_dict.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"de": {},
|
| 3 |
-
"en_gb": {},
|
| 4 |
-
"en_us": {},
|
| 5 |
-
"es": {},
|
| 6 |
-
"fr": {},
|
| 7 |
-
"it": {},
|
| 8 |
-
"vi": {}
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreml/assets/g2p/pronunciation_overrides.json
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"format": "scyllasband_g2p_pronunciation_overrides_v1",
|
| 3 |
-
"languages": {}
|
| 4 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreml/assets/g2p/tokenizer.json
DELETED
|
@@ -1,517 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"format": "deepphonemizer_forward_ctc",
|
| 3 |
-
"languages": [
|
| 4 |
-
"de",
|
| 5 |
-
"en_gb",
|
| 6 |
-
"en_us",
|
| 7 |
-
"es",
|
| 8 |
-
"fr",
|
| 9 |
-
"it",
|
| 10 |
-
"vi"
|
| 11 |
-
],
|
| 12 |
-
"char_repeats": 4,
|
| 13 |
-
"lowercase": true,
|
| 14 |
-
"phoneme_token_mode": "char",
|
| 15 |
-
"text_symbols": {
|
| 16 |
-
"_": 0,
|
| 17 |
-
"<de>": 1,
|
| 18 |
-
"<en_gb>": 2,
|
| 19 |
-
"<en_us>": 3,
|
| 20 |
-
"<es>": 4,
|
| 21 |
-
"<fr>": 5,
|
| 22 |
-
"<it>": 6,
|
| 23 |
-
"<vi>": 7,
|
| 24 |
-
"<end>": 8,
|
| 25 |
-
"\b": 9,
|
| 26 |
-
" ": 10,
|
| 27 |
-
"!": 11,
|
| 28 |
-
"\"": 12,
|
| 29 |
-
"#": 13,
|
| 30 |
-
"$": 14,
|
| 31 |
-
"%": 15,
|
| 32 |
-
"&": 16,
|
| 33 |
-
"'": 17,
|
| 34 |
-
"(": 18,
|
| 35 |
-
")": 19,
|
| 36 |
-
"*": 20,
|
| 37 |
-
"+": 21,
|
| 38 |
-
",": 22,
|
| 39 |
-
"-": 23,
|
| 40 |
-
".": 24,
|
| 41 |
-
"/": 25,
|
| 42 |
-
"0": 26,
|
| 43 |
-
"1": 27,
|
| 44 |
-
"2": 28,
|
| 45 |
-
"3": 29,
|
| 46 |
-
"4": 30,
|
| 47 |
-
"5": 31,
|
| 48 |
-
"6": 32,
|
| 49 |
-
"7": 33,
|
| 50 |
-
"8": 34,
|
| 51 |
-
"9": 35,
|
| 52 |
-
":": 36,
|
| 53 |
-
";": 37,
|
| 54 |
-
"<": 38,
|
| 55 |
-
"=": 39,
|
| 56 |
-
">": 40,
|
| 57 |
-
"?": 41,
|
| 58 |
-
"@": 42,
|
| 59 |
-
"A": 43,
|
| 60 |
-
"B": 44,
|
| 61 |
-
"C": 45,
|
| 62 |
-
"D": 46,
|
| 63 |
-
"E": 47,
|
| 64 |
-
"F": 48,
|
| 65 |
-
"G": 49,
|
| 66 |
-
"H": 50,
|
| 67 |
-
"I": 51,
|
| 68 |
-
"J": 52,
|
| 69 |
-
"K": 53,
|
| 70 |
-
"L": 54,
|
| 71 |
-
"M": 55,
|
| 72 |
-
"N": 56,
|
| 73 |
-
"O": 57,
|
| 74 |
-
"P": 58,
|
| 75 |
-
"Q": 59,
|
| 76 |
-
"R": 60,
|
| 77 |
-
"S": 61,
|
| 78 |
-
"T": 62,
|
| 79 |
-
"U": 63,
|
| 80 |
-
"V": 64,
|
| 81 |
-
"W": 65,
|
| 82 |
-
"X": 66,
|
| 83 |
-
"Y": 67,
|
| 84 |
-
"Z": 68,
|
| 85 |
-
"[": 69,
|
| 86 |
-
"\\": 70,
|
| 87 |
-
"]": 71,
|
| 88 |
-
"^": 72,
|
| 89 |
-
"`": 73,
|
| 90 |
-
"a": 74,
|
| 91 |
-
"b": 75,
|
| 92 |
-
"c": 76,
|
| 93 |
-
"d": 77,
|
| 94 |
-
"e": 78,
|
| 95 |
-
"f": 79,
|
| 96 |
-
"g": 80,
|
| 97 |
-
"h": 81,
|
| 98 |
-
"i": 82,
|
| 99 |
-
"j": 83,
|
| 100 |
-
"k": 84,
|
| 101 |
-
"l": 85,
|
| 102 |
-
"m": 86,
|
| 103 |
-
"n": 87,
|
| 104 |
-
"o": 88,
|
| 105 |
-
"p": 89,
|
| 106 |
-
"q": 90,
|
| 107 |
-
"r": 91,
|
| 108 |
-
"s": 92,
|
| 109 |
-
"t": 93,
|
| 110 |
-
"u": 94,
|
| 111 |
-
"v": 95,
|
| 112 |
-
"w": 96,
|
| 113 |
-
"x": 97,
|
| 114 |
-
"y": 98,
|
| 115 |
-
"z": 99,
|
| 116 |
-
"{": 100,
|
| 117 |
-
"|": 101,
|
| 118 |
-
"}": 102,
|
| 119 |
-
"~": 103,
|
| 120 |
-
"¡": 104,
|
| 121 |
-
"¢": 105,
|
| 122 |
-
"£": 106,
|
| 123 |
-
"¥": 107,
|
| 124 |
-
"§": 108,
|
| 125 |
-
"ª": 109,
|
| 126 |
-
"«": 110,
|
| 127 |
-
"": 111,
|
| 128 |
-
"®": 112,
|
| 129 |
-
"°": 113,
|
| 130 |
-
"±": 114,
|
| 131 |
-
"²": 115,
|
| 132 |
-
"³": 116,
|
| 133 |
-
"´": 117,
|
| 134 |
-
"¶": 118,
|
| 135 |
-
"·": 119,
|
| 136 |
-
"¹": 120,
|
| 137 |
-
"º": 121,
|
| 138 |
-
"»": 122,
|
| 139 |
-
"¼": 123,
|
| 140 |
-
"½": 124,
|
| 141 |
-
"¾": 125,
|
| 142 |
-
"¿": 126,
|
| 143 |
-
"À": 127,
|
| 144 |
-
"Á": 128,
|
| 145 |
-
"Â": 129,
|
| 146 |
-
"Ä": 130,
|
| 147 |
-
"Å": 131,
|
| 148 |
-
"Æ": 132,
|
| 149 |
-
"Ç": 133,
|
| 150 |
-
"È": 134,
|
| 151 |
-
"É": 135,
|
| 152 |
-
"Ê": 136,
|
| 153 |
-
"Í": 137,
|
| 154 |
-
"Ï": 138,
|
| 155 |
-
"Ñ": 139,
|
| 156 |
-
"Ó": 140,
|
| 157 |
-
"Ô": 141,
|
| 158 |
-
"Ö": 142,
|
| 159 |
-
"×": 143,
|
| 160 |
-
"Ù": 144,
|
| 161 |
-
"Ú": 145,
|
| 162 |
-
"Ü": 146,
|
| 163 |
-
"Ý": 147,
|
| 164 |
-
"Þ": 148,
|
| 165 |
-
"ß": 149,
|
| 166 |
-
"à": 150,
|
| 167 |
-
"á": 151,
|
| 168 |
-
"â": 152,
|
| 169 |
-
"ã": 153,
|
| 170 |
-
"ä": 154,
|
| 171 |
-
"å": 155,
|
| 172 |
-
"æ": 156,
|
| 173 |
-
"ç": 157,
|
| 174 |
-
"è": 158,
|
| 175 |
-
"é": 159,
|
| 176 |
-
"ê": 160,
|
| 177 |
-
"ë": 161,
|
| 178 |
-
"ì": 162,
|
| 179 |
-
"í": 163,
|
| 180 |
-
"î": 164,
|
| 181 |
-
"ï": 165,
|
| 182 |
-
"ð": 166,
|
| 183 |
-
"ñ": 167,
|
| 184 |
-
"ò": 168,
|
| 185 |
-
"ó": 169,
|
| 186 |
-
"ô": 170,
|
| 187 |
-
"õ": 171,
|
| 188 |
-
"ö": 172,
|
| 189 |
-
"ø": 173,
|
| 190 |
-
"ù": 174,
|
| 191 |
-
"ú": 175,
|
| 192 |
-
"û": 176,
|
| 193 |
-
"ü": 177,
|
| 194 |
-
"ý": 178,
|
| 195 |
-
"þ": 179,
|
| 196 |
-
"ÿ": 180,
|
| 197 |
-
"ā": 181,
|
| 198 |
-
"Ă": 182,
|
| 199 |
-
"ă": 183,
|
| 200 |
-
"ą": 184,
|
| 201 |
-
"ć": 185,
|
| 202 |
-
"č": 186,
|
| 203 |
-
"Đ": 187,
|
| 204 |
-
"đ": 188,
|
| 205 |
-
"ē": 189,
|
| 206 |
-
"ė": 190,
|
| 207 |
-
"ę": 191,
|
| 208 |
-
"ğ": 192,
|
| 209 |
-
"ġ": 193,
|
| 210 |
-
"ĩ": 194,
|
| 211 |
-
"ī": 195,
|
| 212 |
-
"ļ": 196,
|
| 213 |
-
"ł": 197,
|
| 214 |
-
"ń": 198,
|
| 215 |
-
"Ō": 199,
|
| 216 |
-
"ō": 200,
|
| 217 |
-
"Œ": 201,
|
| 218 |
-
"œ": 202,
|
| 219 |
-
"ŕ": 203,
|
| 220 |
-
"ś": 204,
|
| 221 |
-
"ş": 205,
|
| 222 |
-
"š": 206,
|
| 223 |
-
"ŧ": 207,
|
| 224 |
-
"ũ": 208,
|
| 225 |
-
"ū": 209,
|
| 226 |
-
"ŭ": 210,
|
| 227 |
-
"ů": 211,
|
| 228 |
-
"ű": 212,
|
| 229 |
-
"ż": 213,
|
| 230 |
-
"Ž": 214,
|
| 231 |
-
"ž": 215,
|
| 232 |
-
"ſ": 216,
|
| 233 |
-
"Ơ": 217,
|
| 234 |
-
"ơ": 218,
|
| 235 |
-
"Ư": 219,
|
| 236 |
-
"ư": 220,
|
| 237 |
-
"ǁ": 221,
|
| 238 |
-
"ǂ": 222,
|
| 239 |
-
"ǐ": 223,
|
| 240 |
-
"ǘ": 224,
|
| 241 |
-
"ǧ": 225,
|
| 242 |
-
"ș": 226,
|
| 243 |
-
"Ȝ": 227,
|
| 244 |
-
"ȝ": 228,
|
| 245 |
-
"ȟ": 229,
|
| 246 |
-
"ɛ": 230,
|
| 247 |
-
"ʰ": 231,
|
| 248 |
-
"ˆ": 232,
|
| 249 |
-
"ˈ": 233,
|
| 250 |
-
"ˢ": 234,
|
| 251 |
-
"̃": 235,
|
| 252 |
-
"̍": 236,
|
| 253 |
-
"̣": 237,
|
| 254 |
-
"̱": 238,
|
| 255 |
-
"͈": 239,
|
| 256 |
-
"α": 240,
|
| 257 |
-
"β": 241,
|
| 258 |
-
"γ": 242,
|
| 259 |
-
"δ": 243,
|
| 260 |
-
"ε": 244,
|
| 261 |
-
"η": 245,
|
| 262 |
-
"κ": 246,
|
| 263 |
-
"μ": 247,
|
| 264 |
-
"ξ": 248,
|
| 265 |
-
"π": 249,
|
| 266 |
-
"ς": 250,
|
| 267 |
-
"σ": 251,
|
| 268 |
-
"χ": 252,
|
| 269 |
-
"ψ": 253,
|
| 270 |
-
"а": 254,
|
| 271 |
-
"д": 255,
|
| 272 |
-
"е": 256,
|
| 273 |
-
"з": 257,
|
| 274 |
-
"и": 258,
|
| 275 |
-
"к": 259,
|
| 276 |
-
"л": 260,
|
| 277 |
-
"о": 261,
|
| 278 |
-
"п": 262,
|
| 279 |
-
"р": 263,
|
| 280 |
-
"с": 264,
|
| 281 |
-
"т": 265,
|
| 282 |
-
"ч": 266,
|
| 283 |
-
"ь": 267,
|
| 284 |
-
"ง": 268,
|
| 285 |
-
"ย": 269,
|
| 286 |
-
"า": 270,
|
| 287 |
-
"่": 271,
|
| 288 |
-
"ည": 272,
|
| 289 |
-
"လ": 273,
|
| 290 |
-
"း": 274,
|
| 291 |
-
"်": 275,
|
| 292 |
-
"ᵈ": 276,
|
| 293 |
-
"ᵗ": 277,
|
| 294 |
-
"ḅ": 278,
|
| 295 |
-
"ḍ": 279,
|
| 296 |
-
"ḳ": 280,
|
| 297 |
-
"ṅ": 281,
|
| 298 |
-
"Ṭ": 282,
|
| 299 |
-
"ẓ": 283,
|
| 300 |
-
"ạ": 284,
|
| 301 |
-
"Ả": 285,
|
| 302 |
-
"ả": 286,
|
| 303 |
-
"Ấ": 287,
|
| 304 |
-
"ấ": 288,
|
| 305 |
-
"ầ": 289,
|
| 306 |
-
"ẩ": 290,
|
| 307 |
-
"ẫ": 291,
|
| 308 |
-
"ậ": 292,
|
| 309 |
-
"ắ": 293,
|
| 310 |
-
"ằ": 294,
|
| 311 |
-
"ẳ": 295,
|
| 312 |
-
"ẵ": 296,
|
| 313 |
-
"ặ": 297,
|
| 314 |
-
"ẹ": 298,
|
| 315 |
-
"ẻ": 299,
|
| 316 |
-
"ẽ": 300,
|
| 317 |
-
"Ế": 301,
|
| 318 |
-
"ế": 302,
|
| 319 |
-
"Ề": 303,
|
| 320 |
-
"ề": 304,
|
| 321 |
-
"ể": 305,
|
| 322 |
-
"ễ": 306,
|
| 323 |
-
"ệ": 307,
|
| 324 |
-
"ỉ": 308,
|
| 325 |
-
"ị": 309,
|
| 326 |
-
"ọ": 310,
|
| 327 |
-
"ỏ": 311,
|
| 328 |
-
"Ố": 312,
|
| 329 |
-
"ố": 313,
|
| 330 |
-
"Ồ": 314,
|
| 331 |
-
"ồ": 315,
|
| 332 |
-
"Ổ": 316,
|
| 333 |
-
"ổ": 317,
|
| 334 |
-
"ỗ": 318,
|
| 335 |
-
"Ộ": 319,
|
| 336 |
-
"ộ": 320,
|
| 337 |
-
"ớ": 321,
|
| 338 |
-
"Ờ": 322,
|
| 339 |
-
"ờ": 323,
|
| 340 |
-
"Ở": 324,
|
| 341 |
-
"ở": 325,
|
| 342 |
-
"ỡ": 326,
|
| 343 |
-
"ợ": 327,
|
| 344 |
-
"ụ": 328,
|
| 345 |
-
"ủ": 329,
|
| 346 |
-
"Ứ": 330,
|
| 347 |
-
"ứ": 331,
|
| 348 |
-
"Ừ": 332,
|
| 349 |
-
"ừ": 333,
|
| 350 |
-
"ử": 334,
|
| 351 |
-
"ữ": 335,
|
| 352 |
-
"ự": 336,
|
| 353 |
-
"ỳ": 337,
|
| 354 |
-
"ỵ": 338,
|
| 355 |
-
"Ỷ": 339,
|
| 356 |
-
"ỷ": 340,
|
| 357 |
-
"ỹ": 341,
|
| 358 |
-
"ὖ": 342,
|
| 359 |
-
"ὼ": 343,
|
| 360 |
-
"ῆ": 344,
|
| 361 |
-
"": 345,
|
| 362 |
-
"‐": 346,
|
| 363 |
-
"—": 347,
|
| 364 |
-
"―": 348,
|
| 365 |
-
"†": 349,
|
| 366 |
-
"•": 350,
|
| 367 |
-
"…": 351,
|
| 368 |
-
"‰": 352,
|
| 369 |
-
"′": 353,
|
| 370 |
-
"″": 354,
|
| 371 |
-
"⁄": 355,
|
| 372 |
-
"⁷": 356,
|
| 373 |
-
"⁻": 357,
|
| 374 |
-
"₀": 358,
|
| 375 |
-
"₁": 359,
|
| 376 |
-
"₂": 360,
|
| 377 |
-
"₃": 361,
|
| 378 |
-
"₄": 362,
|
| 379 |
-
"₅": 363,
|
| 380 |
-
"₆": 364,
|
| 381 |
-
"₇": 365,
|
| 382 |
-
"₈": 366,
|
| 383 |
-
"€": 367,
|
| 384 |
-
"₹": 368,
|
| 385 |
-
"⅓": 369,
|
| 386 |
-
"⅔": 370,
|
| 387 |
-
"⅖": 371,
|
| 388 |
-
"⅙": 372,
|
| 389 |
-
"⅛": 373,
|
| 390 |
-
"⅝": 374,
|
| 391 |
-
"√": 375,
|
| 392 |
-
"│": 376,
|
| 393 |
-
"♦": 377,
|
| 394 |
-
"⚓": 378,
|
| 395 |
-
"✈": 379,
|
| 396 |
-
"✠": 380,
|
| 397 |
-
"✨": 381,
|
| 398 |
-
"⟙": 382,
|
| 399 |
-
"⸺": 383,
|
| 400 |
-
"。": 384,
|
| 401 |
-
"〈": 385,
|
| 402 |
-
"な": 386,
|
| 403 |
-
"三": 387,
|
| 404 |
-
"次": 388,
|
| 405 |
-
"肿": 389,
|
| 406 |
-
"臃": 390,
|
| 407 |
-
"구": 391,
|
| 408 |
-
"로": 392,
|
| 409 |
-
"요": 393,
|
| 410 |
-
"ﷺ": 394,
|
| 411 |
-
"️": 395,
|
| 412 |
-
"𝑥": 396,
|
| 413 |
-
"𝑦": 397,
|
| 414 |
-
"🌊": 398,
|
| 415 |
-
"🌿": 399,
|
| 416 |
-
"💦": 400,
|
| 417 |
-
"💨": 401
|
| 418 |
-
},
|
| 419 |
-
"phoneme_symbols": {
|
| 420 |
-
"0": "_",
|
| 421 |
-
"1": "<de>",
|
| 422 |
-
"2": "<en_gb>",
|
| 423 |
-
"3": "<en_us>",
|
| 424 |
-
"4": "<es>",
|
| 425 |
-
"5": "<fr>",
|
| 426 |
-
"6": "<it>",
|
| 427 |
-
"7": "<vi>",
|
| 428 |
-
"8": "<end>",
|
| 429 |
-
"9": " ",
|
| 430 |
-
"10": "!",
|
| 431 |
-
"11": ",",
|
| 432 |
-
"12": "-",
|
| 433 |
-
"13": ".",
|
| 434 |
-
"14": "1",
|
| 435 |
-
"15": "2",
|
| 436 |
-
"16": "4",
|
| 437 |
-
"17": "5",
|
| 438 |
-
"18": "6",
|
| 439 |
-
"19": "7",
|
| 440 |
-
"20": ":",
|
| 441 |
-
"21": ";",
|
| 442 |
-
"22": "?",
|
| 443 |
-
"23": "a",
|
| 444 |
-
"24": "b",
|
| 445 |
-
"25": "c",
|
| 446 |
-
"26": "d",
|
| 447 |
-
"27": "e",
|
| 448 |
-
"28": "f",
|
| 449 |
-
"29": "h",
|
| 450 |
-
"30": "i",
|
| 451 |
-
"31": "j",
|
| 452 |
-
"32": "k",
|
| 453 |
-
"33": "l",
|
| 454 |
-
"34": "m",
|
| 455 |
-
"35": "n",
|
| 456 |
-
"36": "o",
|
| 457 |
-
"37": "p",
|
| 458 |
-
"38": "q",
|
| 459 |
-
"39": "r",
|
| 460 |
-
"40": "s",
|
| 461 |
-
"41": "t",
|
| 462 |
-
"42": "u",
|
| 463 |
-
"43": "v",
|
| 464 |
-
"44": "w",
|
| 465 |
-
"45": "x",
|
| 466 |
-
"46": "y",
|
| 467 |
-
"47": "z",
|
| 468 |
-
"48": "«",
|
| 469 |
-
"49": "»",
|
| 470 |
-
"50": "æ",
|
| 471 |
-
"51": "ç",
|
| 472 |
-
"52": "ð",
|
| 473 |
-
"53": "ø",
|
| 474 |
-
"54": "ŋ",
|
| 475 |
-
"55": "œ",
|
| 476 |
-
"56": "ɐ",
|
| 477 |
-
"57": "ɑ",
|
| 478 |
-
"58": "ɒ",
|
| 479 |
-
"59": "ɔ",
|
| 480 |
-
"60": "ɗ",
|
| 481 |
-
"61": "ə",
|
| 482 |
-
"62": "ɚ",
|
| 483 |
-
"63": "ɛ",
|
| 484 |
-
"64": "ɜ",
|
| 485 |
-
"65": "ɟ",
|
| 486 |
-
"66": "ɡ",
|
| 487 |
-
"67": "ɣ",
|
| 488 |
-
"68": "ɨ",
|
| 489 |
-
"69": "ɪ",
|
| 490 |
-
"70": "ɬ",
|
| 491 |
-
"71": "ɯ",
|
| 492 |
-
"72": "ɲ",
|
| 493 |
-
"73": "ɹ",
|
| 494 |
-
"74": "ɾ",
|
| 495 |
-
"75": "ʁ",
|
| 496 |
-
"76": "ʃ",
|
| 497 |
-
"77": "ʊ",
|
| 498 |
-
"78": "ʌ",
|
| 499 |
-
"79": "ʎ",
|
| 500 |
-
"80": "ʐ",
|
| 501 |
-
"81": "ʒ",
|
| 502 |
-
"82": "ʔ",
|
| 503 |
-
"83": "ʝ",
|
| 504 |
-
"84": "ʲ",
|
| 505 |
-
"85": "ˈ",
|
| 506 |
-
"86": "ˌ",
|
| 507 |
-
"87": "ː",
|
| 508 |
-
"88": "̃",
|
| 509 |
-
"89": "̩",
|
| 510 |
-
"90": "̪",
|
| 511 |
-
"91": "β",
|
| 512 |
-
"92": "θ",
|
| 513 |
-
"93": "ᵻ",
|
| 514 |
-
"94": "—",
|
| 515 |
-
"95": "…"
|
| 516 |
-
}
|
| 517 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreml/assets/languages.json
DELETED
|
@@ -1,30 +0,0 @@
|
|
| 1 |
-
[
|
| 2 |
-
{
|
| 3 |
-
"id": "en_us",
|
| 4 |
-
"index": 0
|
| 5 |
-
},
|
| 6 |
-
{
|
| 7 |
-
"id": "en_gb",
|
| 8 |
-
"index": 1
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"id": "es",
|
| 12 |
-
"index": 2
|
| 13 |
-
},
|
| 14 |
-
{
|
| 15 |
-
"id": "it",
|
| 16 |
-
"index": 3
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"id": "fr",
|
| 20 |
-
"index": 4
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"id": "de",
|
| 24 |
-
"index": 5
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"id": "vi",
|
| 28 |
-
"index": 6
|
| 29 |
-
}
|
| 30 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreml/assets/phone_vocab.json
DELETED
|
@@ -1,111 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"schema_version": 1,
|
| 3 |
-
"mode": "scyllasband_ipa_phone_symbols",
|
| 4 |
-
"special_tokens": [
|
| 5 |
-
"<pad>",
|
| 6 |
-
"<unk>",
|
| 7 |
-
"<sil>",
|
| 8 |
-
"<pause_comma>",
|
| 9 |
-
"<pause_semicolon>",
|
| 10 |
-
"<pause_colon>",
|
| 11 |
-
"<pause_dash>",
|
| 12 |
-
"<ellipsis>",
|
| 13 |
-
"<end_stmt>",
|
| 14 |
-
"<end_question>",
|
| 15 |
-
"<end_exclaim>",
|
| 16 |
-
"<ctx_sentence_start>",
|
| 17 |
-
"<ctx_continuation>",
|
| 18 |
-
"<ctx_sentence_end>",
|
| 19 |
-
"<ctx_chunk_continue>"
|
| 20 |
-
],
|
| 21 |
-
"vocab_size": 87,
|
| 22 |
-
"token_to_id": {
|
| 23 |
-
"<pad>": 0,
|
| 24 |
-
"<unk>": 1,
|
| 25 |
-
"<sil>": 2,
|
| 26 |
-
"<pause_comma>": 3,
|
| 27 |
-
"<pause_semicolon>": 4,
|
| 28 |
-
"<pause_colon>": 5,
|
| 29 |
-
"<pause_dash>": 6,
|
| 30 |
-
"<ellipsis>": 7,
|
| 31 |
-
"<end_stmt>": 8,
|
| 32 |
-
"<end_question>": 9,
|
| 33 |
-
"<end_exclaim>": 10,
|
| 34 |
-
"<ctx_sentence_start>": 11,
|
| 35 |
-
"<ctx_continuation>": 12,
|
| 36 |
-
"<ctx_sentence_end>": 13,
|
| 37 |
-
"<ctx_chunk_continue>": 14,
|
| 38 |
-
"1": 15,
|
| 39 |
-
"2": 16,
|
| 40 |
-
"4": 17,
|
| 41 |
-
"5": 18,
|
| 42 |
-
"6": 19,
|
| 43 |
-
"7": 20,
|
| 44 |
-
"a": 21,
|
| 45 |
-
"b": 22,
|
| 46 |
-
"c": 23,
|
| 47 |
-
"d": 24,
|
| 48 |
-
"e": 25,
|
| 49 |
-
"f": 26,
|
| 50 |
-
"h": 27,
|
| 51 |
-
"i": 28,
|
| 52 |
-
"j": 29,
|
| 53 |
-
"k": 30,
|
| 54 |
-
"l": 31,
|
| 55 |
-
"m": 32,
|
| 56 |
-
"n": 33,
|
| 57 |
-
"o": 34,
|
| 58 |
-
"p": 35,
|
| 59 |
-
"r": 36,
|
| 60 |
-
"s": 37,
|
| 61 |
-
"t": 38,
|
| 62 |
-
"u": 39,
|
| 63 |
-
"v": 40,
|
| 64 |
-
"w": 41,
|
| 65 |
-
"x": 42,
|
| 66 |
-
"y": 43,
|
| 67 |
-
"z": 44,
|
| 68 |
-
"æ": 45,
|
| 69 |
-
"ç": 46,
|
| 70 |
-
"ð": 47,
|
| 71 |
-
"ø": 48,
|
| 72 |
-
"ŋ": 49,
|
| 73 |
-
"œ": 50,
|
| 74 |
-
"ɐ": 51,
|
| 75 |
-
"ɑ": 52,
|
| 76 |
-
"ɒ": 53,
|
| 77 |
-
"ɔ": 54,
|
| 78 |
-
"ɗ": 55,
|
| 79 |
-
"ə": 56,
|
| 80 |
-
"ɚ": 57,
|
| 81 |
-
"ɛ": 58,
|
| 82 |
-
"ɜ": 59,
|
| 83 |
-
"ɟ": 60,
|
| 84 |
-
"ɡ": 61,
|
| 85 |
-
"ɣ": 62,
|
| 86 |
-
"ɪ": 63,
|
| 87 |
-
"ɯ": 64,
|
| 88 |
-
"ɲ": 65,
|
| 89 |
-
"ɹ": 66,
|
| 90 |
-
"ɾ": 67,
|
| 91 |
-
"ʁ": 68,
|
| 92 |
-
"ʃ": 69,
|
| 93 |
-
"ʊ": 70,
|
| 94 |
-
"ʌ": 71,
|
| 95 |
-
"ʎ": 72,
|
| 96 |
-
"ʐ": 73,
|
| 97 |
-
"ʒ": 74,
|
| 98 |
-
"ʔ": 75,
|
| 99 |
-
"ʝ": 76,
|
| 100 |
-
"ʲ": 77,
|
| 101 |
-
"ˈ": 78,
|
| 102 |
-
"ˌ": 79,
|
| 103 |
-
"ː": 80,
|
| 104 |
-
"̃": 81,
|
| 105 |
-
"̩": 82,
|
| 106 |
-
"̪": 83,
|
| 107 |
-
"β": 84,
|
| 108 |
-
"θ": 85,
|
| 109 |
-
"ᵻ": 86
|
| 110 |
-
}
|
| 111 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreml/assets/voices.json
DELETED
|
@@ -1,42 +0,0 @@
|
|
| 1 |
-
[
|
| 2 |
-
{
|
| 3 |
-
"id": "ariadne",
|
| 4 |
-
"index": 0
|
| 5 |
-
},
|
| 6 |
-
{
|
| 7 |
-
"id": "felix",
|
| 8 |
-
"index": 1
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"id": "gwen",
|
| 12 |
-
"index": 2
|
| 13 |
-
},
|
| 14 |
-
{
|
| 15 |
-
"id": "ink",
|
| 16 |
-
"index": 3
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"id": "max",
|
| 20 |
-
"index": 4
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"id": "orpheus",
|
| 24 |
-
"index": 5
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"id": "rex",
|
| 28 |
-
"index": 6
|
| 29 |
-
},
|
| 30 |
-
{
|
| 31 |
-
"id": "scylla",
|
| 32 |
-
"index": 7
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"id": "stone",
|
| 36 |
-
"index": 8
|
| 37 |
-
},
|
| 38 |
-
{
|
| 39 |
-
"id": "tuesday",
|
| 40 |
-
"index": 9
|
| 41 |
-
}
|
| 42 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreml/coreml/duration_predictor.mlmodelc/analytics/coremldata.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:953e274e93c3abfae6f04977436816dc28223ef61d4e91e4191f67837740a2e8
|
| 3 |
-
size 243
|
|
|
|
|
|
|
|
|
|
|
|
coreml/coreml/duration_predictor.mlmodelc/coremldata.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c090d28d8df68312410867a49963b5fbda00f5883178969df17b1b0c86e7eff2
|
| 3 |
-
size 554
|
|
|
|
|
|
|
|
|
|
|
|
coreml/coreml/duration_predictor.mlmodelc/model.mil
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
coreml/coreml/duration_predictor.mlmodelc/weights/weight.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:5383e19195d6807cf6632d2c82b51b86aaa947ba51d8042434f73b5039c70ea4
|
| 3 |
-
size 10562880
|
|
|
|
|
|
|
|
|
|
|
|
coreml/coreml/g2p.mlmodelc/analytics/coremldata.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:61936fdfe11637e628b2134025bea29d673c98e93ce6f01c05e7b5da124563b8
|
| 3 |
-
size 243
|
|
|
|
|
|
|
|
|
|
|
|
coreml/coreml/g2p.mlmodelc/coremldata.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f5fc8bee0186f33fa14d35a59a58ec3393676d07bdf03802a3836d806662cd03
|
| 3 |
-
size 377
|
|
|
|
|
|
|
|
|
|
|
|
coreml/coreml/g2p.mlmodelc/model.mil
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
coreml/coreml/g2p.mlmodelc/weights/weight.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:045da2991ed2a42ba027aaa6b83813054f410b6eedfdce82f2ab287ec4ca74e2
|
| 3 |
-
size 27346752
|
|
|
|
|
|
|
|
|
|
|
|
coreml/coreml/vector_context_encoder.mlmodelc/analytics/coremldata.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f89405fefad88549b521a819805c5c1781e0c930c03b8f670b1e1539aafe88c6
|
| 3 |
-
size 243
|
|
|
|
|
|
|
|
|
|
|
|
coreml/coreml/vector_context_encoder.mlmodelc/coremldata.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d031d4ef221bc846aec129114aec7366fcb6126dacae44c24c4b344c54dc6c5a
|
| 3 |
-
size 476
|
|
|
|
|
|
|
|
|
|
|
|
coreml/coreml/vector_context_encoder.mlmodelc/model.mil
DELETED
|
@@ -1,267 +0,0 @@
|
|
| 1 |
-
program(1.3)
|
| 2 |
-
[buildInfo = dict<string, string>({{"coremlc-component-MIL", "3600.16.1"}, {"coremlc-version", "3600.25.2"}})]
|
| 3 |
-
{
|
| 4 |
-
func main<ios18>(tensor<int32, [1, 512]> span_context_mask, tensor<int32, [1, 512]> span_context_phone_ids, tensor<int32, [1, 512]> span_context_segment_ids) {
|
| 5 |
-
int32 var_15 = const()[name = string("op_15"), val = int32(0)];
|
| 6 |
-
tensor<bool, [1, 512]> span_context_mask_1 = not_equal(x = span_context_mask, y = var_15)[name = string("span_context_mask")];
|
| 7 |
-
int32 var_30 = const()[name = string("op_30"), val = int32(-1)];
|
| 8 |
-
int32 var_35 = const()[name = string("op_35"), val = int32(2)];
|
| 9 |
-
int32 var_36 = const()[name = string("op_36"), val = int32(86)];
|
| 10 |
-
int32 var_38 = const()[name = string("op_38"), val = int32(1)];
|
| 11 |
-
int32 var_40 = const()[name = string("op_40"), val = int32(0)];
|
| 12 |
-
tensor<int32, [1, 512]> var_55 = maximum(x = span_context_phone_ids, y = var_40)[name = string("op_55")];
|
| 13 |
-
tensor<int32, [1, 512]> input_1 = minimum(x = var_55, y = var_36)[name = string("input_1")];
|
| 14 |
-
tensor<int32, [1, 512]> var_59 = maximum(x = span_context_segment_ids, y = var_40)[name = string("op_59")];
|
| 15 |
-
tensor<int32, [1, 512]> input_3 = minimum(x = var_59, y = var_35)[name = string("input_3")];
|
| 16 |
-
string var_64_dtype_0 = const()[name = string("op_64_dtype_0"), val = string("int32")];
|
| 17 |
-
bool var_65_exclusive_0 = const()[name = string("op_65_exclusive_0"), val = bool(false)];
|
| 18 |
-
bool var_65_reverse_0 = const()[name = string("op_65_reverse_0"), val = bool(false)];
|
| 19 |
-
tensor<int32, [1, 512]> var_64 = cast(dtype = var_64_dtype_0, x = span_context_mask_1)[name = string("cast_13")];
|
| 20 |
-
tensor<int32, [1, 512]> var_65 = cumsum(axis = var_38, exclusive = var_65_exclusive_0, reverse = var_65_reverse_0, x = var_64)[name = string("op_65")];
|
| 21 |
-
int32 var_66 = const()[name = string("op_66"), val = int32(1)];
|
| 22 |
-
tensor<int32, [1, 512]> var_67 = sub(x = var_65, y = var_66)[name = string("op_67")];
|
| 23 |
-
tensor<int32, [1, 512]> input_5 = maximum(x = var_67, y = var_40)[name = string("input_5")];
|
| 24 |
-
int32 var_70_batch_dims_0 = const()[name = string("op_70_batch_dims_0"), val = int32(0)];
|
| 25 |
-
bool var_70_validate_indices_0 = const()[name = string("op_70_validate_indices_0"), val = bool(false)];
|
| 26 |
-
tensor<fp16, [87, 512]> module_flow_phone_embed_weight_to_fp16_quantized = constexpr_blockwise_shift_scale(data = tensor<int8, [87, 512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(64))), scale = tensor<fp16, [87, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(44672))))[name = string("module_flow_phone_embed_weight_to_fp16_quantized")];
|
| 27 |
-
string input_1_to_int16_dtype_0 = const()[name = string("input_1_to_int16_dtype_0"), val = string("int16")];
|
| 28 |
-
string cast_24_dtype_0 = const()[name = string("cast_24_dtype_0"), val = string("int32")];
|
| 29 |
-
int32 greater_equal_0_y_0 = const()[name = string("greater_equal_0_y_0"), val = int32(0)];
|
| 30 |
-
tensor<int16, [1, 512]> input_1_to_int16 = cast(dtype = input_1_to_int16_dtype_0, x = input_1)[name = string("cast_12")];
|
| 31 |
-
tensor<int32, [1, 512]> cast_24 = cast(dtype = cast_24_dtype_0, x = input_1_to_int16)[name = string("cast_11")];
|
| 32 |
-
tensor<bool, [1, 512]> greater_equal_0 = greater_equal(x = cast_24, y = greater_equal_0_y_0)[name = string("greater_equal_0")];
|
| 33 |
-
int32 slice_by_index_0 = const()[name = string("slice_by_index_0"), val = int32(87)];
|
| 34 |
-
tensor<int32, [1, 512]> add_0 = add(x = cast_24, y = slice_by_index_0)[name = string("add_0")];
|
| 35 |
-
tensor<int32, [1, 512]> select_0 = select(a = cast_24, b = add_0, cond = greater_equal_0)[name = string("select_0")];
|
| 36 |
-
string select_0_to_int16_dtype_0 = const()[name = string("select_0_to_int16_dtype_0"), val = string("int16")];
|
| 37 |
-
string cast_0_dtype_0 = const()[name = string("cast_0_dtype_0"), val = string("int32")];
|
| 38 |
-
int32 greater_equal_0_y_0_1 = const()[name = string("greater_equal_0_y_0_1"), val = int32(0)];
|
| 39 |
-
tensor<int16, [1, 512]> select_0_to_int16 = cast(dtype = select_0_to_int16_dtype_0, x = select_0)[name = string("cast_10")];
|
| 40 |
-
tensor<int32, [1, 512]> cast_0 = cast(dtype = cast_0_dtype_0, x = select_0_to_int16)[name = string("cast_9")];
|
| 41 |
-
tensor<bool, [1, 512]> greater_equal_0_1 = greater_equal(x = cast_0, y = greater_equal_0_y_0_1)[name = string("greater_equal_0_1")];
|
| 42 |
-
int32 slice_by_index_0_1 = const()[name = string("slice_by_index_0_1"), val = int32(87)];
|
| 43 |
-
tensor<int32, [1, 512]> add_0_1 = add(x = cast_0, y = slice_by_index_0_1)[name = string("add_0_1")];
|
| 44 |
-
tensor<int32, [1, 512]> select_0_1 = select(a = cast_0, b = add_0_1, cond = greater_equal_0_1)[name = string("select_0_1")];
|
| 45 |
-
int32 op_70_cast_fp16_cast_uint16_cast_uint16_axis_0 = const()[name = string("op_70_cast_fp16_cast_uint16_cast_uint16_axis_0"), val = int32(0)];
|
| 46 |
-
tensor<fp16, [1, 512, 512]> op_70_cast_fp16_cast_uint16_cast_uint16 = gather(axis = op_70_cast_fp16_cast_uint16_cast_uint16_axis_0, batch_dims = var_70_batch_dims_0, indices = select_0_1, validate_indices = var_70_validate_indices_0, x = module_flow_phone_embed_weight_to_fp16_quantized)[name = string("op_70_cast_fp16_cast_uint16_cast_uint16")];
|
| 47 |
-
int32 var_72_axis_0 = const()[name = string("op_72_axis_0"), val = int32(0)];
|
| 48 |
-
int32 var_72_batch_dims_0 = const()[name = string("op_72_batch_dims_0"), val = int32(0)];
|
| 49 |
-
bool var_72_validate_indices_0 = const()[name = string("op_72_validate_indices_0"), val = bool(false)];
|
| 50 |
-
tensor<fp16, [3, 512]> module_flow_span_segment_embed_weight_to_fp16 = const()[name = string("module_flow_span_segment_embed_weight_to_fp16"), val = tensor<fp16, [3, 512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(44928)))];
|
| 51 |
-
string input_3_to_uint16_dtype_0 = const()[name = string("input_3_to_uint16_dtype_0"), val = string("uint16")];
|
| 52 |
-
tensor<uint16, [1, 512]> input_3_to_uint16 = cast(dtype = input_3_to_uint16_dtype_0, x = input_3)[name = string("cast_8")];
|
| 53 |
-
tensor<fp16, [1, 512, 512]> var_72_cast_fp16_cast_uint16 = gather(axis = var_72_axis_0, batch_dims = var_72_batch_dims_0, indices = input_3_to_uint16, validate_indices = var_72_validate_indices_0, x = module_flow_span_segment_embed_weight_to_fp16)[name = string("op_72_cast_fp16_cast_uint16")];
|
| 54 |
-
tensor<fp16, [1, 512, 512]> var_73_cast_fp16 = add(x = op_70_cast_fp16_cast_uint16_cast_uint16, y = var_72_cast_fp16_cast_uint16)[name = string("op_73_cast_fp16")];
|
| 55 |
-
int32 var_75_axis_0 = const()[name = string("op_75_axis_0"), val = int32(0)];
|
| 56 |
-
int32 var_75_batch_dims_0 = const()[name = string("op_75_batch_dims_0"), val = int32(0)];
|
| 57 |
-
bool var_75_validate_indices_0 = const()[name = string("op_75_validate_indices_0"), val = bool(false)];
|
| 58 |
-
tensor<fp16, [768, 512]> module_flow_span_position_embed_weight_to_fp16_quantized = constexpr_blockwise_shift_scale(data = tensor<int8, [768, 512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(48064))), scale = tensor<fp16, [768, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(441344))))[name = string("module_flow_span_position_embed_weight_to_fp16_quantized")];
|
| 59 |
-
string input_5_to_uint16_dtype_0 = const()[name = string("input_5_to_uint16_dtype_0"), val = string("uint16")];
|
| 60 |
-
tensor<uint16, [1, 512]> input_5_to_uint16 = cast(dtype = input_5_to_uint16_dtype_0, x = input_5)[name = string("cast_7")];
|
| 61 |
-
tensor<fp16, [1, 512, 512]> var_75_cast_fp16_cast_uint16 = gather(axis = var_75_axis_0, batch_dims = var_75_batch_dims_0, indices = input_5_to_uint16, validate_indices = var_75_validate_indices_0, x = module_flow_span_position_embed_weight_to_fp16_quantized)[name = string("op_75_cast_fp16_cast_uint16")];
|
| 62 |
-
tensor<fp16, [1, 512, 512]> hidden_1_cast_fp16 = add(x = var_73_cast_fp16, y = var_75_cast_fp16_cast_uint16)[name = string("hidden_1_cast_fp16")];
|
| 63 |
-
tensor<int32, [1]> var_82_axes_0 = const()[name = string("op_82_axes_0"), val = tensor<int32, [1]>([-1])];
|
| 64 |
-
tensor<bool, [1, 512, 1]> var_82 = expand_dims(axes = var_82_axes_0, x = span_context_mask_1)[name = string("op_82")];
|
| 65 |
-
tensor<bool, [1, 512, 1]> var_83 = logical_not(x = var_82)[name = string("op_83")];
|
| 66 |
-
fp16 var_18_to_fp16 = const()[name = string("op_18_to_fp16"), val = fp16(0x0p+0)];
|
| 67 |
-
tensor<fp16, [1, 512, 512]> hidden_3_cast_fp16 = select(a = var_18_to_fp16, b = hidden_1_cast_fp16, cond = var_83)[name = string("hidden_3_cast_fp16")];
|
| 68 |
-
tensor<int32, [1]> input_7_axes_0 = const()[name = string("input_7_axes_0"), val = tensor<int32, [1]>([-1])];
|
| 69 |
-
tensor<fp16, [512]> module_flow_span_ordered_encoder_blocks_0_norm_attention_weight_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_0_norm_attention_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(442944)))];
|
| 70 |
-
tensor<fp16, [512]> module_flow_span_ordered_encoder_blocks_0_norm_attention_bias_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_0_norm_attention_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(444032)))];
|
| 71 |
-
fp16 var_28_to_fp16 = const()[name = string("op_28_to_fp16"), val = fp16(0x1.5p-17)];
|
| 72 |
-
tensor<fp16, [1, 512, 512]> input_7_cast_fp16 = layer_norm(axes = input_7_axes_0, beta = module_flow_span_ordered_encoder_blocks_0_norm_attention_bias_to_fp16, epsilon = var_28_to_fp16, gamma = module_flow_span_ordered_encoder_blocks_0_norm_attention_weight_to_fp16, x = hidden_3_cast_fp16)[name = string("input_7_cast_fp16")];
|
| 73 |
-
tensor<fp16, [1536, 512]> module_flow_span_ordered_encoder_blocks_0_qkv_weight_to_fp16_quantized = constexpr_blockwise_shift_scale(data = tensor<int8, [1536, 512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(445120))), scale = tensor<fp16, [1536, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(1231616))))[name = string("module_flow_span_ordered_encoder_blocks_0_qkv_weight_to_fp16_quantized")];
|
| 74 |
-
tensor<fp16, [1536]> module_flow_span_ordered_encoder_blocks_0_qkv_bias_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_0_qkv_bias_to_fp16"), val = tensor<fp16, [1536]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(1234752)))];
|
| 75 |
-
tensor<fp16, [1, 512, 1536]> linear_0_cast_fp16 = linear(bias = module_flow_span_ordered_encoder_blocks_0_qkv_bias_to_fp16, weight = module_flow_span_ordered_encoder_blocks_0_qkv_weight_to_fp16_quantized, x = input_7_cast_fp16)[name = string("linear_0_cast_fp16")];
|
| 76 |
-
tensor<int32, [5]> var_100 = const()[name = string("op_100"), val = tensor<int32, [5]>([1, 512, 3, 8, 64])];
|
| 77 |
-
tensor<fp16, [1, 512, 3, 8, 64]> qkv_1_cast_fp16 = reshape(shape = var_100, x = linear_0_cast_fp16)[name = string("qkv_1_cast_fp16")];
|
| 78 |
-
tensor<int32, [3]> var_102_split_sizes_0 = const()[name = string("op_102_split_sizes_0"), val = tensor<int32, [3]>([1, 1, 1])];
|
| 79 |
-
int32 var_102_axis_0 = const()[name = string("op_102_axis_0"), val = int32(2)];
|
| 80 |
-
tensor<fp16, [1, 512, 1, 8, 64]> var_102_cast_fp16_0, tensor<fp16, [1, 512, 1, 8, 64]> var_102_cast_fp16_1, tensor<fp16, [1, 512, 1, 8, 64]> var_102_cast_fp16_2 = split(axis = var_102_axis_0, split_sizes = var_102_split_sizes_0, x = qkv_1_cast_fp16)[name = string("op_102_cast_fp16")];
|
| 81 |
-
tensor<int32, [1]> squeeze_0_axes_0 = const()[name = string("squeeze_0_axes_0"), val = tensor<int32, [1]>([2])];
|
| 82 |
-
tensor<fp16, [1, 512, 8, 64]> squeeze_0_cast_fp16 = squeeze(axes = squeeze_0_axes_0, x = var_102_cast_fp16_0)[name = string("squeeze_0_cast_fp16")];
|
| 83 |
-
tensor<int32, [1]> squeeze_1_axes_0 = const()[name = string("squeeze_1_axes_0"), val = tensor<int32, [1]>([2])];
|
| 84 |
-
tensor<fp16, [1, 512, 8, 64]> squeeze_1_cast_fp16 = squeeze(axes = squeeze_1_axes_0, x = var_102_cast_fp16_1)[name = string("squeeze_1_cast_fp16")];
|
| 85 |
-
tensor<int32, [1]> squeeze_2_axes_0 = const()[name = string("squeeze_2_axes_0"), val = tensor<int32, [1]>([2])];
|
| 86 |
-
tensor<fp16, [1, 512, 8, 64]> squeeze_2_cast_fp16 = squeeze(axes = squeeze_2_axes_0, x = var_102_cast_fp16_2)[name = string("squeeze_2_cast_fp16")];
|
| 87 |
-
tensor<int32, [4]> value_3_perm_0 = const()[name = string("value_3_perm_0"), val = tensor<int32, [4]>([0, 2, -3, -1])];
|
| 88 |
-
bool var_110_transpose_x_0 = const()[name = string("op_110_transpose_x_0"), val = bool(false)];
|
| 89 |
-
bool var_110_transpose_y_0 = const()[name = string("op_110_transpose_y_0"), val = bool(false)];
|
| 90 |
-
tensor<int32, [4]> transpose_8_perm_0 = const()[name = string("transpose_8_perm_0"), val = tensor<int32, [4]>([0, 2, -3, -1])];
|
| 91 |
-
tensor<int32, [4]> transpose_9_perm_0 = const()[name = string("transpose_9_perm_0"), val = tensor<int32, [4]>([0, 2, -1, -3])];
|
| 92 |
-
tensor<fp16, [1, 8, 64, 512]> transpose_9 = transpose(perm = transpose_9_perm_0, x = squeeze_1_cast_fp16)[name = string("transpose_18")];
|
| 93 |
-
tensor<fp16, [1, 8, 512, 64]> transpose_8 = transpose(perm = transpose_8_perm_0, x = squeeze_0_cast_fp16)[name = string("transpose_19")];
|
| 94 |
-
tensor<fp16, [1, 8, 512, 512]> var_110_cast_fp16 = matmul(transpose_x = var_110_transpose_x_0, transpose_y = var_110_transpose_y_0, x = transpose_8, y = transpose_9)[name = string("op_110_cast_fp16")];
|
| 95 |
-
fp16 var_111_to_fp16 = const()[name = string("op_111_to_fp16"), val = fp16(0x1p-3)];
|
| 96 |
-
tensor<fp16, [1, 8, 512, 512]> scores_1_cast_fp16 = mul(x = var_110_cast_fp16, y = var_111_to_fp16)[name = string("scores_1_cast_fp16")];
|
| 97 |
-
tensor<int32, [1]> var_114_axes_0 = const()[name = string("op_114_axes_0"), val = tensor<int32, [1]>([1])];
|
| 98 |
-
tensor<bool, [1, 1, 512]> var_114 = expand_dims(axes = var_114_axes_0, x = span_context_mask_1)[name = string("op_114")];
|
| 99 |
-
tensor<int32, [1]> var_115_axes_0 = const()[name = string("op_115_axes_0"), val = tensor<int32, [1]>([2])];
|
| 100 |
-
tensor<bool, [1, 1, 1, 512]> var_115 = expand_dims(axes = var_115_axes_0, x = var_114)[name = string("op_115")];
|
| 101 |
-
tensor<bool, [1, 1, 1, 512]> var_117 = logical_not(x = var_115)[name = string("op_117")];
|
| 102 |
-
fp16 var_23_to_fp16 = const()[name = string("op_23_to_fp16"), val = fp16(-inf)];
|
| 103 |
-
tensor<fp16, [1, 8, 512, 512]> scores_3_cast_fp16 = select(a = var_23_to_fp16, b = scores_1_cast_fp16, cond = var_117)[name = string("scores_3_cast_fp16")];
|
| 104 |
-
tensor<fp16, [1, 8, 512, 512]> var_119_cast_fp16 = softmax(axis = var_30, x = scores_3_cast_fp16)[name = string("op_119_cast_fp16")];
|
| 105 |
-
string var_120_to_fp16_dtype_0 = const()[name = string("op_120_to_fp16_dtype_0"), val = string("fp16")];
|
| 106 |
-
tensor<fp16, [1, 1, 1, 512]> var_115_to_fp16 = cast(dtype = var_120_to_fp16_dtype_0, x = var_115)[name = string("cast_6")];
|
| 107 |
-
tensor<fp16, [1, 8, 512, 512]> weights_1_cast_fp16 = mul(x = var_119_cast_fp16, y = var_115_to_fp16)[name = string("weights_1_cast_fp16")];
|
| 108 |
-
tensor<int32, [1]> var_123_axes_0 = const()[name = string("op_123_axes_0"), val = tensor<int32, [1]>([-1])];
|
| 109 |
-
bool var_123_keep_dims_0 = const()[name = string("op_123_keep_dims_0"), val = bool(true)];
|
| 110 |
-
tensor<fp16, [1, 8, 512, 1]> var_123_cast_fp16 = reduce_sum(axes = var_123_axes_0, keep_dims = var_123_keep_dims_0, x = weights_1_cast_fp16)[name = string("op_123_cast_fp16")];
|
| 111 |
-
fp16 var_21_to_fp16 = const()[name = string("op_21_to_fp16"), val = fp16(0x1.1p-20)];
|
| 112 |
-
tensor<fp16, [1, 8, 512, 1]> var_124_cast_fp16 = maximum(x = var_123_cast_fp16, y = var_21_to_fp16)[name = string("op_124_cast_fp16")];
|
| 113 |
-
tensor<fp16, [1, 8, 512, 512]> weights_3_cast_fp16 = real_div(x = weights_1_cast_fp16, y = var_124_cast_fp16)[name = string("weights_3_cast_fp16")];
|
| 114 |
-
bool var_126_transpose_x_0 = const()[name = string("op_126_transpose_x_0"), val = bool(false)];
|
| 115 |
-
bool var_126_transpose_y_0 = const()[name = string("op_126_transpose_y_0"), val = bool(false)];
|
| 116 |
-
tensor<fp16, [1, 8, 512, 64]> value_3_cast_fp16 = transpose(perm = value_3_perm_0, x = squeeze_2_cast_fp16)[name = string("transpose_17")];
|
| 117 |
-
tensor<fp16, [1, 8, 512, 64]> var_126_cast_fp16 = matmul(transpose_x = var_126_transpose_x_0, transpose_y = var_126_transpose_y_0, x = weights_3_cast_fp16, y = value_3_cast_fp16)[name = string("op_126_cast_fp16")];
|
| 118 |
-
tensor<int32, [4]> var_127_perm_0 = const()[name = string("op_127_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])];
|
| 119 |
-
tensor<int32, [3]> var_128 = const()[name = string("op_128"), val = tensor<int32, [3]>([1, 512, 512])];
|
| 120 |
-
tensor<fp16, [1, 512, 8, 64]> var_127_cast_fp16 = transpose(perm = var_127_perm_0, x = var_126_cast_fp16)[name = string("transpose_16")];
|
| 121 |
-
tensor<fp16, [1, 512, 512]> input_9_cast_fp16 = reshape(shape = var_128, x = var_127_cast_fp16)[name = string("input_9_cast_fp16")];
|
| 122 |
-
tensor<fp16, [512, 512]> module_flow_span_ordered_encoder_blocks_0_attention_proj_weight_to_fp16_quantized = constexpr_blockwise_shift_scale(data = tensor<int8, [512, 512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(1237888))), scale = tensor<fp16, [512, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(1500096))))[name = string("module_flow_span_ordered_encoder_blocks_0_attention_proj_weight_to_fp16_quantized")];
|
| 123 |
-
tensor<fp16, [512]> module_flow_span_ordered_encoder_blocks_0_attention_proj_bias_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_0_attention_proj_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(1501184)))];
|
| 124 |
-
tensor<fp16, [1, 512, 512]> linear_1_cast_fp16 = linear(bias = module_flow_span_ordered_encoder_blocks_0_attention_proj_bias_to_fp16, weight = module_flow_span_ordered_encoder_blocks_0_attention_proj_weight_to_fp16_quantized, x = input_9_cast_fp16)[name = string("linear_1_cast_fp16")];
|
| 125 |
-
tensor<fp16, [1, 512, 512]> input_13_cast_fp16 = add(x = hidden_3_cast_fp16, y = linear_1_cast_fp16)[name = string("input_13_cast_fp16")];
|
| 126 |
-
tensor<int32, [1]> input_15_axes_0 = const()[name = string("input_15_axes_0"), val = tensor<int32, [1]>([-1])];
|
| 127 |
-
tensor<fp16, [512]> module_flow_span_ordered_encoder_blocks_0_norm_feedforward_weight_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_0_norm_feedforward_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(1502272)))];
|
| 128 |
-
tensor<fp16, [512]> module_flow_span_ordered_encoder_blocks_0_norm_feedforward_bias_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_0_norm_feedforward_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(1503360)))];
|
| 129 |
-
tensor<fp16, [1, 512, 512]> input_15_cast_fp16 = layer_norm(axes = input_15_axes_0, beta = module_flow_span_ordered_encoder_blocks_0_norm_feedforward_bias_to_fp16, epsilon = var_28_to_fp16, gamma = module_flow_span_ordered_encoder_blocks_0_norm_feedforward_weight_to_fp16, x = input_13_cast_fp16)[name = string("input_15_cast_fp16")];
|
| 130 |
-
tensor<fp16, [2048, 512]> module_flow_span_ordered_encoder_blocks_0_feedforward_0_weight_to_fp16_quantized = constexpr_blockwise_shift_scale(data = tensor<int8, [2048, 512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(1504448))), scale = tensor<fp16, [2048, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(2553088))))[name = string("module_flow_span_ordered_encoder_blocks_0_feedforward_0_weight_to_fp16_quantized")];
|
| 131 |
-
tensor<fp16, [2048]> module_flow_span_ordered_encoder_blocks_0_feedforward_0_bias_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_0_feedforward_0_bias_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(2557248)))];
|
| 132 |
-
tensor<fp16, [1, 512, 2048]> linear_2_cast_fp16 = linear(bias = module_flow_span_ordered_encoder_blocks_0_feedforward_0_bias_to_fp16, weight = module_flow_span_ordered_encoder_blocks_0_feedforward_0_weight_to_fp16_quantized, x = input_15_cast_fp16)[name = string("linear_2_cast_fp16")];
|
| 133 |
-
string input_19_mode_0 = const()[name = string("input_19_mode_0"), val = string("TANH_APPROXIMATION")];
|
| 134 |
-
tensor<fp16, [1, 512, 2048]> input_19_cast_fp16 = gelu(mode = input_19_mode_0, x = linear_2_cast_fp16)[name = string("input_19_cast_fp16")];
|
| 135 |
-
tensor<fp16, [512, 2048]> module_flow_span_ordered_encoder_blocks_0_feedforward_2_weight_to_fp16_quantized = constexpr_blockwise_shift_scale(data = tensor<int8, [512, 2048]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(2561408))), scale = tensor<fp16, [512, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(3610048))))[name = string("module_flow_span_ordered_encoder_blocks_0_feedforward_2_weight_to_fp16_quantized")];
|
| 136 |
-
tensor<fp16, [512]> module_flow_span_ordered_encoder_blocks_0_feedforward_2_bias_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_0_feedforward_2_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(3611136)))];
|
| 137 |
-
tensor<fp16, [1, 512, 512]> linear_3_cast_fp16 = linear(bias = module_flow_span_ordered_encoder_blocks_0_feedforward_2_bias_to_fp16, weight = module_flow_span_ordered_encoder_blocks_0_feedforward_2_weight_to_fp16_quantized, x = input_19_cast_fp16)[name = string("linear_3_cast_fp16")];
|
| 138 |
-
tensor<fp16, [1, 512, 512]> hidden_5_cast_fp16 = add(x = input_13_cast_fp16, y = linear_3_cast_fp16)[name = string("hidden_5_cast_fp16")];
|
| 139 |
-
tensor<fp16, [1, 512, 512]> hidden_7_cast_fp16 = select(a = var_18_to_fp16, b = hidden_5_cast_fp16, cond = var_83)[name = string("hidden_7_cast_fp16")];
|
| 140 |
-
tensor<int32, [1]> input_23_axes_0 = const()[name = string("input_23_axes_0"), val = tensor<int32, [1]>([-1])];
|
| 141 |
-
tensor<fp16, [512]> module_flow_span_ordered_encoder_blocks_1_norm_attention_weight_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_1_norm_attention_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(3612224)))];
|
| 142 |
-
tensor<fp16, [512]> module_flow_span_ordered_encoder_blocks_1_norm_attention_bias_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_1_norm_attention_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(3613312)))];
|
| 143 |
-
tensor<fp16, [1, 512, 512]> input_23_cast_fp16 = layer_norm(axes = input_23_axes_0, beta = module_flow_span_ordered_encoder_blocks_1_norm_attention_bias_to_fp16, epsilon = var_28_to_fp16, gamma = module_flow_span_ordered_encoder_blocks_1_norm_attention_weight_to_fp16, x = hidden_7_cast_fp16)[name = string("input_23_cast_fp16")];
|
| 144 |
-
tensor<fp16, [1536, 512]> module_flow_span_ordered_encoder_blocks_1_qkv_weight_to_fp16_quantized = constexpr_blockwise_shift_scale(data = tensor<int8, [1536, 512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(3614400))), scale = tensor<fp16, [1536, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(4400896))))[name = string("module_flow_span_ordered_encoder_blocks_1_qkv_weight_to_fp16_quantized")];
|
| 145 |
-
tensor<fp16, [1536]> module_flow_span_ordered_encoder_blocks_1_qkv_bias_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_1_qkv_bias_to_fp16"), val = tensor<fp16, [1536]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(4404032)))];
|
| 146 |
-
tensor<fp16, [1, 512, 1536]> linear_4_cast_fp16 = linear(bias = module_flow_span_ordered_encoder_blocks_1_qkv_bias_to_fp16, weight = module_flow_span_ordered_encoder_blocks_1_qkv_weight_to_fp16_quantized, x = input_23_cast_fp16)[name = string("linear_4_cast_fp16")];
|
| 147 |
-
tensor<int32, [5]> var_168 = const()[name = string("op_168"), val = tensor<int32, [5]>([1, 512, 3, 8, 64])];
|
| 148 |
-
tensor<fp16, [1, 512, 3, 8, 64]> qkv_3_cast_fp16 = reshape(shape = var_168, x = linear_4_cast_fp16)[name = string("qkv_3_cast_fp16")];
|
| 149 |
-
tensor<int32, [3]> var_170_split_sizes_0 = const()[name = string("op_170_split_sizes_0"), val = tensor<int32, [3]>([1, 1, 1])];
|
| 150 |
-
int32 var_170_axis_0 = const()[name = string("op_170_axis_0"), val = int32(2)];
|
| 151 |
-
tensor<fp16, [1, 512, 1, 8, 64]> var_170_cast_fp16_0, tensor<fp16, [1, 512, 1, 8, 64]> var_170_cast_fp16_1, tensor<fp16, [1, 512, 1, 8, 64]> var_170_cast_fp16_2 = split(axis = var_170_axis_0, split_sizes = var_170_split_sizes_0, x = qkv_3_cast_fp16)[name = string("op_170_cast_fp16")];
|
| 152 |
-
tensor<int32, [1]> squeeze_3_axes_0 = const()[name = string("squeeze_3_axes_0"), val = tensor<int32, [1]>([2])];
|
| 153 |
-
tensor<fp16, [1, 512, 8, 64]> squeeze_3_cast_fp16 = squeeze(axes = squeeze_3_axes_0, x = var_170_cast_fp16_0)[name = string("squeeze_3_cast_fp16")];
|
| 154 |
-
tensor<int32, [1]> squeeze_4_axes_0 = const()[name = string("squeeze_4_axes_0"), val = tensor<int32, [1]>([2])];
|
| 155 |
-
tensor<fp16, [1, 512, 8, 64]> squeeze_4_cast_fp16 = squeeze(axes = squeeze_4_axes_0, x = var_170_cast_fp16_1)[name = string("squeeze_4_cast_fp16")];
|
| 156 |
-
tensor<int32, [1]> squeeze_5_axes_0 = const()[name = string("squeeze_5_axes_0"), val = tensor<int32, [1]>([2])];
|
| 157 |
-
tensor<fp16, [1, 512, 8, 64]> squeeze_5_cast_fp16 = squeeze(axes = squeeze_5_axes_0, x = var_170_cast_fp16_2)[name = string("squeeze_5_cast_fp16")];
|
| 158 |
-
tensor<int32, [4]> value_perm_0 = const()[name = string("value_perm_0"), val = tensor<int32, [4]>([0, 2, -3, -1])];
|
| 159 |
-
bool var_178_transpose_x_0 = const()[name = string("op_178_transpose_x_0"), val = bool(false)];
|
| 160 |
-
bool var_178_transpose_y_0 = const()[name = string("op_178_transpose_y_0"), val = bool(false)];
|
| 161 |
-
tensor<int32, [4]> transpose_10_perm_0 = const()[name = string("transpose_10_perm_0"), val = tensor<int32, [4]>([0, 2, -3, -1])];
|
| 162 |
-
tensor<int32, [4]> transpose_11_perm_0 = const()[name = string("transpose_11_perm_0"), val = tensor<int32, [4]>([0, 2, -1, -3])];
|
| 163 |
-
tensor<fp16, [1, 8, 64, 512]> transpose_11 = transpose(perm = transpose_11_perm_0, x = squeeze_4_cast_fp16)[name = string("transpose_14")];
|
| 164 |
-
tensor<fp16, [1, 8, 512, 64]> transpose_10 = transpose(perm = transpose_10_perm_0, x = squeeze_3_cast_fp16)[name = string("transpose_15")];
|
| 165 |
-
tensor<fp16, [1, 8, 512, 512]> var_178_cast_fp16 = matmul(transpose_x = var_178_transpose_x_0, transpose_y = var_178_transpose_y_0, x = transpose_10, y = transpose_11)[name = string("op_178_cast_fp16")];
|
| 166 |
-
fp16 var_179_to_fp16 = const()[name = string("op_179_to_fp16"), val = fp16(0x1p-3)];
|
| 167 |
-
tensor<fp16, [1, 8, 512, 512]> scores_5_cast_fp16 = mul(x = var_178_cast_fp16, y = var_179_to_fp16)[name = string("scores_5_cast_fp16")];
|
| 168 |
-
tensor<fp16, [1, 8, 512, 512]> scores_cast_fp16 = select(a = var_23_to_fp16, b = scores_5_cast_fp16, cond = var_117)[name = string("scores_cast_fp16")];
|
| 169 |
-
tensor<fp16, [1, 8, 512, 512]> var_187_cast_fp16 = softmax(axis = var_30, x = scores_cast_fp16)[name = string("op_187_cast_fp16")];
|
| 170 |
-
tensor<fp16, [1, 8, 512, 512]> weights_5_cast_fp16 = mul(x = var_187_cast_fp16, y = var_115_to_fp16)[name = string("weights_5_cast_fp16")];
|
| 171 |
-
tensor<int32, [1]> var_191_axes_0 = const()[name = string("op_191_axes_0"), val = tensor<int32, [1]>([-1])];
|
| 172 |
-
bool var_191_keep_dims_0 = const()[name = string("op_191_keep_dims_0"), val = bool(true)];
|
| 173 |
-
tensor<fp16, [1, 8, 512, 1]> var_191_cast_fp16 = reduce_sum(axes = var_191_axes_0, keep_dims = var_191_keep_dims_0, x = weights_5_cast_fp16)[name = string("op_191_cast_fp16")];
|
| 174 |
-
tensor<fp16, [1, 8, 512, 1]> var_192_cast_fp16 = maximum(x = var_191_cast_fp16, y = var_21_to_fp16)[name = string("op_192_cast_fp16")];
|
| 175 |
-
tensor<fp16, [1, 8, 512, 512]> weights_cast_fp16 = real_div(x = weights_5_cast_fp16, y = var_192_cast_fp16)[name = string("weights_cast_fp16")];
|
| 176 |
-
bool var_194_transpose_x_0 = const()[name = string("op_194_transpose_x_0"), val = bool(false)];
|
| 177 |
-
bool var_194_transpose_y_0 = const()[name = string("op_194_transpose_y_0"), val = bool(false)];
|
| 178 |
-
tensor<fp16, [1, 8, 512, 64]> value_cast_fp16 = transpose(perm = value_perm_0, x = squeeze_5_cast_fp16)[name = string("transpose_13")];
|
| 179 |
-
tensor<fp16, [1, 8, 512, 64]> var_194_cast_fp16 = matmul(transpose_x = var_194_transpose_x_0, transpose_y = var_194_transpose_y_0, x = weights_cast_fp16, y = value_cast_fp16)[name = string("op_194_cast_fp16")];
|
| 180 |
-
tensor<int32, [4]> var_195_perm_0 = const()[name = string("op_195_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])];
|
| 181 |
-
tensor<int32, [3]> var_196 = const()[name = string("op_196"), val = tensor<int32, [3]>([1, 512, 512])];
|
| 182 |
-
tensor<fp16, [1, 512, 8, 64]> var_195_cast_fp16 = transpose(perm = var_195_perm_0, x = var_194_cast_fp16)[name = string("transpose_12")];
|
| 183 |
-
tensor<fp16, [1, 512, 512]> input_25_cast_fp16 = reshape(shape = var_196, x = var_195_cast_fp16)[name = string("input_25_cast_fp16")];
|
| 184 |
-
tensor<fp16, [512, 512]> module_flow_span_ordered_encoder_blocks_1_attention_proj_weight_to_fp16_quantized = constexpr_blockwise_shift_scale(data = tensor<int8, [512, 512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(4407168))), scale = tensor<fp16, [512, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(4669376))))[name = string("module_flow_span_ordered_encoder_blocks_1_attention_proj_weight_to_fp16_quantized")];
|
| 185 |
-
tensor<fp16, [512]> module_flow_span_ordered_encoder_blocks_1_attention_proj_bias_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_1_attention_proj_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(4670464)))];
|
| 186 |
-
tensor<fp16, [1, 512, 512]> linear_5_cast_fp16 = linear(bias = module_flow_span_ordered_encoder_blocks_1_attention_proj_bias_to_fp16, weight = module_flow_span_ordered_encoder_blocks_1_attention_proj_weight_to_fp16_quantized, x = input_25_cast_fp16)[name = string("linear_5_cast_fp16")];
|
| 187 |
-
tensor<fp16, [1, 512, 512]> input_29_cast_fp16 = add(x = hidden_7_cast_fp16, y = linear_5_cast_fp16)[name = string("input_29_cast_fp16")];
|
| 188 |
-
tensor<int32, [1]> input_31_axes_0 = const()[name = string("input_31_axes_0"), val = tensor<int32, [1]>([-1])];
|
| 189 |
-
tensor<fp16, [512]> module_flow_span_ordered_encoder_blocks_1_norm_feedforward_weight_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_1_norm_feedforward_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(4671552)))];
|
| 190 |
-
tensor<fp16, [512]> module_flow_span_ordered_encoder_blocks_1_norm_feedforward_bias_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_1_norm_feedforward_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(4672640)))];
|
| 191 |
-
tensor<fp16, [1, 512, 512]> input_31_cast_fp16 = layer_norm(axes = input_31_axes_0, beta = module_flow_span_ordered_encoder_blocks_1_norm_feedforward_bias_to_fp16, epsilon = var_28_to_fp16, gamma = module_flow_span_ordered_encoder_blocks_1_norm_feedforward_weight_to_fp16, x = input_29_cast_fp16)[name = string("input_31_cast_fp16")];
|
| 192 |
-
tensor<fp16, [2048, 512]> module_flow_span_ordered_encoder_blocks_1_feedforward_0_weight_to_fp16_quantized = constexpr_blockwise_shift_scale(data = tensor<int8, [2048, 512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(4673728))), scale = tensor<fp16, [2048, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(5722368))))[name = string("module_flow_span_ordered_encoder_blocks_1_feedforward_0_weight_to_fp16_quantized")];
|
| 193 |
-
tensor<fp16, [2048]> module_flow_span_ordered_encoder_blocks_1_feedforward_0_bias_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_1_feedforward_0_bias_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(5726528)))];
|
| 194 |
-
tensor<fp16, [1, 512, 2048]> linear_6_cast_fp16 = linear(bias = module_flow_span_ordered_encoder_blocks_1_feedforward_0_bias_to_fp16, weight = module_flow_span_ordered_encoder_blocks_1_feedforward_0_weight_to_fp16_quantized, x = input_31_cast_fp16)[name = string("linear_6_cast_fp16")];
|
| 195 |
-
string input_35_mode_0 = const()[name = string("input_35_mode_0"), val = string("TANH_APPROXIMATION")];
|
| 196 |
-
tensor<fp16, [1, 512, 2048]> input_35_cast_fp16 = gelu(mode = input_35_mode_0, x = linear_6_cast_fp16)[name = string("input_35_cast_fp16")];
|
| 197 |
-
tensor<fp16, [512, 2048]> module_flow_span_ordered_encoder_blocks_1_feedforward_2_weight_to_fp16_quantized = constexpr_blockwise_shift_scale(data = tensor<int8, [512, 2048]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(5730688))), scale = tensor<fp16, [512, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(6779328))))[name = string("module_flow_span_ordered_encoder_blocks_1_feedforward_2_weight_to_fp16_quantized")];
|
| 198 |
-
tensor<fp16, [512]> module_flow_span_ordered_encoder_blocks_1_feedforward_2_bias_to_fp16 = const()[name = string("module_flow_span_ordered_encoder_blocks_1_feedforward_2_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(6780416)))];
|
| 199 |
-
tensor<fp16, [1, 512, 512]> linear_7_cast_fp16 = linear(bias = module_flow_span_ordered_encoder_blocks_1_feedforward_2_bias_to_fp16, weight = module_flow_span_ordered_encoder_blocks_1_feedforward_2_weight_to_fp16_quantized, x = input_35_cast_fp16)[name = string("linear_7_cast_fp16")];
|
| 200 |
-
tensor<fp16, [1, 512, 512]> hidden_9_cast_fp16 = add(x = input_29_cast_fp16, y = linear_7_cast_fp16)[name = string("hidden_9_cast_fp16")];
|
| 201 |
-
tensor<fp16, [1, 512, 512]> hidden_cast_fp16 = select(a = var_18_to_fp16, b = hidden_9_cast_fp16, cond = var_83)[name = string("hidden_cast_fp16")];
|
| 202 |
-
tensor<bool, [1, 512]> var_224 = equal(x = input_3, y = var_40)[name = string("op_224")];
|
| 203 |
-
tensor<bool, [1, 512]> var_225 = logical_and(x = span_context_mask_1, y = var_224)[name = string("op_225")];
|
| 204 |
-
tensor<int32, [1]> var_228_axes_0 = const()[name = string("op_228_axes_0"), val = tensor<int32, [1]>([1])];
|
| 205 |
-
bool var_228_keep_dims_0 = const()[name = string("op_228_keep_dims_0"), val = bool(true)];
|
| 206 |
-
string weight_15_to_fp16_dtype_0 = const()[name = string("weight_15_to_fp16_dtype_0"), val = string("fp16")];
|
| 207 |
-
tensor<fp16, [1, 512]> var_225_to_fp16 = cast(dtype = weight_15_to_fp16_dtype_0, x = var_225)[name = string("cast_5")];
|
| 208 |
-
tensor<fp16, [1, 1]> var_228_cast_fp16 = reduce_sum(axes = var_228_axes_0, keep_dims = var_228_keep_dims_0, x = var_225_to_fp16)[name = string("op_228_cast_fp16")];
|
| 209 |
-
fp16 var_17_to_fp16 = const()[name = string("op_17_to_fp16"), val = fp16(0x1p+0)];
|
| 210 |
-
tensor<fp16, [1, 1]> var_229_cast_fp16 = maximum(x = var_228_cast_fp16, y = var_17_to_fp16)[name = string("op_229_cast_fp16")];
|
| 211 |
-
tensor<fp16, [1, 512]> weight_17_cast_fp16 = real_div(x = var_225_to_fp16, y = var_229_cast_fp16)[name = string("weight_17_cast_fp16")];
|
| 212 |
-
tensor<int32, [1]> var_231_axes_0 = const()[name = string("op_231_axes_0"), val = tensor<int32, [1]>([-1])];
|
| 213 |
-
tensor<fp16, [1, 512, 1]> var_231_cast_fp16 = expand_dims(axes = var_231_axes_0, x = weight_17_cast_fp16)[name = string("op_231_cast_fp16")];
|
| 214 |
-
tensor<fp16, [1, 512, 512]> var_232_cast_fp16 = mul(x = hidden_cast_fp16, y = var_231_cast_fp16)[name = string("op_232_cast_fp16")];
|
| 215 |
-
tensor<int32, [1]> var_234_axes_0 = const()[name = string("op_234_axes_0"), val = tensor<int32, [1]>([1])];
|
| 216 |
-
bool var_234_keep_dims_0 = const()[name = string("op_234_keep_dims_0"), val = bool(false)];
|
| 217 |
-
tensor<fp16, [1, 512]> var_234_cast_fp16 = reduce_sum(axes = var_234_axes_0, keep_dims = var_234_keep_dims_0, x = var_232_cast_fp16)[name = string("op_234_cast_fp16")];
|
| 218 |
-
tensor<bool, [1, 512]> var_235 = equal(x = input_3, y = var_38)[name = string("op_235")];
|
| 219 |
-
tensor<bool, [1, 512]> var_236 = logical_and(x = span_context_mask_1, y = var_235)[name = string("op_236")];
|
| 220 |
-
tensor<int32, [1]> var_239_axes_0 = const()[name = string("op_239_axes_0"), val = tensor<int32, [1]>([1])];
|
| 221 |
-
bool var_239_keep_dims_0 = const()[name = string("op_239_keep_dims_0"), val = bool(true)];
|
| 222 |
-
string weight_19_to_fp16_dtype_0 = const()[name = string("weight_19_to_fp16_dtype_0"), val = string("fp16")];
|
| 223 |
-
tensor<fp16, [1, 512]> var_236_to_fp16 = cast(dtype = weight_19_to_fp16_dtype_0, x = var_236)[name = string("cast_4")];
|
| 224 |
-
tensor<fp16, [1, 1]> var_239_cast_fp16 = reduce_sum(axes = var_239_axes_0, keep_dims = var_239_keep_dims_0, x = var_236_to_fp16)[name = string("op_239_cast_fp16")];
|
| 225 |
-
tensor<fp16, [1, 1]> var_240_cast_fp16 = maximum(x = var_239_cast_fp16, y = var_17_to_fp16)[name = string("op_240_cast_fp16")];
|
| 226 |
-
tensor<fp16, [1, 512]> weight_21_cast_fp16 = real_div(x = var_236_to_fp16, y = var_240_cast_fp16)[name = string("weight_21_cast_fp16")];
|
| 227 |
-
tensor<int32, [1]> var_242_axes_0 = const()[name = string("op_242_axes_0"), val = tensor<int32, [1]>([-1])];
|
| 228 |
-
tensor<fp16, [1, 512, 1]> var_242_cast_fp16 = expand_dims(axes = var_242_axes_0, x = weight_21_cast_fp16)[name = string("op_242_cast_fp16")];
|
| 229 |
-
tensor<fp16, [1, 512, 512]> var_243_cast_fp16 = mul(x = hidden_cast_fp16, y = var_242_cast_fp16)[name = string("op_243_cast_fp16")];
|
| 230 |
-
tensor<int32, [1]> var_245_axes_0 = const()[name = string("op_245_axes_0"), val = tensor<int32, [1]>([1])];
|
| 231 |
-
bool var_245_keep_dims_0 = const()[name = string("op_245_keep_dims_0"), val = bool(false)];
|
| 232 |
-
tensor<fp16, [1, 512]> var_245_cast_fp16 = reduce_sum(axes = var_245_axes_0, keep_dims = var_245_keep_dims_0, x = var_243_cast_fp16)[name = string("op_245_cast_fp16")];
|
| 233 |
-
tensor<bool, [1, 512]> var_246 = equal(x = input_3, y = var_35)[name = string("op_246")];
|
| 234 |
-
tensor<bool, [1, 512]> var_247 = logical_and(x = span_context_mask_1, y = var_246)[name = string("op_247")];
|
| 235 |
-
tensor<int32, [1]> var_250_axes_0 = const()[name = string("op_250_axes_0"), val = tensor<int32, [1]>([1])];
|
| 236 |
-
bool var_250_keep_dims_0 = const()[name = string("op_250_keep_dims_0"), val = bool(true)];
|
| 237 |
-
string weight_23_to_fp16_dtype_0 = const()[name = string("weight_23_to_fp16_dtype_0"), val = string("fp16")];
|
| 238 |
-
tensor<fp16, [1, 512]> var_247_to_fp16 = cast(dtype = weight_23_to_fp16_dtype_0, x = var_247)[name = string("cast_3")];
|
| 239 |
-
tensor<fp16, [1, 1]> var_250_cast_fp16 = reduce_sum(axes = var_250_axes_0, keep_dims = var_250_keep_dims_0, x = var_247_to_fp16)[name = string("op_250_cast_fp16")];
|
| 240 |
-
tensor<fp16, [1, 1]> var_251_cast_fp16 = maximum(x = var_250_cast_fp16, y = var_17_to_fp16)[name = string("op_251_cast_fp16")];
|
| 241 |
-
tensor<fp16, [1, 512]> weight_25_cast_fp16 = real_div(x = var_247_to_fp16, y = var_251_cast_fp16)[name = string("weight_25_cast_fp16")];
|
| 242 |
-
tensor<int32, [1]> var_253_axes_0 = const()[name = string("op_253_axes_0"), val = tensor<int32, [1]>([-1])];
|
| 243 |
-
tensor<fp16, [1, 512, 1]> var_253_cast_fp16 = expand_dims(axes = var_253_axes_0, x = weight_25_cast_fp16)[name = string("op_253_cast_fp16")];
|
| 244 |
-
tensor<fp16, [1, 512, 512]> var_254_cast_fp16 = mul(x = hidden_cast_fp16, y = var_253_cast_fp16)[name = string("op_254_cast_fp16")];
|
| 245 |
-
tensor<int32, [1]> var_256_axes_0 = const()[name = string("op_256_axes_0"), val = tensor<int32, [1]>([1])];
|
| 246 |
-
bool var_256_keep_dims_0 = const()[name = string("op_256_keep_dims_0"), val = bool(false)];
|
| 247 |
-
tensor<fp16, [1, 512]> var_256_cast_fp16 = reduce_sum(axes = var_256_axes_0, keep_dims = var_256_keep_dims_0, x = var_254_cast_fp16)[name = string("op_256_cast_fp16")];
|
| 248 |
-
bool input_39_interleave_0 = const()[name = string("input_39_interleave_0"), val = bool(false)];
|
| 249 |
-
tensor<fp16, [1, 1536]> input_39_cast_fp16 = concat(axis = var_30, interleave = input_39_interleave_0, values = (var_234_cast_fp16, var_245_cast_fp16, var_256_cast_fp16))[name = string("input_39_cast_fp16")];
|
| 250 |
-
tensor<fp16, [512, 1536]> module_flow_span_segment_pool_proj_weight_to_fp16_quantized = constexpr_blockwise_shift_scale(data = tensor<int8, [512, 1536]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(6781504))), scale = tensor<fp16, [512, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(7568000))))[name = string("module_flow_span_segment_pool_proj_weight_to_fp16_quantized")];
|
| 251 |
-
tensor<fp16, [512]> module_flow_span_segment_pool_proj_bias_to_fp16 = const()[name = string("module_flow_span_segment_pool_proj_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(7569088)))];
|
| 252 |
-
tensor<fp16, [1, 512]> linear_8_cast_fp16 = linear(bias = module_flow_span_segment_pool_proj_bias_to_fp16, weight = module_flow_span_segment_pool_proj_weight_to_fp16_quantized, x = input_39_cast_fp16)[name = string("linear_8_cast_fp16")];
|
| 253 |
-
tensor<int32, [1]> pooled_axes_0 = const()[name = string("pooled_axes_0"), val = tensor<int32, [1]>([-1])];
|
| 254 |
-
tensor<fp16, [512]> module_flow_span_context_norm_weight_to_fp16 = const()[name = string("module_flow_span_context_norm_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(7570176)))];
|
| 255 |
-
tensor<fp16, [512]> module_flow_span_context_norm_bias_to_fp16 = const()[name = string("module_flow_span_context_norm_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(7571264)))];
|
| 256 |
-
tensor<fp16, [1, 512]> pooled_cast_fp16 = layer_norm(axes = pooled_axes_0, beta = module_flow_span_context_norm_bias_to_fp16, epsilon = var_28_to_fp16, gamma = module_flow_span_context_norm_weight_to_fp16, x = linear_8_cast_fp16)[name = string("pooled_cast_fp16")];
|
| 257 |
-
tensor<int32, [1]> var_38_list = const()[name = string("op_38_list"), val = tensor<int32, [1]>([1])];
|
| 258 |
-
bool reduce_max_0_keep_dims_0 = const()[name = string("reduce_max_0_keep_dims_0"), val = bool(true)];
|
| 259 |
-
tensor<int32, [1, 1]> reduce_max_0 = reduce_max(axes = var_38_list, keep_dims = reduce_max_0_keep_dims_0, x = var_64)[name = string("reduce_max_0")];
|
| 260 |
-
string var_266_dtype_0 = const()[name = string("op_266_dtype_0"), val = string("bool")];
|
| 261 |
-
tensor<bool, [1, 1]> var_266 = cast(dtype = var_266_dtype_0, x = reduce_max_0)[name = string("cast_2")];
|
| 262 |
-
tensor<bool, [1, 1]> var_267 = logical_not(x = var_266)[name = string("op_267")];
|
| 263 |
-
tensor<fp16, [1, 512]> var_268_cast_fp16 = select(a = var_18_to_fp16, b = pooled_cast_fp16, cond = var_267)[name = string("op_268_cast_fp16")];
|
| 264 |
-
string var_268_cast_fp16_to_fp32_dtype_0 = const()[name = string("op_268_cast_fp16_to_fp32_dtype_0"), val = string("fp32")];
|
| 265 |
-
tensor<fp32, [1, 512]> span_context_hidden = cast(dtype = var_268_cast_fp16_to_fp32_dtype_0, x = var_268_cast_fp16)[name = string("cast_1")];
|
| 266 |
-
} -> (span_context_hidden);
|
| 267 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coreml/coreml/vector_context_encoder.mlmodelc/weights/weight.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7120be9d216af8b1021ad92a4d3d0d136881d55e48debfb348197f12da2a21d6
|
| 3 |
-
size 7572352
|
|
|
|
|
|
|
|
|
|
|
|