Instructions to use bezzam/VibeVoice-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bezzam/VibeVoice-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="bezzam/VibeVoice-7B")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForTextToWaveform processor = AutoProcessor.from_pretrained("bezzam/VibeVoice-7B") model = AutoModelForTextToWaveform.from_pretrained("bezzam/VibeVoice-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload VibeVoiceForConditionalGeneration
Browse files- generation_config.json +2 -2
generation_config.json
CHANGED
|
@@ -3,8 +3,8 @@
|
|
| 3 |
"do_sample": false,
|
| 4 |
"eos_token_id": 151643,
|
| 5 |
"guidance_scale": 1.3,
|
| 6 |
-
"max_length":
|
| 7 |
-
"max_new_tokens":
|
| 8 |
"noise_scheduler_class": "DPMSolverMultistepScheduler",
|
| 9 |
"noise_scheduler_config": {
|
| 10 |
"beta_schedule": "squaredcos_cap_v2",
|
|
|
|
| 3 |
"do_sample": false,
|
| 4 |
"eos_token_id": 151643,
|
| 5 |
"guidance_scale": 1.3,
|
| 6 |
+
"max_length": 40500,
|
| 7 |
+
"max_new_tokens": 40500,
|
| 8 |
"noise_scheduler_class": "DPMSolverMultistepScheduler",
|
| 9 |
"noise_scheduler_config": {
|
| 10 |
"beta_schedule": "squaredcos_cap_v2",
|