Automatic Speech Recognition
Transformers
PyTorch
JAX
TensorBoard
ONNX
Safetensors
whisper
audio
asr
hf-asr-leaderboard
Instructions to use NbAiLab/nb-whisper-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLab/nb-whisper-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NbAiLab/nb-whisper-large")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("NbAiLab/nb-whisper-large") model = AutoModelForSpeechSeq2Seq.from_pretrained("NbAiLab/nb-whisper-large") - Notebooks
- Google Colab
- Kaggle
Any plans on releasing a model based on whisper-large-v3?
#1
by MCFred - opened
Have you experimented with using whisper-large-v3 as the base model instead of whisper-large?
It should lead to better performance.
The released model is based on Whisper-large-v3. It is slightly better, but we see the biggest difference early in training. After a while, the differences between v2 and v3 is not really very big.
Cool.
In the model card you are linking to the base whisper-large (not even v2) under the 'Trained from model' point.
MCFred changed discussion status to closed
Fixed.