Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
asr
hf-asr-leaderboard
Instructions to use NbAiLab/nb-whisper-large-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLab/nb-whisper-large-beta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NbAiLab/nb-whisper-large-beta")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("NbAiLab/nb-whisper-large-beta") model = AutoModelForSpeechSeq2Seq.from_pretrained("NbAiLab/nb-whisper-large-beta") - Notebooks
- Google Colab
- Kaggle
Alignment heads
#2
by mmichelli - opened
Are the alignment heads the same as https://huggingface.co/openai/whisper-large/blob/main/generation_config.json?
When using this model, I get a lot of zero-duration words that have an offset start of a few seconds.
There are no changes to genaration_config.json.
This is a very early model. New models will be coming in just a few days.
mmichelli changed discussion status to closed