Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results
Instructions to use openai/whisper-large-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-large-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large-v2")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-large-v2") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large-v2") - Notebooks
- Google Colab
- Kaggle
Commit History
Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (#95) a3710f8 verified
add timestamp tokens (#63) 696465c
add timestamp tokens (#64) 0007ffc
Adding `safetensors` variant of this model (#57) 94ee83d
Update generation config with word-level alignment heads (#55) b9bcbc3
Update README.md 1f66457
Update config.json to suppress task tokens (#32) 8be909d
Update generation_config.json to suppress task tokens (#33) 48274ca
Update the pad token (#30) 1187dc6
Add Flax weights 5ff6499
sanchit-gandhi commited on