Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use openai/whisper-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-medium with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-medium")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-medium") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-medium") - Notebooks
- Google Colab
- Kaggle
Commit History
Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (#32) 16688be verified
Add `return_timestamps` attribute to generation config (#29) 353117b
add special tokens for fast (#24) 18530d7
add timestamp tokens (#22) e8c4fa7
Adding `safetensors` variant of this model (#18) edffa06
Adding `safetensors` variant of this model (#21) 7c172ed
Update generation config with word-level alignment heads (#20) ad14d5b
Update README.md 8b6593e
Update README.md 692ba36
Update generation_config.json to suppress task tokens (#14) b5ad047
Update config.json to suppress task tokens (#13) ba4c731
Update the pad token (#12) f1457a2
Add Flax weights 0d49445
sanchit-gandhi commited on