Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use openai/whisper-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-tiny")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-tiny") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-tiny") - Notebooks
- Google Colab
- Kaggle
Commit History
Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (#39) 167c219 verified
add special tokens for fast (#35) be0ba7c
add timestamp tokens (#33) e8ff9f9
Update generation config with word-level alignment heads (#29) 1135fb8
Adding `safetensors` variant of this model (#14) aaf41dd
Update README.md ed50ab0
Update README.md 299b03b
Update generation_config.json to suppress task tokens (#11) 79aace4
Update config.json to suppress task tokens (#10) 3a57fe6
Update the pad token (#9) a8d7651
Add Flax weights 3025605
sanchit-gandhi commited on