Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
English
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use openai/whisper-small.en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-small.en with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-small.en")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-small.en") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-small.en", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download flax_model.msgpack from openai/whisper-small.en: direct link, hf CLI and curl.
- Browser
- Download file 967 MB
-
https://huggingface.co/openai/whisper-small.en/resolve/a8ed7698a1d870e588f48649ff8aff4a4f945953/flax_model.msgpack
- Command line
-
hf download hf://openai/whisper-small.en@a8ed7698a1d870e588f48649ff8aff4a4f945953/flax_model.msgpack
-
curl -L -o flax_model.msgpack https://huggingface.co/openai/whisper-small.en/resolve/a8ed7698a1d870e588f48649ff8aff4a4f945953/flax_model.msgpack
967 MB
- Xet hash:
- 0bf8c6a4864a2e5de658f65badb020ec5f4100d0d09bd1c3a3d27dbb38583bf6
- Size of remote file:
- 967 MB
- SHA256:
- f1c8d569697781d484a4516315806f6f97d4fe5ff2d62789dc351909f16ebd92
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.