Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use openai/whisper-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-small")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-small") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-small") - Notebooks
- Google Colab
- Kaggle
Why does snapshot_download for whisper-small download several GB when the PyTorch model is only ~500 MB?
#46
by Kerwin11 - opened
why whisper-mall contains all of the model and when i use it i have to download all of the version even if i just use one structure such a s PyTorch but i have to dowload other file.
Kerwin11 changed discussion title from why the repository contains all of the model? to Why does snapshot_download for whisper-small download several GB when the PyTorch model is only ~500 MB?