Automatic Speech Recognition
Transformers
PyTorch
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results
Instructions to use openai/whisper-large-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-large-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-large-v3") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large-v3") - Inference
- Notebooks
- Google Colab
- Kaggle
Add fp32, flax weights
#5
by sanchit-gandhi - opened
Adds Whisper large-v3 weights in fp32 safetensors, fp32 pytorch, fp16 pytorch, and fp32 flax. We only push fp32 flax weights since we don't upcast flax weights to fp32 when we call from_pretrained (unlike in pytorch), and so need them in fp32 precision.
sanchit-gandhi changed pull request status to open
patrickvonplaten changed pull request status to merged