Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results
Instructions to use openai/whisper-large-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-large-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large-v2")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-large-v2") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large-v2") - Notebooks
- Google Colab
- Kaggle
Default large model
#22
by giuliastro - opened
Hello, I see whisper has 3 options for using the 2 large models:
- large
- large-v1
- large-v2
What is simply "large" referring to? Large-v1 or Large-v2?
Thank you in advance.
Hey @giuliastro ! To avoid breaking changes, we've kept "large-v1" == "large" and distinguished it from "large-v2" (see https://huggingface.co/openai/whisper-large/discussions/22)
thank you! :)
giuliastro changed discussion status to closed