Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
English
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use openai/whisper-medium.en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-medium.en with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-medium.en")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-medium.en") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-medium.en") - Notebooks
- Google Colab
- Kaggle
Can I use flash attention 2 with this model?
#15
by anuragrawal - opened
Hi,
I am currently comparing time improvements for openai/whisper-medium.en vs distil-whisper/distil-medium.en
As suggested in the model card for distil-whisper/distil-medium.en, I am using flash attention 2 to get the best results. I don't completely understand the concept behind flash attention 2. Do I need to use it with openai/whisper-medium.en for a fair comparison? If yes,
- Is it feasible to use flash attention 2 with openai/whisper-medium.en?
- How?
Thanks!
I have NVIDIA GeForce RTX 3060 GPU.