Lite-Whisper
Collection
https://github.com/efeslab/LiteASR • 7 items • Updated • 2
How to use efficient-speech/lite-whisper-large-v3-fast with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="efficient-speech/lite-whisper-large-v3-fast", trust_remote_code=True) # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("efficient-speech/lite-whisper-large-v3-fast", trust_remote_code=True, dtype="auto")Lite-Whisper is a compressed version of OpenAI Whisper with LiteASR. See our GitHub repository and paper for details. The paper is also available on Hugging Face: Link to Hugging Face Paper Page
Following is the average word error rate (WER) evaluated on the ESB datasets:\
| Model | Average WER (↓) | Encoder Size | Decoder Size |
|---|---|---|---|
| whisper-large-v3 | 10.1 | 635M | 907M |
| lite-whisper-large-v3-acc | 10.1 | 429M | 907M |
| lite-whisper-large-v3 | 10.2 | 377M | 907M |
| lite-whisper-large-v3-fast | 11.3 | 308M | 907M |
| whisper-large-v3-turbo | 10.1 | 635M | 172M |
| lite-whisper-large-v3-turbo-acc | 10.2 | 421M | 172M |
| lite-whisper-large-v3-turbo | 12.6 | 374M | 172M |
| lite-whisper-large-v3-turbo-fast | 20.1 | 313M | 172M |
| whisper-medium | 14.8 | 306M | 457M |