|
--- |
|
base_model: openai/whisper-large-v3-turbo |
|
library_name: transformers |
|
license: apache-2.0 |
|
pipeline_tag: automatic-speech-recognition |
|
tags: |
|
- audio |
|
- automatic-speech-recognition |
|
- whisper |
|
- hf-asr-leaderboard |
|
--- |
|
|
|
# Model Card for Lite-Whisper large-v3-turbo-fast |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
Lite-Whisper is a compressed version of OpenAI Whisper with LiteASR. See our [GitHub repository](https://github.com/efeslab/LiteASR) and [paper](https://arxiv.org/abs/2502.20583) for details. |
|
|
|
## Benchmark Results |
|
|
|
Following is the average word error rate (WER) evaluated on the [ESB datasets](https://huggingface.co/datasets/hf-audio/esb-datasets-test-only-sorted): |
|
|
|
| Model | Average WER (↓) | Encoder Size | Decoder Size | |
|
|-------|----------------|--------------|--------------| |
|
| [whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) | 10.1 | 635M | 907M | |
|
| [lite-whisper-large-v3-acc](https://huggingface.co/efficient-speech/lite-whisper-large-v3-acc) | 10.1 | 429M | 907M | |
|
| [lite-whisper-large-v3](https://huggingface.co/efficient-speech/lite-whisper-large-v3) | 10.2 | 377M | 907M | |
|
| [lite-whisper-large-v3-fast](https://huggingface.co/efficient-speech/lite-whisper-large-v3-fast) | 11.3 | 308M | 907M | |
|
| | | | | |
|
| [whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) | 10.1 | 635M | 172M | |
|
| [lite-whisper-large-v3-turbo-acc](https://huggingface.co/efficient-speech/lite-whisper-large-v3-turbo-acc) | 10.2 | 421M | 172M | |
|
| [lite-whisper-large-v3-turbo](https://huggingface.co/efficient-speech/lite-whisper-large-v3-turbo) | 12.6 | 374M | 172M | |
|
| [lite-whisper-large-v3-turbo-fast](https://huggingface.co/efficient-speech/lite-whisper-large-v3-turbo-fast) | 20.1 | 313M | 172M | |
|
| | | | | |
|
| [whisper-medium](https://huggingface.co/openai/whisper-medium) | 14.8 | 306M | 457M | |
