efficient-speech / lite-whisper-small

huggingface.co
Total runs: 18
24-hour runs: 0
7-day runs: -1
30-day runs: 11
Model's Last Updated: April 04 2025
automatic-speech-recognition

Introduction of lite-whisper-small

Model Details of lite-whisper-small

Lite-Whisper is a compressed version of OpenAI Whisper with LiteASR. See our GitHub repository and paper for details.

Benchmark Results

Following is the average word error rate (WER) evaluated on the ESB datasets :

Model Average WER (↓) Encoder Size Decoder Size
whisper-tiny 22.01 7.63M 29.55M
lite-whisper-tiny-acc 22.97 7.41M 29.55M
lite-whisper-tiny 23.95 7.00M 29.55M
lite-whisper-tiny-fast 27.09 6.48M 29.55M
whisper-base 17.67 19.82M 52.00M
lite-whisper-base-acc 19.07 18.64M 52.00M
lite-whisper-base 19.71 17.44M 52.00M
lite-whisper-base-fast 23.05 16.07M 52.00M
whisper-small 15.89 87.00M 153.58M
lite-whisper-small-acc 15.37 76.99M 153.58M
lite-whisper-small 14.96 70.16M 153.58M
lite-whisper-small-fast 14.92 63.11M 153.58M
whisper-medium 15.12 305.68M 456.64M
lite-whisper-medium-acc 13.46 269.93M 456.64M
lite-whisper-medium 14.50 239.99M 456.64M
lite-whisper-medium-fast 14.52 215.31M 456.64M
Citation

If you use LiteASR in your research, please cite the following paper:

@misc{kamahori2025liteasrefficientautomaticspeech,
      title={LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation}, 
      author={Keisuke Kamahori and Jungo Kasai and Noriyuki Kojima and Baris Kasikci},
      year={2025},
      eprint={2502.20583},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2502.20583}, 
}

Runs of efficient-speech lite-whisper-small on huggingface.co

18
Total runs
0
24-hour runs
0
3-day runs
-1
7-day runs
11
30-day runs

More Information About lite-whisper-small huggingface.co Model

More lite-whisper-small license Visit here:

https://choosealicense.com/licenses/apache-2.0

lite-whisper-small huggingface.co

lite-whisper-small huggingface.co is an AI model on huggingface.co that provides lite-whisper-small's model effect (), which can be used instantly with this efficient-speech lite-whisper-small model. huggingface.co supports a free trial of the lite-whisper-small model, and also provides paid use of the lite-whisper-small. Support call lite-whisper-small model through api, including Node.js, Python, http.

efficient-speech lite-whisper-small online free

lite-whisper-small huggingface.co is an online trial and call api platform, which integrates lite-whisper-small's modeling effects, including api services, and provides a free online trial of lite-whisper-small, you can try lite-whisper-small online for free by clicking the link below.

efficient-speech lite-whisper-small online free url in huggingface.co:

https://huggingface.co/efficient-speech/lite-whisper-small

lite-whisper-small install

lite-whisper-small is an open source model from GitHub that offers a free installation service, and any user can find lite-whisper-small on GitHub to install. At the same time, huggingface.co provides the effect of lite-whisper-small install, users can directly use lite-whisper-small installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

lite-whisper-small install url in huggingface.co:

https://huggingface.co/efficient-speech/lite-whisper-small

Url of lite-whisper-small

Provider of lite-whisper-small huggingface.co

efficient-speech
ORGANIZATIONS

Other API from efficient-speech