willopcbeta/lite-whisper-small-fast-ONNX-v2

lite-whisper-small-fast (ONNX)

This is an ONNX version of willopcbeta/lite-whisper-small-fast. It was automatically converted and uploaded using this Hugging Face Space.

This model library is compatible with transformers.js v4, exported using optimum-cli, and is backward compatible with transformers.js v3.

Old version lite-whisper-small-fast-ONNX will be deprecated.

The optimal Q4 quantitative configuration: using decoder_model with q4f16 results in less ambiguous or nonsensical outputs.

quantization: {
    encoder_model: 'q4f16',
    decoder_model_merged: 'q4',
},

Usage with Transformers.js

See the pipeline documentation for automatic-speech-recognition: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.AutomaticSpeechRecognitionPipeline

---

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

This model revised the name of “efficient-speech/lite-whisper-small-fast” and merged any missing files to facilitate subsequent conversion to ONNX format or for other purposes.

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}, 
}