distill-whisper-th-medium

Distilled Medium Whisper ASR Model for Thai

Model Description

This is a distilled Automatic Speech Recognition (ASR) model, based on the Whisper architecture. It has been specifically tailored for Thai language speech recognition. The model features 4 decoder layers (vs 24 in teacher model) and has been distilled from a larger teacher model, focusing on enhancing performance and efficiency.

Distillation Details

• Teacher Model: Medium Whisper ASR model
• Datasets Used for Distillation:
  • Common Voice v13
  • Gowajee
  • Thai Elderly Speech Corpus
  • Custom Scraped Data
  • Thai-Central Dialect from SLSCU Thai Dialect Corpus

Model Performance

• DeepCut Tokenized WER on Common Voice 13 Test Set:
  • Distilled Model: 7.58%
  • Teacher Model: 7.42%

Additional datasets for distillation or more decoder layers might improve the WER. More to come soon!

Intended Use

This model is intended for use in applications requiring Thai language speech recognition.

Limitations

• The model is specifically trained for the Thai language and may not perform well with other languages.
• Performance might vary across different Thai dialects and accents.
• As with any ASR system, background noise and speech clarity can impact recognition accuracy.

Acknowledgments

This model was developed using resources and datasets provided by the speech and language technology community. Special thanks to the teams behind Common Voice, Gowajee, SLSCU, and the Thai Elderly Speech Corpus for their valuable datasets.

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.2
• Datasets 2.16.1
• Tokenizers 0.15.0

Contributors

• Biomedical and Data Lab, Mahidol University
• WordSense by Looloo technology
• Mahamor by Looloo technology

<p style="display: flex; justify-content: center; align-items: center; gap: 10px;"> <img width="110px" src="assets/bdl.png" /> <img width="50px" src="assets/wordsense-looloo.png" /> <img width="45px" src="assets/mahamor-looloo.png" /> <img width="150px" src="assets/looloo-logo.png" /> </p>

Citation

Cite using Bibtex:

@inproceedings{aung-etal-2024-thonburian,
    title = "Thonburian Whisper: Robust Fine-tuned and Distilled Whisper for {T}hai",
    author = "Aung, Zaw Htet  and
      Thavornmongkol, Thanachot  and
      Boribalburephan, Atirut  and
      Tangsriworakan, Vittavas  and
      Pipatsrisawat, Knot  and
      Achakulvisut, Titipat",
    editor = "Abbas, Mourad  and
      Freihat, Abed Alhakim",
    booktitle = "Proceedings of the 7th International Conference on Natural Language and Speech Processing (ICNLSP 2024)",
    month = oct,
    year = "2024",
    address = "Trento",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.icnlsp-1.17",
    pages = "149--156",
}

---