hugpadhugpad

5CD-AI / VieGem-ASR

Audio09Updated Oct 21, 2026
Hugging Face

Downloads

0

Likes

9

Last updated

Oct 21, 2026

License

cc-by-nc-sa-4.0

Fast Vietnamese and Vietnamese–English speech recognition: a 359M-parameter streaming CTC model on Google's EmbeddingGemma 2 audio encoder. Inspired by Quan Nguyen's QUAN-Transcribe-1.0.

Tasks & library

  • automatic speech recognition
  • pytorch

Tags

  • pytorch
  • ctc
  • vietnamese
  • code-switching
  • streaming
  • embeddinggemma

Technical specifications

ParametersNot available
Librarypytorch
Languagesvi, en
Base modelgoogle/embeddinggemma-2
Licensecc-by-nc-sa-4.0