Thanks to visit codestin.com
Credit goes to github.com

Skip to content
@sarulab-speech

sarulab-speech

UTokyo-SaruLab Speech Research Group at The University of Tokyo, Japan.

Popular repositories Loading

  1. UTMOS22 UTMOS22 Public

    UT-Sarulab MOS prediction system using SSL models

    Python 294 15

  2. UTMOSv2 UTMOSv2 Public

    UTokyo-SaruLab MOS Prediction System

    Python 285 28

  3. jtubespeech jtubespeech Public

    Python 229 48

  4. jsut-label jsut-label Public

    context labels and pronunciation data for JSUT corpus

    77 12

  5. Sidon Sidon Public

    Training code and dataset cleasing with Sidon

    Python 69 8

  6. audio-foundation-model-dataset audio-foundation-model-dataset Public

    58

Repositories

Showing 10 of 31 repositories

Top languages

Python HTML

Most used topics

Loading…