-
The University of Tokyo
- Tokyo
- wataru-nakata.github.io
- @wataru9871
Highlights
- Pro
Stars
Lightning-UQ-Box: Uncertainty Quantification for Neural Networks with PyTorch and Lightning
A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/abs/1905.11235.
This is the official train-dev-test release of the Interspeech2024 Discrete Speech Representation Challenge.
Stream What You Hear written in rust, inspired by SWYH.
SelfRemaster: SSL Speech Restoration
A repository of Japanese Phoneme-Level BERT
Wataru-Nakata / FastSpeech2-JSUT
Forked from ming024/FastSpeech2An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
UT-Sarulab MOS prediction system using SSL models
A familiar HTTP Service Framework for Python.
Stream Stereo Video from Webcam or Pi Camera to Google Cardboard