README.md

metadata

title: S2st
emoji: 📉
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 4.1.1
app_file: app.py
pinned: false
license: apache-2.0

HF Space App for End-to-End Speech-to-Speech Translation

• Paper: Direct Speech-to-Speech Translation With Discrete Units
• Dataset: CVSS-C
• Toolkit: ESPnet
• Pretrained Speech-to-Unit translation model: https://huggingface.co/espnet/jiyang_tang_cvss-c_es-en_discrete_unit
• Pretrained WaveGAN vocoder: https://huggingface.co/espnet/cvss-c_en_wavegan_hubert_vocoder

Part of a CMU MIIS capstone project with @realzza and @sophia1488