duplex-0 / README.md
multimodalart's picture
multimodalart HF Staff
Upload folder using huggingface_hub
d20eb3e verified
|
Raw History Blame Contribute Delete
815 Bytes
metadata
title: duplex-0
emoji: 🎙️
colorFrom: blue
colorTo: gray
sdk: gradio
sdk_version: 6.32.0
app_file: app.py
short_description: Small full-duplex speech-to-speech model (Mimi tokens)
python_version: '3.12'
startup_duration_timeout: 30m
models:
  - Trelis/duplex-0
  - kyutai/mimi
  - kyutai/moshiko-pytorch-bf16

Demo of Trelis/duplex-0, a 201M-parameter two-track speech-to-speech research model.

The model code in duplex/ is copied from the model repo's scripts/duplex/model (Apache-2.0, see duplex/NOTICE). Example prompts are the first 10 seconds of the "real" sample clips in the model repo's report/samples/ (Apache-2.0 repository). Audio is encoded/decoded with Kyutai's Mimi codec, and text uses Moshi's tokenizer.