Exploring "linear attention" for text-to-speech.
It predicts audio codec "à la" MusicGen : delayed residual vector quantizers so that we do not need multiple models.
Featuring RWKV, Mamba, Gated Linear Attention.
Compared to other LM TTS model :
Model | #Params | Dataset | Checkpoint | Steps | Note |
---|---|---|---|---|---|
GLA | 60M, 130M | Librilight-medium | Download | 300k | GPU inference only |
Mamba | 60M | Librilight-medium | Download | 300k | GPU inference only |
RWKV v6 | 60M | LibriTTS | Download | 150k | GPU inference only |
Following the linear complexity LM you choose, follow respective instructions first:
Download configuration and weights above, then check Inference.ipynb
.
@software{lemerle2024linaspeech,
title = {LinaSpeech: Exploring "linear attention" for text-to-speech.},
author = {Lemerle, Théodor},
url = {https://github.com/theodorblackbird/lina-speech},
month = april,
year = {2024}
}
This work is performed in the Analysis/Synthesis team of the STMS Laboratory at IRCAM, and is part of the following project: ANR Exovoices