Inicio Explorar Axuda
Iniciar sesión
Server
/
fish-speech
41
0
Fork 0
Ficheiros Incidencias 0 Pull Requests 0 Wiki

Sen descrición

Árbore: e09afa2601
Ramas Etiquetas
fish-speech
ZIP TAR.GZ
Lengyue e09afa2601 remove mqtts %!s(int64=2) %!d(string=hai) anos
data_server 57755e1e74 Add rust data server %!s(int64=2) %!d(string=hai) anos
fish_speech e09afa2601 remove mqtts %!s(int64=2) %!d(string=hai) anos
tools 9649873532 Update generate examples %!s(int64=2) %!d(string=hai) anos
.dockerignore 57755e1e74 Add rust data server %!s(int64=2) %!d(string=hai) anos
.gitignore 57755e1e74 Add rust data server %!s(int64=2) %!d(string=hai) anos
.pre-commit-config.yaml f1ea577c4c [pre-commit.ci] pre-commit autoupdate %!s(int64=2) %!d(string=hai) anos
LICENSE 62710e34a4 Add llama inference tool chain %!s(int64=2) %!d(string=hai) anos
README.md 57755e1e74 Add rust data server %!s(int64=2) %!d(string=hai) anos
dockerfile f8cfbb4ac0 Greatly improved data loading speed %!s(int64=2) %!d(string=hai) anos
pyproject.toml 57755e1e74 Add rust data server %!s(int64=2) %!d(string=hai) anos
pyrightconfig.json f7f2c03282 Support pytorch lightning %!s(int64=2) %!d(string=hai) anos

README.md

Fish Speech

This repo is still under construction. Please check back later.

Setup

# Basic environment setup
conda create -n fish-speech python=3.10
conda activate fish-speech
conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia

# Install flash-attn (for linux)
pip3 install ninja && MAX_JOBS=4 pip3 install flash-attn --no-build-isolation

# Install fish-speech
pip3 install -e .

Rust Data Server

Since loading and shuffle the dataset is very slow and memory consuming, we use a rust server to load and shuffle the dataset. The server is based on GRPC and can be installed by

cd data_server
cargo build --release

Credits