|
|
2 лет назад | |
|---|---|---|
| data_server | 2 лет назад | |
| fish_speech | 2 лет назад | |
| tools | 2 лет назад | |
| .dockerignore | 2 лет назад | |
| .gitignore | 2 лет назад | |
| .pre-commit-config.yaml | 2 лет назад | |
| LICENSE | 2 лет назад | |
| README.md | 2 лет назад | |
| dockerfile | 2 лет назад | |
| pyproject.toml | 2 лет назад | |
| pyrightconfig.json | 2 лет назад |
This repo is still under construction. Please check back later.
# 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 .
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