lafi2333 f5ad1b01f9 | 1 year ago | |
---|---|---|
.github/workflows | 1 year ago | |
configs | 1 year ago | |
dictionaries | 1 year ago | |
fish_diffusion | 1 year ago | |
tests | 1 year ago | |
tools | 1 year ago | |
.gitignore | 1 year ago | |
LICENSE | 1 year ago | |
README.en.md | 1 year ago | |
README.md | 1 year ago | |
inference.py | 1 year ago | |
poetry.lock | 1 year ago | |
poetry.toml | 1 year ago | |
pyproject.toml | 1 year ago | |
requirements.txt | 1 year ago | |
train.py | 1 year ago |
一个简单易懂的 TTS / SVS / SVC 框架.
基于 DiffSinger 实现歌声音色转换。相较于原 diffsvc 仓库,本仓库优缺点如下
以下命令需要在 python 3.10 的 conda 环境下执行
# 安装 PyTorch 相关核心依赖, 如果已安装则跳过
# 参考 https://pytorch.org/get-started/locally/
conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
# 安装 Poetry 依赖管理工具, 如果已安装则跳过
# 参考 https://python-poetry.org/docs/#installation
curl -sSL https://install.python-poetry.org | python3 -
# 安装依赖 (推荐)
poetry install
# 如果 Poetry 不可用, 或者速度较慢, 可以使用 pip 安装依赖
pip install -r requirements.txt
pip install -e .
Fish Diffusion 需要 OPENVPI 441khz NSF-HiFiGAN 声码器来生成音频.
python tools/download_nsf_hifigan.py
下载 441khz 声码器 中的 nsf_hifigan_20221211.zip
解压 nsf_hifigan
文件夹到 checkpoints
目录下 (如果没有则创建)
仅需要以以下文件结构将数据集放入 dataset 目录即可
dataset
├───train
│ ├───xxx1-xxx1.wav
│ ├───...
│ ├───Lxx-0xx8.wav
│ └───speaker0 (支持子目录)
│ └───xxx1-xxx1.wav
└───valid
├───xx2-0xxx2.wav
├───...
└───xxx7-xxx007.wav
# 1. 提取全部数据的特征, 如 pitch, text features, mel features 等
python tools/preprocessing/extract_features.py --config configs/svc_hubert_soft.py --path dataset --clean
# 2. 生成训练集统计信息
python tools/preprocessing/generate_stats.py --input-dir dataset/train --output-file dataset/stats.json
该项目仍在积极开发, 请记得备份你的 config 文件
该项目仍在积极开发, 请记得备份你的 config 文件
该项目仍在积极开发, 请记得备份你的 config 文件
# 单机单卡 / 单机多卡训练
python train.py --config configs/svc_hubert_soft.py
# 继续训练
python train.py --config configs/svc_hubert_soft.py --resume [checkpoint]
python inference.py --config configs/svc_hubert_soft.py \
--checkpoint [checkpoint] \
--input [input audio] \
--output [output audio]
python tools/diff_svc_converter.py --config configs/svc_hubert_soft_diff_svc.py \
--input-path [DiffSVC ckpt] \
--output-path [Fish Diffusion ckpt]
如果你有任何问题, 请提交 issue 或 pull request.
你应该在提交 pull request 之前运行 tools/lint.sh
用于训练fish启动环境脚本
Python Text
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》