This commit is contained in:
zhousha
2025-12-04 20:16:27 +08:00
parent def1973c5f
commit b90e011dca
2 changed files with 12 additions and 1 deletions

View File

@@ -9,4 +9,5 @@
支持模型列表:
- AI-ModelScope/F5-TTS
- microsoft/speecht5_tts
- microsoft/speecht5_tts
- ByteDance/MegaTTS3

10
enginex/MegaTTS3.md Normal file
View File

@@ -0,0 +1,10 @@
# 运行方式
```python
docker pull git.modelhub.org.cn:9443/enginex-hygon/pytorch:2.4.1-ubuntu22.04-dtk25.04-py3.10-fixpy
# 为以上拉取的docker的镜像ID替换本镜像为e77c15729879
docker run -it --shm-size=64G -v $PWD/MegaTTS3:/home/MegaTTS3 -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name tts bash
cd /home/MegaTTS3
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple
sh ffmpeg_apt.sh # ffmpeg=4.4.4,若无法直接运行完成安装,可拷贝出来单独依次运行脚本中的命令,以避免网络不畅的问题。
```