57 lines
1.6 KiB
Markdown
57 lines
1.6 KiB
Markdown
|
# GPT_SoVITS
|
|||
|
|
|
|||
|
|
本项目基于 **GPT_SoVITS** 模型封装，提供简洁的 Docker 部署方式，支持 **SSML 输入**，输出 **PCM 原始音频**，可用于语音合成。
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Quickstart
|
|||
|
|
|
|||
|
|
### 1. 安装镜像
|
|||
|
|
```bash
|
|||
|
|
docker build -t tts:gsv . -f Dockerfile_gsv
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
### 2. 启动服务
|
|||
|
|
```bash
|
|||
|
|
docker run -it --rm \
|
|||
|
|
-v /models/GPT-SoVITS:/mnt/models \
|
|||
|
|
-e ASCEND_VISIBLE_DEVICES=1 \
|
|||
|
|
--device /dev/davinci2:/dev/davinci0 \
|
|||
|
|
--device /dev/davinci_manager \
|
|||
|
|
--device /dev/devmm_svm \
|
|||
|
|
--device /dev/hisi_hdc \
|
|||
|
|
-v /usr/local/dcmi:/usr/local/dcmi \
|
|||
|
|
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
|
|||
|
|
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
|
|||
|
|
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
|
|||
|
|
-v /etc/ascend_install.info:/etc/ascend_install.info \
|
|||
|
|
--privileged \
|
|||
|
|
-p 8080:80 \
|
|||
|
|
-e MODEL_DIR=/mnt/models \
|
|||
|
|
-e MODEL_NAME=s1v3.ckpt \
|
|||
|
|
tts:gsv
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
参数说明：
|
|||
|
|
- `MODEL_DIR`：模型所在目录（挂载到容器内 `/mnt/models`）
|
|||
|
|
- `MODEL_NAME`：加载的模型文件名（通常为 `.safetensors`）
|
|||
|
|
- `-p 8080:80`：将容器内服务端口映射到宿主机 `8080`
|
|||
|
|
|
|||
|
|
### 3. 测试服务
|
|||
|
|
```bash
|
|||
|
|
curl --request POST "http://localhost:8080/tts" \
|
|||
|
|
--header 'Content-Type: application/ssml+xml' \
|
|||
|
|
--header 'User-Agent: curl' \
|
|||
|
|
--data-raw '<speak version="1.0" xml:lang="zh">
|
|||
|
|
<voice xml:lang="zh" xml:gender="Female" name="zh">
|
|||
|
|
今天天气很好，不知道明天天气怎么样。
|
|||
|
|
</voice>
|
|||
|
|
</speak>' \
|
|||
|
|
--output sound.pcm
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Notes
|
|||
|
|
- Fix NPU 兼容问题： GPT_SoVITS/eres2net/kaldi.py
|