Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "50cfbb726b26700d143ce5bb55c0b5e86de7a1e6"
Commit be69ba06 authored by weishb's avatar weishb
Browse files

update README.md

parent bcdb7109
Hide whitespace changes
Inline Side-by-side
Showing with 16 additions and 7 deletions
README.md
View file @ be69ba06
...@@ -84,15 +84,12 @@ python test_model_12hz_base.py ...@@ -84,15 +84,12 @@ python test_model_12hz_base.py
``` ```
### vllm ### vllm
#### 单机推理 #### 单机推理
VoiceDesign
启动服务
```bash ```bash
#以VoiceDesign为例子，CustomVoice和Voice Clone需要使用不同的模型 ## serve启动
VLLM_USE_V1=0 python -m vllm.entrypoints.openai.api_server --model Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-VoiceDesign --served-model-name qwen3-tts --host 0.0.0.0 --port 8000 --trust-remote-code --dtype bfloat16 --disable-async-output-proc VLLM_USE_V1=0 python -m vllm.entrypoints.openai.api_server --model Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-VoiceDesign --served-model-name qwen3-tts --host 0.0.0.0 --port 8000 --trust-remote-code --dtype bfloat16 --disable-async-output-proc
```
调用服务： ## client访问
```
VoiceDesign
curl -sS http://127.0.0.1:8000/v1/audio/speech \ curl -sS http://127.0.0.1:8000/v1/audio/speech \
-H "Content-Type: application/json" \ -H "Content-Type: application/json" \
-o output.wav \ -o output.wav \
...@@ -111,8 +108,14 @@ curl -sS http://127.0.0.1:8000/v1/audio/speech \ ...@@ -111,8 +108,14 @@ curl -sS http://127.0.0.1:8000/v1/audio/speech \
}, },
"response_format":"wav" "response_format":"wav"
}' }'
```
CustomVoice CustomVoice
```bash
## serve启动
VLLM_USE_V1=0 python -m vllm.entrypoints.openai.api_server --model Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-CustomVoice --served-model-name qwen3-tts --host 0.0.0.0 --port 8000 --trust-remote-code --dtype bfloat16 --disable-async-output-proc
## client访问
curl -sS http://127.0.0.1:8000/v1/audio/speech \ curl -sS http://127.0.0.1:8000/v1/audio/speech \
-H "Content-Type: application/json" \ -H "Content-Type: application/json" \
-o output_customvoice.wav \ -o output_customvoice.wav \
...@@ -132,8 +135,14 @@ curl -sS http://127.0.0.1:8000/v1/audio/speech \ ...@@ -132,8 +135,14 @@ curl -sS http://127.0.0.1:8000/v1/audio/speech \
}, },
"response_format":"wav" "response_format":"wav"
}' }'
```
Voice Clone Voice Clone
```bash
## serve启动
VLLM_USE_V1=0 python -m vllm.entrypoints.openai.api_server --model Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-Base --served-model-name qwen3-tts --host 0.0.0.0 --port 8000 --trust-remote-code --dtype bfloat16 --disable-async-output-proc
## client访问
curl -sS http://127.0.0.1:8000/v1/audio/speech \ curl -sS http://127.0.0.1:8000/v1/audio/speech \
-H "Content-Type: application/json" \ -H "Content-Type: application/json" \
-o output_clone_icl.wav \ -o output_clone_icl.wav \
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment