Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
Qwen3-TTS_pytorch
Commits
ba769e5f
Commit
ba769e5f
authored
Feb 10, 2026
by
weishb
Browse files
Update the README file
parent
e3cdb305
Pipeline
#3392
failed with stages
in 0 seconds
Changes
3
Pipelines
1
Show whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
11 additions
and
13 deletions
+11
-13
README.md
README.md
+9
-11
iocn.png
iocn.png
+0
-0
model.properties
model.properties
+2
-2
No files found.
README.md
View file @
ba769e5f
...
...
@@ -16,8 +16,6 @@ Qwen3-TTS 覆盖10种主要语言(中文、英文、日文、韩文、德文
## 环境依赖
-
列举基础环境需求,根据实际情况填写
| 软件 | 版本 |
| :------: | :------: |
| DTK | 25.04.2 |
...
...
@@ -27,8 +25,7 @@ Qwen3-TTS 覆盖10种主要语言(中文、英文、日文、韩文、德文
| torchaudio | 2.5.1+das.opt1.dtk25042.20251127.g10a9ffcd |
| transformer_engine | 2.5.0+das.opt1.dtk25042 |
推荐使用镜像:harbor.sourcefind.cn:5443/dcu/admin/base/vllm:0.9.2-ubuntu22.04-dtk26.04-0130-py3.10-20260202
-
挂载地址
`-v`
,
`{docker_name}`
和
`{docker_image_name}`
根据实际模型情况修改
推荐使用镜像:harbor.sourcefind.cn:5443/dcu/admin/base/vllm:0.9.2-ubuntu22.04-dtk25.04.2-1226-das1.7-py3.10-20251226
```
bash
docker run
-it
\
...
...
@@ -49,8 +46,7 @@ docker run -it \
```
更多镜像可前往
[
光源
](
https://sourcefind.cn/#/service-list
)
下载使用。
关于本项目DCU显卡所需的特殊深度学习库可从
[
光合
](
https://developer.sourcefind.cn/tool/
)
开发者社区下载安装
其它包参照requirements.txt安装:
关于本项目DCU显卡所需的特殊深度学习库可从
[
光合
](
https://developer.sourcefind.cn/tool/
)
开发者社区下载安装,其它包参照requirements.txt安装:
```
pip install -r requirements.txt
```
...
...
@@ -87,9 +83,11 @@ Voice Clone
python test_model_12hz_base.py
```
### vllm
#### 单机推理(以VoiceDesign为例子,CustomVoice和Voice Clone需要切换模型)
#### 单机推理
启动服务
```
bash
#以VoiceDesign为例子,CustomVoice和Voice Clone需要使用不同的模型
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:
...
...
@@ -166,14 +164,14 @@ curl -sS http://127.0.0.1:8000/v1/audio/speech \
示例输出音频:output_audio
\o
utput.wav
### 精度
`DCU与GPU精度一致,推理框架:vllm`
`DCU与GPU精度一致,推理框架:vllm
,transformers
`
## 预训练权重
| 模型名称 | 权重大小 | DCU型号 | 最低卡数需求 |下载地址|
|:-----:|:----------:|:----------:|:---------------------:|:----------:|
| Qwen3-TTS-12Hz-1.7B-VoiceDesign | 1.7B | K100AI | 1 | [Modelscope]
https://www.modelscope.cn/models/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign|
| Qwen3-TTS-12Hz-1.7B-CustomVoice | 1.7B | K100AI | 1 | [Modelscope]
https://www.modelscope.cn/models/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice|
| Qwen3-TTS-12Hz-1.7B-Base | 1.7B | K100AI | 1 | [Modelscope]
https://www.modelscope.cn/models/Qwen/Qwen3-TTS-12Hz-1.7B-Base|
| Qwen3-TTS-12Hz-1.7B-VoiceDesign | 1.7B | K100AI | 1 |
[
Modelscope
]
(
https://www.modelscope.cn/models/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign
)
|
| Qwen3-TTS-12Hz-1.7B-CustomVoice | 1.7B | K100AI | 1 |
[
Modelscope
]
(
https://www.modelscope.cn/models/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
)
|
| Qwen3-TTS-12Hz-1.7B-Base | 1.7B | K100AI | 1 |
[
Modelscope
]
(
https://www.modelscope.cn/models/Qwen/Qwen3-TTS-12Hz-1.7B-Base
)
|
## 源码仓库及问题反馈
-
https://developer.sourcefind.cn/codes/weishb/qwen3-tts_pytorch
...
...
doc/
iocn.png
→
iocn.png
View file @
ba769e5f
File suppressed by a .gitattributes entry or the file's encoding is unsupported.
model.properties
View file @
ba769e5f
# 模型唯一标识
modelCode
=
20
47
modelCode
=
20
68
# 模型名称
modelName
=
Qwen3-TTS_pytorch
# 模型描述
...
...
@@ -9,6 +9,6 @@ processType=推理
# 算法类别
appCategory
=
语音合成
# 框架类型
frameType
=
vllm
frameType
=
vllm
,transformers
# 加速卡类型
accelerateType
=
K100AI
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment