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
Granite-Speech_vllm
Commits
ee3c746d
Commit
ee3c746d
authored
Jul 11, 2025
by
zhangwq5
Browse files
modified:README.md
parent
e702e403
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
19 additions
and
6 deletions
+19
-6
README.md
README.md
+19
-6
No files found.
README.md
View file @
ee3c746d
...
...
@@ -26,8 +26,14 @@ docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:vllm0.8.5-ubuntu22.04
docker run
-it
--shm-size
200g
--network
=
host
--name
{
docker_name
}
--privileged
--device
=
/dev/kfd
--device
=
/dev/dri
--device
=
/dev/mkfd
--group-add
video
--cap-add
=
SYS_PTRACE
--security-opt
seccomp
=
unconfined
-u
root
-v
/path/your_code_data/:/path/your_code_data/
-v
/opt/hyhal/:/opt/hyhal/:ro
{
imageID
}
bash
# 需要将transformers至少升级到4.53.1
pip
install
transformers
==
4.53.1
pip
install
librosa
==
0.11.0
# 需要安装torchaudio包
wget https://download.sourcefind.cn:65024/directlink/4/torchaudio/DAS1.6/torchaudio-2.4.1+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl
pip
install
torchaudio-2.4.1+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl
cd
/your_code_path/granite-speech_pytorch
pip
install
transformers>
=
4.53.1
```
### Dockerfile(方法二)
此处提供dockerfile的使用方法
...
...
@@ -36,8 +42,14 @@ cd docker
docker build
--no-cache
-t
granite-speech:latest
.
docker run
-it
--shm-size
200g
--network
=
host
--name
{
docker_name
}
--privileged
--device
=
/dev/kfd
--device
=
/dev/dri
--device
=
/dev/mkfd
--group-add
video
--cap-add
=
SYS_PTRACE
--security-opt
seccomp
=
unconfined
-u
root
-v
/path/your_code_data/:/path/your_code_data/
-v
/opt/hyhal/:/opt/hyhal/:ro
{
imageID
}
bash
# 需要将transformers至少升级到4.53.1
pip
install
transformers
==
4.53.1
pip
install
librosa
==
0.11.0
# 需要安装torchaudio包
wget https://download.sourcefind.cn:65024/directlink/4/torchaudio/DAS1.6/torchaudio-2.4.1+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl
pip
install
torchaudio-2.4.1+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl
cd
/your_code_path/granite-speech_pytorch
pip
install
transformers>
=
4.53.1
```
### Anaconda(方法三)
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。
...
...
@@ -45,14 +57,15 @@ pip install transformers>=4.53.1
DTK: 25.04
python: 3.10
vllm: 0.8.5
torch: 2.4.1+das.opt
2
.dtk2504
deepspeed: 0.1
4.
2
+das.opt
2
.dtk2504
torch: 2.4.1+das.opt
1
.dtk2504
1
torchaudio: 2.
4.
1
+das.opt
1
.dtk2504
1
```
`Tips:以上dtk驱动、
python、paddle
等DCU相关工具版本需要严格一一对应`
`Tips:以上dtk驱动、
torch
等DCU相关工具版本需要严格一一对应`
其它非深度学习库安装方式如下:
```
bash
pip
install
transformers>
=
4.53.1
pip
install
transformers
==
4.53.1
pip
install
librosa
==
0.11.0
```
## 数据集
暂无
...
...
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