https://github.com/alphasnow/modelscope-serving
Build AI model service based on ModelScope / 一键搭建基于魔搭的AI模型服务
https://github.com/alphasnow/modelscope-serving
deep-learning machine-learning modelscope python
Last synced: about 1 year ago
JSON representation
Build AI model service based on ModelScope / 一键搭建基于魔搭的AI模型服务
- Host: GitHub
- URL: https://github.com/alphasnow/modelscope-serving
- Owner: alphasnow
- License: apache-2.0
- Created: 2023-06-01T09:11:48.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2023-06-01T10:17:26.000Z (almost 3 years ago)
- Last Synced: 2025-03-28T18:51:50.156Z (about 1 year ago)
- Topics: deep-learning, machine-learning, modelscope, python
- Language: Python
- Homepage:
- Size: 44.9 KB
- Stars: 6
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ModelScope Serving
Use the following command to easily start ModelScope Serving
```bash
git clone https://github.com/alphasnow/modelscope-serving.git
cd modelscope-serving
docker-compose up -f docker-compose.yml -d
```
## Example
```bash
# request
curl 'http://127.0.0.1:8800/api/predict/image-cartoon' \
-H 'Content-Type:application/json' \
-X POST \
-d '{"image":"TdbnJ6cHh9mV09O5qu+z6Sv3j06vPvJvcePHqdrLa...","algo_type":"anime"}'
# response
{"image":"Yc+a9/V3bHXmnZSu26oXaBa66pbLpbd4f7+8dHxj370o..."}
```
## Features
- Automatic Speech Recognition `/asr/paraformer`
- Text To Speech `/tts/emotion`
- Photo to Cartoon `/image-cartoon`
- Image segmentation `/image-segment/person` `/image-segment/product`
- Optical Character Recognition `/image-ocr/general`
- Word Segment `/word-segmentation`
- Body Detection `/image-body/2d-keypoint`
## Dependencies
- docker
- docker-compose
- modelscope
- python
- fastapi
- opencv
- uvicorn
## License
This project is licensed under the [Apache License (Version 2.0)](LICENSE).