https://github.com/ai-forever/easy_sign
Easy_sign is an open source russian sign language recognition project that uses small CPU model for predictions and is designed for easy deployment via Streamlit.
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (6.9%) to scientific vocabulary
Keywords
Repository
Easy_sign is an open source russian sign language recognition project that uses small CPU model for predictions and is designed for easy deployment via Streamlit.
Basic Info
- Host: GitHub
- Owner: ai-forever
- License: cc-by-sa-4.0
- Language: Python
- Default Branch: main
- Homepage: https://habr.com/ru/companies/sberbank/articles/775688/
- Size: 33.1 MB
Statistics
- Stars: 29
- Watchers: 7
- Forks: 6
- Open Issues: 0
- Releases: 0
Topics
Metadata Files
README.md
Easy_sign
Easy_sign - опенсорс проект по распознаванию Русского жестового языка, спроектированный для развёртывания через Streamlit. В проекте используется "лёгкая" ML-модель, способная работать на CPU.
О проекте
Easy_sign использует ML-модель для распознавания отдельных жестов Русского жестового языка. Модель была обучена на ~180 000 примеров жестов. Приблизительно 20 000 из которых были взяты из датасета Slovo. Модель распознаёт 1598 жестов Русского жестового языка и может обеспечить распознавание 3-3.5 жестов в секунду на процессоре Intel(R) Core(TM) i5-6600 CPU @3.30GHz. Список распознаваемых жестов содержится в файле RSLclasslist.txt.
Больше информации о проекте - в статье на habr.
Порядок установки
conda create --name fleury-env python=3.10
conda activate fleury-env
pip install -r requirements.txt
Использование
streamlit run app.py
Ссылки
Команда ПИН-КОД выпустила на базе easy_sign тренажёр для изучения РЖЯ. Статья на хабр, репозиторий
S3D модели, обученные на датасете Slovo для различного количества кадров, подаваемых на вход.
| Кол-во кадров | Ссылка | Mean accuracy, % | |:---------------:|:--------:|:----------------:| | 32 | https://sc.link/l8VTi | 44.22 | | 48 | https://sc.link/GSojW | 52.28 | | 64 | https://sc.link/fhLfd | 55.86 |
Лицензия
This work is licensed under the Creative Commons Attribution-ShareAlike 4.0 International License.
Owner
- Name: AI Forever
- Login: ai-forever
- Kind: organization
- Location: Armenia
- Repositories: 60
- Profile: https://github.com/ai-forever
Creating ML for the future. AI projects you already know. We are non-profit organization with members from all over the world.
GitHub Events
Total
- Watch event: 8
Last Year
- Watch event: 8
Issues and Pull Requests
Last synced: about 1 year ago
All Time
- Total issues: 0
- Total pull requests: 1
- Average time to close issues: N/A
- Average time to close pull requests: 15 days
- Total issue authors: 0
- Total pull request authors: 1
- Average comments per issue: 0
- Average comments per pull request: 0.0
- Merged pull requests: 1
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
- mosvlad (1)
Top Labels
Issue Labels
Pull Request Labels
Dependencies
- einops ==0.6.1
- onnx ==1.14.0
- onnxruntime ==1.16.0
- onnxruntime-openvino ==1.16
- openvino ==2023.1
- streamlit ==1.28.2
- streamlit-webrtc ==0.47.1