{"id":23902543,"url":"https://github.com/adrianocleao/talking-hands","last_synced_at":"2026-04-16T10:02:38.759Z","repository":{"id":249172696,"uuid":"830296970","full_name":"AdrianoCLeao/talking-hands","owner":"AdrianoCLeao","description":"Talking Hands is a project that implements real-time recognition of Brazilian Sign Language (LIBRAS). ","archived":false,"fork":false,"pushed_at":"2025-09-03T03:01:58.000Z","size":24785,"stargazers_count":2,"open_issues_count":3,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-03T05:20:08.027Z","etag":null,"topics":["computer-vision","deep-learning","keras","libras","machine-learning","mediapipe","sign-language","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AdrianoCLeao.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-07-18T02:22:49.000Z","updated_at":"2025-02-22T18:05:55.000Z","dependencies_parsed_at":"2025-09-03T05:15:24.387Z","dependency_job_id":"2f6819d0-3843-41b8-881b-e361d011bf37","html_url":"https://github.com/AdrianoCLeao/talking-hands","commit_stats":null,"previous_names":["adrianocleao/librasdetector","adrianocleao/talking-hands"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/AdrianoCLeao/talking-hands","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdrianoCLeao%2Ftalking-hands","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdrianoCLeao%2Ftalking-hands/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdrianoCLeao%2Ftalking-hands/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdrianoCLeao%2Ftalking-hands/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AdrianoCLeao","download_url":"https://codeload.github.com/AdrianoCLeao/talking-hands/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdrianoCLeao%2Ftalking-hands/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31880884,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-16T09:23:21.276Z","status":"ssl_error","status_checked_at":"2026-04-16T09:23:15.028Z","response_time":69,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","deep-learning","keras","libras","machine-learning","mediapipe","sign-language","tensorflow"],"created_at":"2025-01-04T22:48:22.504Z","updated_at":"2026-04-16T10:02:38.754Z","avatar_url":"https://github.com/AdrianoCLeao.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Talking Hands - Sign Language Recognition System\n\n\u003cimg src=\"https://github.com/user-attachments/assets/36c6c711-d5f1-48e0-ae6f-c5ddf566440c\" alt=\"Alt text\" width=\"450\"\u003e\n\nA complete sign language recognition system using MediaPipe for hand tracking and TensorFlow/Keras for gesture classification.\n\nThis project aims to create a machine learning model that can identify, translate, and speak from live video of Libras (Brazilian Sign Language). It uses Google's Mediapipe to detect key points and Keras from TensorFlow to create the model.\n\n## Project Structure\n\n```\ntalking-hands/\n├── src/\n│   ├── __init__.py\n│   ├── core/\n│   │   ├── __init__.py\n│   │   ├── capture/\n│   │   │   ├── __init__.py\n│   │   │   ├── capture_samples.py\n│   │   │   └── create_keypoints.py\n│   │   ├── models/\n│   │   │   └── actions_18.keras\n│   │   ├── train/\n│   │   │   ├── __init__.py\n│   │   │   ├── evaluate_model.py\n│   │   │   ├── model.py\n│   │   │   └── training_model.py\n│   │   └── tts/\n│   │       ├── __init__.py\n│   │       └── text_to_speech.py\n│   └── utils/\n│       ├── __init__.py\n│       ├── constants.py\n│       └── utils.py\n├── data/\n│   └── keypoints/\n├── main.py\n├── mainwindow.ui\n├── run.py\n├── setup.py\n├── requirements.txt\n└── README.md\n```\n\n## Installation\n\n### Method 1: Using pip (Recommended)\n\n```bash\n# Install the package in development mode\npip install -e .\n```\n\n### Method 2: Manual installation\n\n```bash\n# Install dependencies\npip install -r requirements.txt\n```\n\n## Usage\n\n### Running the Main Application\n\n```bash\n# Using the run script\npython run.py main\n\n# Or directly\npython main.py\n```\n\n### Training a Model\n\n```bash\n# Using the run script\npython run.py train\n\n# Or using the module\npython -m src.core.train.training_model\n```\n\n### Creating Keypoints\n\n```bash\n# Using the run script\npython run.py keypoints\n\n# Or using the module\npython -m src.core.capture.create_keypoints\n```\n\n### Capturing Samples\n\n```bash\n# Using the run script\npython run.py capture\n\n# Or using the module\npython -m src.core.capture.capture_samples\n```\n\n## Package Usage\n\nYou can also import and use the modules directly:\n\n```python\nfrom src.core.train import training_model, get_model\nfrom src.core.capture import capture_sample, create_keypoints\nfrom src.core.tts import text_to_speech\nfrom src.utils import constants, utils\n\n# Train a model\nmodel_path = \"path/to/model.keras\"\ntraining_model(model_path, model_num=18)\n\n# Create keypoints\ncreate_keypoints(\"word_id\", \"frames_path\", \"output.h5\")\n\n# Text to speech\ntext_to_speech(\"Hello world\")\n```\n\n## Dependencies\n\nSee `requirements.txt` for the complete list of dependencies. Main dependencies include:\n\n- TensorFlow/Keras for machine learning\n- MediaPipe for hand tracking\n- OpenCV for computer vision\n- PyQt5 for GUI\n- NumPy and Pandas for data processing\n- scikit-learn for machine learning utilities\n\n## Features\n\n- Real-time sign language recognition\n- Model training with data augmentation\n- Keypoint extraction from video frames\n- Text-to-speech output\n- GUI interface for easy interaction\n- Modular package structure\n\n## Development\n\nTo develop this package:\n\n1. Clone the repository\n2. Install in development mode: `pip install -e .`\n3. Make your changes\n4. Run tests and ensure everything works\n  - `utils/utils.py`\n  - `utils/constants.py`\n  - `utils/text_to_speech.py`\n- `models/`: Pre-trained models for gesture translation.\n- `train/`: Scripts for model training.\n  - `training_model.py`\n  - `evaluate_model.py`\n- `capture/`: Scripts for capturing and processing new data.\n  - `capture_samples.py`\n  - `create_keypoints.py`\n\n## How to Use\n\n1. **Create a Virtual Environment**\n\nTo isolate the project's dependencies, it is recommended to create a virtual environment using `venv`.\n\n```bash\npython -m venv venv\n```\n2. Activate the Virtual Environment\nActivate the created virtual environment:\n- On Windows:\n```bash\nvenv\\Scripts\\activate\n```\n- On macOS and Linux:\n```bash\nsource venv/bin/activate\n```\n3. Install the Requirements\nWith the virtual environment activated, install the project's requirements:\n```bash\npip install -r requirements.txt\n```\n4. Run the Application\nExecute the main.py file to start the GUI application:\n```bash\npython main.py\n```\n## Contributions\nFeel free to contribute to this project. You can open issues and pull requests to discuss and implement improvements.\n\n## License\nThis project is under the MIT license. Check LICENSE.md for more details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadrianocleao%2Ftalking-hands","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fadrianocleao%2Ftalking-hands","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadrianocleao%2Ftalking-hands/lists"}