{"id":30141140,"url":"https://github.com/pacatro/lse2text","last_synced_at":"2026-04-11T19:03:57.037Z","repository":{"id":308762563,"uuid":"1026314881","full_name":"Pacatro/Lse2Text","owner":"Pacatro","description":"Deep learning program that translates Spanish Sign Language (LSE) to text in real time.","archived":false,"fork":false,"pushed_at":"2025-08-07T17:53:00.000Z","size":913,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-07T19:32:40.822Z","etag":null,"topics":["ai","cnn","computer-vision","deep-learning","lse","matplotlib","numpy","pandas","python","pytorch","pytorch-lightning","scikit-learn","torchmetrics","translation"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Pacatro.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2025-07-25T17:08:34.000Z","updated_at":"2025-08-07T14:19:31.000Z","dependencies_parsed_at":"2025-08-07T19:46:26.016Z","dependency_job_id":null,"html_url":"https://github.com/Pacatro/Lse2Text","commit_stats":null,"previous_names":["pacatro/lse2text"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Pacatro/Lse2Text","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pacatro%2FLse2Text","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pacatro%2FLse2Text/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pacatro%2FLse2Text/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pacatro%2FLse2Text/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Pacatro","download_url":"https://codeload.github.com/Pacatro/Lse2Text/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pacatro%2FLse2Text/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269831923,"owners_count":24482298,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-11T02:00:10.019Z","response_time":75,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["ai","cnn","computer-vision","deep-learning","lse","matplotlib","numpy","pandas","python","pytorch","pytorch-lightning","scikit-learn","torchmetrics","translation"],"created_at":"2025-08-11T04:34:42.034Z","updated_at":"2025-12-30T21:47:47.680Z","avatar_url":"https://github.com/Pacatro.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LSE to Text\n\nLSE to Text is a tool for translating [Spanish Sign Language (`LSE`)](https://en.wikipedia.org/wiki/Spanish_Sign_Language) images to text using deep learning. It provides a simple command line interface (`CLI`) for training and evaluating models.\n\n---\n\n## Features\n\n- Train a custom model on Spanish Sign Language alphabet images\n- Predict text from sign language images using a trained model\n- Evaluate model performance using K-Fold Cross Validation\n- Easy CLI for training and inference\n- Configurable training parameters\n\n---\n\n## Requirements\n\n- [`Python`](https://www.python.org/) 3.12+\n- [`uv`](https://docs.astral.sh/uv/) (for dependency management)\n\n## Installation\n\n1. Clone this repository:\n\n   ```terminal\n   git clone https://github.com/Pacatro/Lse2Text\n   cd Lse2Text\n   ```\n\n2. Run the program (this will install dependencies and create a virtual environment):\n\n   ```terminal\n   uv run src/main.py\n   ```\n\n---\n\n## Usage\n\nThe CLI offers three main commands: `train`, `predict` and `eval`.\n\n### General CLI\n\n```terminal\nUsage: main.py [OPTIONS] COMMAND [ARGS]...\n\nOptions:\n  --verbose             -v        Verbose mode\n  --install-completion            Install completion for the current shell.\n  --show-completion               Show completion for the current shell, to copy it or customize the\n                                  installation.\n  --help                -h        Show this message and exit.\n\nCommands:\n  train     Train a model with the given parameters and save it to the given path.\n  predict   Runs inference with the given model.\n  eval      Runs a K-Fold Cross Validation evaluation.\n```\n\n---\n\n### Train Command\n\nTrain a model with the given parameters and save it in [`ONNX`](https://onnx.ai/) format.\n\n```terminal\nUsage: main.py train [OPTIONS]\n\nOptions:\n  --out-model         -o      TEXT     Model path in ONNX format [default: model.onnx]\n  --epochs            -e      INTEGER  Number of train epochs [default: 50]\n  --batch-size        -b      INTEGER  Batch size [default: 32]\n  --debug             -d               Run in debug mode\n  --metrics-filename  -m      TEXT     Metrics filename without extension [default: None]\n  --use-logger        -l               Use a logger\n  --help              -h               Show this message and exit.\n```\n\n**Example:**\n\n```terminal\nuv run src/main.py train -o model.onnx -e 20 -b 64\n```\n\n---\n\n### Predict Command\n\nRun inference with the given model.\n\n```terminal\nUsage: main.py predict [OPTIONS]\n\nOptions:\n  --model-path  -m      TEXT     Model path [default: model.onnx]\n  --max-preds   -p      INTEGER  Max number of predictions [default: 20]\n  --help        -h               Show this message and exit.\n```\n\n**Example:**\n\n```terminal\nuv run src/main.py predict -m model.onnx -p 10\n```\n\n### Evaluate Command\n\nRun a K-Fold Cross Validation evaluation.\n\n```terminal\nUsage: main.py eval [OPTIONS]\n\nOptions:\n  --folds       -k      INTEGER  The number of folds for CV [default: 5]\n  --batch-size  -b      INTEGER  Batch size [default: 32]\n  --epochs      -e      INTEGER  Number of train epochs [default: 50]\n  --help        -h               Show this message and exit.\n```\n\n**Example:**\n\n```terminal\nuv run src/main.py eval -k 10 -b 64\n```\n\n## Author\n\nCreated by [**Paco Algar Muñoz**](https://github.com/Pacatro).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpacatro%2Flse2text","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpacatro%2Flse2text","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpacatro%2Flse2text/lists"}