aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/src
Commit message (Collapse)AuthorAgeFilesLines
* fix: update version number to 0.1.8 in __init__.pyHsiangNianian2026-01-051-1/+1
|
* refactor: improve error handling and enhance code readability in inference ↵HsiangNianian2026-01-051-23/+25
| | | | module
* refactor: streamline import statements and improve print messages in ↵HsiangNianian2026-01-051-22/+10
| | | | training module
* refactor: improve code formatting and readability in utils/__init__.pyHsiangNianian2026-01-051-15/+21
|
* feat: add max_length validation in TRPGParser to enforce input constraintsHsiangNianian2026-01-051-0/+3
|
* feat: update max_length parameter for TRPGParser and onnx_infer to improve ↵HsiangNianian2026-01-051-3/+3
| | | | text parsing capabilities
* refactor: Clean up publish workflow by removing Test PyPI steps and ↵HsiangNianian2025-12-301-39/+9
| | | | improving artifact packaging
* feat: Enhance model download functionality to support zip file retrieval and ↵HsiangNianian2025-12-301-28/+57
| | | | extraction
* feat: Bump version to 0.1.3 in pyproject.toml and __init__.pyv0.1.3HsiangNianian2025-12-301-1/+1
|
* refactor: Update model download functionality and improve inference module ↵HsiangNianian2025-12-304-91/+122
| | | | to support automatic model retrieval from GitHub releases
* refactor: Refactor TRPG NER model SDK: restructure codebase into ↵HsiangNianian2025-12-305-9/+9
| | | | base_model_trpgner package, implement training and inference modules, and add model download functionality. Remove legacy training and utils modules. Enhance documentation and examples for better usability.
* feat: Refactor and enhance TRPG NER model SDKHsiangNianian2025-12-307-318/+795
| | | | | | | | | | | - Removed deprecated `word_conll_to_char_conll.py` utility and integrated its functionality into the new `utils` module. - Introduced a comprehensive GitHub Actions workflow for automated publishing to PyPI and GitHub Releases. - Added `__init__.py` files to establish package structure for `basemodel`, `inference`, `training`, and `utils` modules. - Implemented model downloading functionality in `download_model.py` to fetch pre-trained ONNX models. - Developed `TRPGParser` class for ONNX-based inference, including methods for parsing TRPG logs. - Created training utilities in `training/__init__.py` for NER model training with Hugging Face Transformers. - Enhanced utility functions for CoNLL file parsing and dataset creation. - Added command-line interface for converting CoNLL files to datasets with validation options.
* feat: Implement TRPG NER training and inference script with robust model ↵HsiangNianian2025-12-302-0/+318
path detection and enhanced timestamp/speaker handling - Added main training and inference logic in main.py, including CoNLL parsing, tokenization, and model training. - Introduced TRPGParser class for inference with entity aggregation and special handling for timestamps and speakers. - Developed utility functions for converting word-level CoNLL to char-level and saving datasets in various formats. - Added ONNX export functionality for the trained model. - Created a comprehensive requirements.txt and updated pyproject.toml with necessary dependencies. - Implemented tests for ONNX inference to validate model outputs.
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2026-01-20 22:26:12 +0000