base-model/tests, branch v0.1.10 BaseModel for HydroRoll https://git.hydroroll.team/base-model/atom?h=v0.1.10 2026-01-05T11:17:08Z refactor: remove unused fix_speaker function and clean up code in onnx_infer.py 2026-01-05T11:17:08Z HsiangNianian i@jyunko.cn 2026-01-05T11:17:08Z urn:sha1:911a5610703a4ee2d7438e1398c5bbe8079099cc fix: simplify conditional assignment for entity text processing in test_onnx_only_infer.py 2026-01-05T06:40:15Z HsiangNianian i@jyunko.cn 2026-01-05T06:39:35Z urn:sha1:1a6d6edbe14f00df021a1e826d8d30555f301e30 feat: enhance code readability and formatting in onnx_infer.py 2026-01-05T06:40:15Z HsiangNianian i@jyunko.cn 2026-01-05T06:39:30Z urn:sha1:6713e38407bdbc1495692c7e297c027a1dc3f612 feat: update max_length parameter for TRPGParser and onnx_infer to improve text parsing capabilities 2026-01-05T06:33:10Z HsiangNianian i@jyunko.cn 2026-01-05T06:33:10Z urn:sha1:df94eb6c125279a9c32bc85de8633371d50afbed refactor: Update model download functionality and improve inference module to support automatic model retrieval from GitHub releases 2025-12-30T12:39:34Z HsiangNianian i@jyunko.cn 2025-12-30T12:39:34Z urn:sha1:298035052b3e3d083b57f5dbac0e86de4f94efba feat: Implement TRPG NER training and inference script with robust model path detection and enhanced timestamp/speaker handling 2025-12-30T11:14:39Z HsiangNianian i@jyunko.cn 2025-12-30T11:14:39Z urn:sha1:7ac684f1f82023c6284cd7d7efde11b8dc98c149 - 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.