base-model - Base Model (GitHub mirror)

	Commit message (Collapse)	Author	Age	Files	Lines
*	refactor: remove unused fix_speaker function and clean up code in onnx_infer.py	HsiangNianian	2026-01-05	1	-12/+4
\|
*	fix: simplify conditional assignment for entity text processing in ↵	HsiangNianian	2026-01-05	1	-3/+1
\| \| \| \|	test_onnx_only_infer.py
*	feat: enhance code readability and formatting in onnx_infer.py	HsiangNianian	2026-01-05	1	-13/+42
\|
*	feat: update max_length parameter for TRPGParser and onnx_infer to improve ↵	HsiangNianian	2026-01-05	1	-1/+1
\| \| \| \|	text parsing capabilities
*	refactor: Update model download functionality and improve inference module ↵	HsiangNianian	2025-12-30	1	-0/+198
\| \| \| \|	to support automatic model retrieval from GitHub releases
*	feat: Implement TRPG NER training and inference script with robust model ↵	HsiangNianian	2025-12-30	1	-0/+115
	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.