tsukumi 0e0b4bea31 Fix: Disable optimization on InferenceSession initialization to speed up loading of ONNX models

2024-09-22 23:08:00 +09:00

..

chinese

Fix: Specifying the device_map option in extract_bert_feature()

2024-09-17 05:22:30 +09:00

english

Fix: Specifying the device_map option in extract_bert_feature()

2024-09-17 05:22:30 +09:00

japanese

Improve: Support ONNX inference, add ONNX conversion script

2024-09-17 16:55:03 +09:00

__init__.py

Improve: Support ONNX inference, add ONNX conversion script

2024-09-17 16:55:03 +09:00

bert_models.py

Fix: ONNX BERT model/tokenizer is not preloaded by default to avoid wasting VRAM

2024-09-18 05:11:15 +09:00

onnx_bert_models.py

Fix: Disable optimization on InferenceSession initialization to speed up loading of ONNX models

2024-09-22 23:08:00 +09:00

symbols.py

Refactor: rename text_processing to nlp

2024-03-08 06:20:44 +00:00