tsukumi 15af441cba Improve: Convert ONNX version of BERT models to FP16 ...

I have found that half-precision has little effect on speech synthesis quality and, depending on the environment, can reduce file size and memory usage by half, so I have decided to use FP16.

2024-12-19 14:51:30 +09:00

..

chinese

Remove: Unused import

2024-09-28 13:50:10 +09:00

english

Remove: Unused import

2024-09-28 13:50:10 +09:00

japanese

Remove: Unused import

2024-09-28 13:50:10 +09:00

__init__.py

Add: Support for speech synthesis in English and Chinese for ONNX inference in Non-JP-Extra models

2024-09-23 07:14:44 +09:00

bert_models.py

Fix: The conversion script for English BERT to Fast Tokenizer was incorrect, so tokenization was not performed correctly

2024-12-19 11:10:33 +09:00

onnx_bert_models.py

Improve: Convert ONNX version of BERT models to FP16

2024-12-19 14:51:30 +09:00

symbols.py

Refactor: rename text_processing to nlp

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