7 Commits

Author	SHA1	Message	Date
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
tsukumi	ebd249bca8	Fix: spm.model is missing	2024-12-19 13:16:25 +09:00
tsukumi	dcca37b9a8	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
tsukumi	9de6e04ad7	Add: Preparation for ONNX inference support ④	2024-09-17 13:25:17 +09:00
Isotr0py	dec3fc0737	Auto download update, optimize dataloader num_workers (#195) ... * update bert * auto download emo * fix typo * fix typo * fix bert download * optimize code format * remove unsued import * fix a bug * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>	2023-11-26 20:16:25 +08:00
Stardust·减	2c2b7e85e1	更新 bert_models.json	2023-11-07 14:27:52 +08:00
Isotr0py	8609449b63	Auto download missing model for bert_gen.py (#146) ... * auto download missing model * support openi * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix wrong delete * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * pass pre-commit * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix repeat login --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>	2023-11-04 04:06:10 +08:00