ChasonJiang 6dd2f72090

更改gpt并行推理时的mask策略为padding left (#2144) ...

* 更改gpt并行推理时的mask策略为padding left，使batch_infer更接近于naive_infer
减少冗余操作并使用torch_sdpa，以提升推理速度

* rollback tts_infer.yaml

2025-03-04 16:45:37 +08:00

..

AR

更改gpt并行推理时的mask策略为padding left (#2144)

2025-03-04 16:45:37 +08:00

BigVGAN

gpt_sovits_v3

2025-02-11 21:15:24 +08:00

configs

更改gpt并行推理时的mask策略为padding left (#2144)

2025-03-04 16:45:37 +08:00

f5_tts/model

update Gradient Checkpointing to reduce VRAM usage (#2040)

2025-02-12 23:00:34 +08:00

feature_extractor

All in one! 合并main分支和fast_inference_分支 (#1490)

2024-08-20 22:19:04 +08:00

module

v3sovits模型推理支持webui传语速参数调整合成语速

2025-02-28 16:50:35 +08:00

prepare_datasets

https://github.com/RVC-Boss/GPT-SoVITS/issues/2048

2025-02-14 12:01:27 +08:00

pretrained_models

Delete GPT_SoVITS/pretrained_models/init

2024-01-17 18:41:45 +08:00

text

Matching fast_langdetect update (#2140)

2025-03-04 14:10:58 +08:00

TTS_infer_pack

更改gpt并行推理时的mask策略为padding left (#2144)

2025-03-04 16:45:37 +08:00

download.py

Chores (#1422)

2024-08-13 16:31:12 +08:00

export_torch_script.py

优化 export_torch_script.py (#1739)

2024-11-07 18:19:20 +08:00

inference_cli.py

inference cli tool (#1195)

2024-06-26 22:17:05 +08:00

inference_gui.py

Update gui.py&webui.py (#1216)

2024-06-21 18:05:16 +08:00

inference_webui_fast.py

拆分i18n

2025-02-28 01:41:04 +08:00

inference_webui.py

修复超分后音量超过1写错了的bug

2025-03-01 19:17:03 +08:00

onnx_export.py

Fix onnx_export to support v2 (#1604)

2024-09-13 11:27:22 +08:00

process_ckpt.py

support sovits v3 lora training, 8G GPU memory is enough

2025-02-23 00:37:14 +08:00

s1_train.py

support sovits v3 lora training, 8G GPU memory is enough

2025-02-23 00:37:14 +08:00

s2_train_v3_lora.py

Add files via upload

2025-02-23 20:26:18 +08:00

s2_train_v3.py

Add files via upload

2025-02-23 20:26:18 +08:00

s2_train.py

Add files via upload

2025-02-23 20:26:18 +08:00

utils.py

Chores (#1422)

2024-08-13 16:31:12 +08:00