XucroYuri 757994c4ba style(webui): 训练样本下拉整合进参考信息板块(参考音频的文本上方) ...

将操作的入口和输出结果聚合在同一区域:
- 删除独立的「训练样本选择」板块
- 「训练样本音频」下拉移入「*请上传并填写参考信息」板块顶部
  (位于参考音频/参考文本上方), 入口与输出结果聚合

新结构:
  模型切换: [模型名|刷新] / [GPT|SoVITS|刷新路径]
  *请上传并填写参考信息:
    [训练样本音频(满宽, 选中即自动引用)]   <- 入口
    [参考音频 | 参考音频的文本+情绪/括注]   <- 输出

板块从3个精简为2个(组件58), 事件绑定不变。
端到端验证: 选模型->样本+权重; 切样本->参考音频+文本+情绪自动填入。

2026-07-07 13:16:53 +08:00

..

AR

增加cuda graph支持，普通推理模式推理速度原地翻倍，效果不变。2

2026-04-30 15:01:45 +08:00

BigVGAN

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

configs

优化TTS_Config的代码逻辑 (#2536)

2025-07-18 11:54:40 +08:00

eres2net

Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464)

2025-06-17 15:21:36 +08:00

f5_tts/model

Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464)

2025-06-17 15:21:36 +08:00

feature_extractor

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

module

fix: 修复多个模块中的独立 bug (#2755)

2026-04-18 17:10:56 +08:00

prepare_datasets

feat: 兼容 proplus-hc-dev 训练数据 + 新增「情绪/括注」字段

2026-07-07 11:44:02 +08:00

pretrained_models

Delete GPT_SoVITS/pretrained_models/init

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

text

fix: 多音字修改 (#2791)

2026-06-16 21:46:53 +08:00

TTS_infer_pack

feat: add training model/sample browsing API + WebUI, relax ref audio duration

2026-07-07 11:32:14 +08:00

download.py

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

export_torch_script_v3v4.py

Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464)

2025-06-17 15:21:36 +08:00

export_torch_script.py

尝试 stream infer (#2469)

2025-11-28 21:36:57 +08:00

inference_cli.py

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

inference_gui.py

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

inference_webui_fast.py

对齐gpt topk默认采样参数 (#2696)

2025-12-19 16:05:36 +08:00

inference_webui.py

style(webui): 训练样本下拉整合进参考信息板块(参考音频的文本上方)

2026-07-07 13:16:53 +08:00

onnx_export.py

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

process_ckpt.py

Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464)

2025-06-17 15:21:36 +08:00

s1_train.py

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

s2_train_v3_lora.py

[codex] Improve Windows single-GPU v3 LoRA training / 改进 Windows 单卡 v3 LoRA 训练流程 (#2767)

2026-04-18 16:54:26 +08:00

s2_train_v3.py

Add files via upload

2025-11-28 22:02:03 +08:00

s2_train.py

Add files via upload

2025-11-28 22:02:03 +08:00

stream_v2pro.py

尝试 stream infer (#2469)

2025-11-28 21:36:57 +08:00

sv.py

Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464)

2025-06-17 15:21:36 +08:00

utils.py

Resolve Python Logger warnings (#2379)

2025-06-10 18:03:23 +08:00