ZSCGR/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2026-08-13 01:53:43 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,044 Commits 3 Branches 4 Tags
08d627c3338173c3229286d8787060d6559fe0f8
Commit Graph
1044 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
RVC-BossandGitHub 08d627c333 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 
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
RVC-BossandGitHub 6d95b559e8 增加cuda graph支持，普通推理模式推理速度原地翻倍，效果不变。1 
增加cuda graph支持，普通推理模式推理速度原地翻倍，效果不变。1
 2026-04-30 15:01:11 +08:00
RVC-BossandGitHub ea2d2a8166 Update README.md 2026-04-19 21:02:57 +08:00
SapphireLabandGitHub d9f03dad3e Update Documentation (#2768) 
* 调整日志格式

* docs: Update other languages' changelogs
 2026-04-18 22:33:55 +08:00
RVC-BossandGitHub 647935357a Update Changelog_CN.md 2026-04-18 19:01:11 +08:00
RVC-BossandGitHub 02425ea256 Fixed issues such as missing imports for types like Optional. 
Fixed issues such as missing imports for types like `Optional`.
 2026-04-18 17:33:53 +08:00
Harikrishna KPandGitHub 938f05fce8 fix: correct torch.randint upper bound to include both values (#2733) 2026-04-18 17:19:55 +08:00
huang yutongandGitHub 445d18ccce fix: 修复 TTS 音频后处理中的多个缺陷 (#2753) 
1. 修复音频超采样时 int16 双重转换导致整数溢出（CRITICAL）
   - audio_postprocess 中 `audio = (audio * 32768).astype(np.int16)` 位于
     if/else 块之外无条件执行，当 super_sampling=True 时音频已在分支内
     转为 int16，再次乘以 32768 导致溢出和音频完全失真
   - 同时修复 super_sampling=True 但超分模型不存在时 torch.Tensor 调用
     .astype() 的 AttributeError

2. 修复 batched vocoder 推理中 padding_len=0 导致音频丢失（HIGH）
   - 当 padding_len 恰好为 0 时，`-0 * upsample_rate == 0`，切片
     `audio[x:0]` 返回空张量，导致整段音频丢失

3. 修复文件不存在时错误地抛出 FileExistsError（LOW）
   - 应为 FileNotFoundError

Made-with: Cursor
 2026-04-18 17:16:24 +08:00
MushroomcowisheggsGitHubmoomushroom
 		00ce973412 feat: 添加数据集的错误处理提示 (#2758) 
Co-authored-by: moomushroom <[email protected]>
 2026-04-18 17:13:30 +08:00
huang yutongandGitHub 14191901cd fix: 修复多个模块中的独立 bug (#2755) 
1. 修复 sync_buffer 中除以函数对象而非调用结果（distrib.py）
   - `buffer.data /= world_size` 中 world_size 是函数，缺少 ()，
     导致 TypeError 使分布式训练 buffer 同步失败

2. 修复 istft 函数缺少 return 语句（spec_utils.py）
   - 函数计算了结果但未返回，调用者始终得到 None

3. 修复 cut0 返回字面量 "/n" 而非换行符 "\n"（text_segmentation_method.py）
   - 导致后续 text.split("\n") 无法正确切分，字面 /n 被当作文本内容

4. 修复粤语 ASR 的 vad/punc model_revision 被无条件覆盖（funasr_asr.py）
   - 粤语分支将 vad_model_revision 设为空（因不使用 VAD/标点模型），
     但 if/else 外的赋值将其覆盖为 "v2.0.4"，传入错误的 revision 参数

Made-with: Cursor
 2026-04-18 17:10:56 +08:00
东云andGitHub 780383d5bd [codex] Improve Windows single-GPU v3 LoRA training / 改进 Windows 单卡 v3 LoRA 训练流程 (#2767) 
* Improve Windows single-GPU v3 LoRA training

* Drop unrelated checkpoint helper change from PR

* Tighten PR scope to single-GPU training path fixes
 2026-04-18 16:54:26 +08:00
白菜工厂1145号员工andGitHub ba8de9b760 优化 G2PW 的推理输入构造与多音字处理流程，减少重复计算，降低长句场景下的推理开销 (#2763) 
* Enhance G2P processing by implementing batch input handling in _g2p function, improving efficiency. Update prepare_onnx_input to utilize caching for tokenization and add optional parameters for character ID mapping and phoneme masks. Refactor G2PWOnnxConverter to streamline model loading and configuration management.

* Enhance G2PW model input handling by introducing polyphonic context character support and updating the data preparation method to return additional query IDs. This improves the processing of polyphonic characters in sentences.
 2026-04-18 16:52:32 +08:00
XXXXRT666andGitHub 2d9193b0d3 Migrate to miniforge, add missing dependencies, update docker file, remove deprecated files (#2732) 
* Migrate to miniforge, add missing dependencies, update docker file, remove deprecated files

* Add Env Vars and Secrets
 2026-02-09 15:05:25 +08:00
OaroraandGitHub 9986880b3f fix Conda 条款未同意导致的构建失败 (#2727) 2026-02-08 23:52:04 +08:00
ChasonJiangandGitHub c767f0b83b 修复bug (#2704) 
* 修复bug

* fallbak and bug fix
 2025-12-30 16:00:21 +08:00
ChasonJiangandGitHub 9080a967d5 修复采样错误 (#2703) 2025-12-30 15:21:03 +08:00
sushistackandGitHub 51df9f7384 Fix model file name in README instructions (#2700) 2025-12-25 16:44:21 +08:00
ChasonJiangandGitHub bfca0f6b2d 对齐naive_infer的解码策略，防止吞句 (#2697) 2025-12-19 17:37:19 +08:00
ChasonJiangandGitHub abe984395c 对齐gpt topk默认采样参数 (#2696) 2025-12-19 16:05:36 +08:00
RVC-BossandGitHub cc89c3660e Update requirements.txt 2025-12-19 15:54:54 +08:00
ChasonJiangandGitHub 36b3231c6f bug fix (#2689) 2025-12-15 14:23:06 +08:00
RVC-BossandGitHub 9ec3a60f30 Update config.py 2025-12-01 20:23:49 +08:00
RVC-BossandGitHub fc533b6fb7 Update fasterwhisper_asr.py 2025-12-01 11:38:37 +08:00
XXXXRT666andGitHub 857799276c Fix Modelscope (#2679) 2025-12-01 11:13:15 +08:00
Spr_AachenandGitHub 92d2d337fd Fix training error caused by float type of default_batch_size parameter (#2662) 2025-11-28 22:53:43 +08:00
ChasonJiangandGitHub 6fb441f65e 更友好的流模式选项 (#2678) 2025-11-28 22:13:48 +08:00
XXXXRT666andGitHub c85c54eca9 Add ModelScope Snapshot Download For ASR (#2627) 
* Add ModelScope Snapshot Download For ASR

* Typo Fix

* Remove YUE in whisper

* Remove HF ENDPOINT

* Add FunASR Download
 2025-11-28 22:10:49 +08:00
RVC-BossandGitHub cb00840c4e Add files via upload 2025-11-28 22:02:03 +08:00
wzy3650GitHubwangzeyuan
 		60a4a214af vq distributed training support (#2577) 
Co-authored-by: wangzeyuan <[email protected]>
 2025-11-28 21:57:13 +08:00
zzzandGitHub 6375bbe316 尝试 stream infer (#2469) 
* 尝试 stream infer

* 在 stream_infer 脚本中绘制生成的音频

* stream_infer 增加导出部分。

* stream_infer: 更方便找规律的图

* stream_infer: 在拼接音频时进行相关性搜索，减少拼接带来基频断裂的情况

* stream_infer: 导出 `find_best_audio_offset_fast`

* stream_infer: 优化波形显示，方便对比

* stream_v2pro.py 从命令行读取参数

* stream_v2pro.py 减少用于导出的文本长度

* stream_v2pro: 修复由于 spectrogram_torch 输入是 half 导致 spec 溢出最终没有声音的问题

* stream_v2pro: 新增 --lang 参数提示参考文字的语言类型
 2025-11-28 21:36:57 +08:00
KamioRinnandGitHub e00ca92140 Fix ASMD (#2636) 2025-11-28 21:22:43 +08:00
ChasonJiangandGitHub 92ab59c553 更细粒度的流式推理模式 (#2671) 
* 更好的流式推理模式

* 清理无用代码

* modified:   GPT_SoVITS/AR/models/t2s_model.py
	modified:   GPT_SoVITS/TTS_infer_pack/TTS.py
	modified:   GPT_SoVITS/module/models.py

* modified:   GPT_SoVITS/TTS_infer_pack/TTS.py

* modified:   .gitignore
	modified:   GPT_SoVITS/AR/models/t2s_model.py
	modified:   GPT_SoVITS/TTS_infer_pack/TTS.py
	modified:   GPT_SoVITS/module/models.py

* modified:   GPT_SoVITS/AR/models/t2s_model.py
	modified:   GPT_SoVITS/TTS_infer_pack/TTS.py
	modified:   GPT_SoVITS/module/models.py
	modified:   api_v2.py

* modified:   GPT_SoVITS/TTS_infer_pack/TTS.py

* 更正拼写错误

* 支持固定chunk长度的流式推理，优化sola算法

* 修复api_v2的ogg格式传输问题
 2025-11-28 21:12:41 +08:00
RVC-BossandGitHub 11aa78bd9b 修复环境变量可能不为str的问题 
修复环境变量可能不为str的问题
 2025-09-10 15:01:04 +08:00
XXXXRT666andGitHub fdf794e31d Update WSL Rocm (#2561) 2025-08-02 17:47:15 +08:00
多玩幻灵qwqandGitHub 0be59c8043 fix: 更正链接 (#2539) 2025-07-19 00:29:48 +08:00
ChasonJiangandGitHub b5a67e6247 修复gpt的loss计算问题 (#2537) 
* 修复gpt的loss计算问题

* fallback tts config
 2025-07-18 14:59:59 +08:00
ChasonJiangandGitHub b9211657d8 优化TTS_Config的代码逻辑 (#2536) 
* 优化TTS_Config的代码逻辑

* 在载入vits权重之后保存tts_config
 2025-07-18 11:54:40 +08:00
XXXXRT666andGitHub cefafee32c Add Distil (#2531) 2025-07-17 20:28:25 +08:00
RVC-BossandGitHub 2d09bbe63a Update tts_infer.yaml 2025-07-16 15:44:04 +08:00
RVC-BossandGitHub 4d8ebf8523 Update TTS.py 2025-07-16 15:43:26 +08:00
jiangsier-xyzGitHubjiangsier-xyz
 		e476b01f30 解决 TTS.py 无法识别真正支持版本 v2Pro、v2ProPlus 的问题 (#2490) 
同时更新一版默认配置。

Co-authored-by: jiangsier-xyz <[email protected]>
 2025-07-16 15:42:36 +08:00
RVC-BossandGitHub 42586e20f7 add RTF performence 
add RTF performence
 2025-07-14 19:01:26 +08:00
RVC-BossandGitHub 85035f7ac0 add RTF performence 
add RTF performence
 2025-07-14 18:56:22 +08:00
RVC-BossandGitHub 706bec74f8 Update assets.py 2025-07-11 16:11:08 +08:00
XXXXRT666andGitHub ec1218893e Update Badge (#2518) 
* Update README.md

* Update README.md

* Update Badges

* specify ranges
 2025-07-11 16:10:07 +08:00
RVC-BossandGitHub fec515dcce Update Changelog_CN.md 2025-07-10 18:33:18 +08:00
RVC-BossandGitHub 426e1a2bb4 提升推理进程优先级 2025-07-10 18:16:45 +08:00
RVC-BossandGitHub 4e3c69043c Update inference_webui.py 2025-07-10 18:16:24 +08:00
RVC-BossandGitHub e63e0901fd Update assets.py 2025-07-10 18:12:24 +08:00
RVC-BossandGitHub 97e37c74d8 Update README.md 2025-07-10 18:06:04 +08:00