Commit Graph

  • 4a9d566aa8
    Merge 8c0cb0d691554d8311d8904972ae3efa8bfd1cc4 into 08d627c3338173c3229286d8787060d6559fe0f8 Ella Zhang 2026-05-06 22:08:06 +08:00
  • 3666fd2bbf
    Merge 7f6787121bca21f78a77a9c9de9206f9b48179d7 into 08d627c3338173c3229286d8787060d6559fe0f8 linguikun1986 2026-05-03 14:39:22 -03:00
  • ff89da1da3
    Merge d939ec35875d018fd5bc4f280189fb736b4c401c into 08d627c3338173c3229286d8787060d6559fe0f8 SEUNG YEOP HAN 2026-05-03 14:39:20 -03:00
  • 5af6aa3781
    Merge 76020a920616513b98175d8614838bd00d468ae1 into 08d627c3338173c3229286d8787060d6559fe0f8 amlyczz 2026-05-03 14:39:04 -03:00
  • faaab603ef
    Merge 4a2d88ce4e06cbff751702cac8824591d306e1a6 into 08d627c3338173c3229286d8787060d6559fe0f8 c137650 2026-05-03 14:38:53 -03:00
  • cbe7f6b1ca
    Merge 1fae47bf19dccd1c26e3c9517bad148949027674 into 08d627c3338173c3229286d8787060d6559fe0f8 ChanningWang2018 2026-05-01 16:54:06 +08:00
  • 47008e2d66
    Merge 0061b0012481383ec49fe6ef274289099b5d3853 into 08d627c3338173c3229286d8787060d6559fe0f8 justoy 2026-04-30 09:55:56 -07:00
  • 32d650b709
    Merge 8858492f56326dce521db2c4a4b3a7323e786596 into 08d627c3338173c3229286d8787060d6559fe0f8 zpeng11 2026-04-30 16:52:30 +08:00
  • 67e54b2380
    Merge edc9ef99adef0ad0bc98c39f7840529d5af1c8a7 into 08d627c3338173c3229286d8787060d6559fe0f8 EdgeInfinity 2026-04-30 15:06:59 +08:00
  • 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 main RVC-Boss 2026-04-30 15:01:45 +08:00
  • 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 RVC-Boss 2026-04-30 15:01:11 +08:00
  • 47365e2085
    Merge 6fc6148f8d3016f4f7e6d176710284a1645c26d9 into ea2d2a81667239d37615697e8f0056e35bab2db6 huang yutong 2026-04-21 16:01:57 +08:00
  • 4b8fe9b768
    Merge 6c349541d3cbfae62eab6e533662bdfe4df68c38 into ea2d2a81667239d37615697e8f0056e35bab2db6 terrenceyeyang-code 2026-04-21 06:32:58 +00:00
  • 63adee93a6
    Merge 8b195a5adb362c35c65ca4ab093543a1168fb221 into ea2d2a81667239d37615697e8f0056e35bab2db6 changhaowuwu 2026-04-21 01:39:28 +00:00
  • c2e0b167e1
    Merge 36df18cbb94041a71f30501c10f3b73b18e8a1e4 into ea2d2a81667239d37615697e8f0056e35bab2db6 foreverhell 2026-04-21 00:08:45 +00:00
  • 31fafc4541
    Merge 855c369a17f04d300f7005708c92d60b8590563d into ea2d2a81667239d37615697e8f0056e35bab2db6 Zone Tome 2026-04-20 21:03:42 +00:00
  • 56180a4c26
    Merge 7604f36bb270d0a897df0b8d4dd9d35f860d06cb into ea2d2a81667239d37615697e8f0056e35bab2db6 逸游仙人 2026-04-20 17:49:18 +00:00
  • 7ed8e462be
    Merge fc987e2a6512ae82ba27ec925c221d54cc54a3ae into ea2d2a81667239d37615697e8f0056e35bab2db6 Jacky He 2026-04-20 17:05:53 +00:00
  • 65e898f6a8
    Merge 2e230d055efc7a37e908a3b28bec8914792397e7 into ea2d2a81667239d37615697e8f0056e35bab2db6 Oct0pu5 2026-04-20 11:20:26 +00:00
  • be1c3424f1
    Merge 61afcf2600646fca8e27b412cd9564fefb6a6678 into ea2d2a81667239d37615697e8f0056e35bab2db6 jackwu982 2026-04-20 10:30:34 +00:00
  • 4a25469099
    Merge c93bf48785aba24ee47a268f1eb5dcee1b8866dd into ea2d2a81667239d37615697e8f0056e35bab2db6 spawner 2026-04-20 10:26:26 +00:00
  • 03631feafd
    Merge 485cb85a552c5bd5b6387569da9b1727332e940e into ea2d2a81667239d37615697e8f0056e35bab2db6 Jacky He 2026-04-20 10:05:33 +00:00
  • 1bfd0e1f57
    Merge 36d01b87ac0345be9e307d9d754d8eea51266177 into ea2d2a81667239d37615697e8f0056e35bab2db6 0xAlexKorn 2026-04-20 06:33:37 +00:00
  • d89c277f01 fix: V-001 security vulnerability orbisai0security 2026-04-20 04:03:58 +00:00
  • a94fd5a14a
    Merge 60414d25a39f3786a392523297734c144d1c59a9 into ea2d2a81667239d37615697e8f0056e35bab2db6 __kaning123__ 2026-04-19 14:16:06 +01:00
  • ea2d2a8166
    Update README.md RVC-Boss 2026-04-19 21:02:57 +08:00
  • 4a2d88ce4e Fix: handle empty bert_list and align BERT/phones length Bronya Zaychik 2026-04-19 13:28:08 +08:00
  • d9f03dad3e
    Update Documentation (#2768) SapphireLab 2026-04-18 22:33:55 +08:00
  • 6cd768ff79 docs: Update other languages' changelogs starylan 2026-04-18 22:23:54 +08:00
  • 6bb8eb0172 调整日志格式 starylan 2026-04-18 20:40:49 +08:00
  • 647935357a
    Update Changelog_CN.md RVC-Boss 2026-04-18 19:01:11 +08:00
  • 02425ea256
    Fixed issues such as missing imports for types like Optional. RVC-Boss 2026-04-18 17:33:53 +08:00
  • 65f902ca80
    Merge 62ee3c2aa063bc2361127f9aa418eea49a132dae into 938f05fce8bcfb2407b8311fbbc10ac4d9ffe1c0 Ray 2026-04-18 17:20:15 +08:00
  • 938f05fce8
    fix: correct torch.randint upper bound to include both values (#2733) Harikrishna KP 2026-04-18 14:49:55 +05:30
  • 445d18ccce
    fix: 修复 TTS 音频后处理中的多个缺陷 (#2753) huang yutong 2026-04-18 17:16:24 +08:00
  • 00ce973412
    feat: 添加数据集的错误处理提示 (#2758) Mushroomcowisheggs 2026-04-18 17:13:30 +08:00
  • 14191901cd
    fix: 修复多个模块中的独立 bug (#2755) huang yutong 2026-04-18 17:10:56 +08:00
  • 780383d5bd
    [codex] Improve Windows single-GPU v3 LoRA training / 改进 Windows 单卡 v3 LoRA 训练流程 (#2767) 东云 2026-04-18 16:54:26 +08:00
  • 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) 白菜工厂1145号员工 2026-04-18 16:52:32 +08:00
  • 43506a8a69 Tighten PR scope to single-GPU training path fixes 东云 2026-04-18 15:02:38 +08:00
  • e8c53643e7 Drop unrelated checkpoint helper change from PR 东云 2026-04-18 14:59:30 +08:00
  • 96b8701186 Improve Windows single-GPU v3 LoRA training 东云 2026-04-18 13:50:17 +08:00
  • 76020a9206 fix: ensure torchaudio matches PyTorch CUDA version and add libnppicc amlyczz 2026-04-12 23:16:28 +08:00
  • 60414d25a3
    Merge pull request #2 from kaning123/Dev __kaning123__ 2026-04-06 13:32:49 +08:00
  • e6a67650ff feat: 添加中间量导出功能 Kaning123 2026-04-06 13:01:32 +08:00
  • 24d7290c11 feat: Added VoiceChange.py Kaning123 2026-04-06 12:59:31 +08:00
  • fb50fc090f feat:Added batch tts option Kaning123 2026-04-06 12:58:00 +08:00
  • cb2b844f45 feat: Added ReturnWay option to get_tts_wav Kaning123 2026-04-04 14:17:07 +08:00
  • 5c03499fcf feat:向 VoiceSave 模块中添加 find_func Kaning123 2026-04-02 17:26:08 +08:00
  • 46ae12bf17 feat:添加关闭tts webui 的入口 与 ge 等中间量的保存入口用于分发及使用 Kaning123 2026-04-02 17:24:19 +08:00
  • 47170fd555 feat: 添加了向张量组文件中追加张量的功能 Kaning123 2026-03-29 11:10:28 +08:00
  • cdfa2bc859 feat: 添加数据集的错误处理提示 moomushroom 2026-03-22 20:40:11 +08:00
  • f3a9603eb0 style: move new entries to the middle of the page Kaning123 2026-03-21 13:19:48 +08:00
  • 5450922d8d feat:Added entry to get value "ge" of class SynthesizerTrn Kaning123 2026-03-19 17:39:55 +08:00
  • 7ed3a730ec fix: 修复多个模块中的独立 bug wishhyt 2026-03-18 10:48:01 +08:00
  • 6fc6148f8d fix: 修复 API 输入验证和参数处理中的多个缺陷 wishhyt 2026-03-18 10:47:05 +08:00
  • c62f629aa7 fix: 修复 TTS 音频后处理中的多个缺陷 wishhyt 2026-03-18 10:46:19 +08:00
  • 86ac5555e1 feat: Added webUI entries Kaning123 2026-03-14 15:28:50 +08:00
  • e49d396b18 fix: 添加了inst.bat 与 inst2.ps1 以应对 install.ps1 运行时可能出现的 “由于调用深度溢出,脚本失败。” 错误 Kaning123 2026-03-14 13:28:46 +08:00
  • eedb06b303 fix:Fixed config.json loader in config.py Kaning123 2026-03-14 13:01:11 +08:00
  • 6e3db0126c fix: Fixed conda-go-webui.bat Kaning123 2026-03-14 12:59:09 +08:00
  • 0e83383544 feat:added bat file for launching webui with conda Kaning123 2026-03-14 09:32:11 +08:00
  • 99a2e356f2 feat:remove “-q“ option of conda installation Kaning123 2026-03-13 21:35:24 +08:00
  • 8a444c10b7 Enhance TTS processing with new reference specification handling and profiling metrics baicai-1145 2026-03-13 16:45:38 +08:00
  • c94de2f2cb Enhance TTS audio processing with improved resampling and profiling metrics baicai-1145 2026-03-13 16:45:00 +08:00
  • bc1f3f32de Enhance audio processing in TTS framework with resampling and profiling improvements baicai-1145 2026-03-13 02:03:25 +08:00
  • 17cb2e5acf Implement G2PW processing enhancements in TTS framework baicai-1145 2026-03-12 23:04:39 +08:00
  • 5cf68a91d3 Add g2pw submodule and enhance TTS processing with AsyncStageGate baicai-1145 2026-03-12 23:03:33 +08:00
  • 6c349541d3 fix: add fallback for torchaudio/torchcodec loading and support PyTorch 2.6+ security policy Terrence Yang 2026-03-12 10:53:58 +08:00
  • 6a822b28c3 Enhance TTS API with improved request handling and asynchronous processing baicai-1145 2026-03-12 01:27:19 +08:00
  • d453a8e47c Add unified engine stage components for TTS processing orchestration baicai-1145 2026-03-11 21:15:19 +08:00
  • a3a5aad157 Add unified engine components for TTS processing and state management baicai-1145 2026-03-11 20:49:41 +08:00
  • 3fd4f48651 Add unified engine API modules for direct and scheduler-based TTS processing baicai-1145 2026-03-11 18:36:24 +08:00
  • b046a093d3 Add unified engine delegates and orchestration components for enhanced TTS processing baicai-1145 2026-03-11 18:35:47 +08:00
  • 800f01790e Refactor EngineApiFacade and EngineApiDelegates for improved method naming and structure baicai-1145 2026-03-11 17:58:20 +08:00
  • d1ec7d9e54 Add unified engine components and API for enhanced TTS processing baicai-1145 2026-03-11 08:32:56 +08:00
  • 06d6b67f73 Add PreparedCpuStage data class and refactor prepare_cpu_stage_profiled_async method in PrepareCoordinator for improved CPU profiling. Introduce prepare_gpu_stage_profiled_async method to streamline GPU stage preparation using the new data class, enhancing overall performance and maintainability. baicai-1145 2026-03-11 05:29:30 +08:00
  • 6a427b4f54 Update TTS API to support asynchronous execution by replacing synchronous TTS calls with asynchronous counterparts in both api_v2.py and api_v3.py. Introduce new data classes in unified_engine.py for enhanced request handling and state management, improving overall system performance and maintainability. baicai-1145 2026-03-10 21:25:14 +08:00
  • d1a97fd04d Refactor TTS API to streamline audio processing by removing unused packing functions and optimizing the tts_handle method for asynchronous execution. Update type hints and clean up imports for improved code clarity and maintainability. baicai-1145 2026-03-10 20:46:14 +08:00
  • 69ac7f9027 Integrate UnifiedTTSEngine into TTS API for improved audio processing and control. Refactor tts_handle and control endpoints to utilize the new engine, enhancing error handling and response management. Update set_refer_audio and set_gpt_weights endpoints to return payloads from the engine, streamlining audio configuration processes. baicai-1145 2026-03-10 06:59:28 +08:00
  • 827d6ea47c Refactor TTS and scheduler components to enhance text processing and batching capabilities. Introduce PrepareCoordinator for managing text feature preparation asynchronously, and update SchedulerDebugWorker to support new finalize task management. Implement batch processing in PrepareBertBatchWorker with improved admission control and profiling metrics. Add text CPU preprocessing utilities for better text segmentation and normalization. baicai-1145 2026-03-10 06:58:53 +08:00
  • a45e171ff5 Enhance sampling functions in TTS by adding support for previous token masks in logits_to_probs. Implement batch processing for sampling with padded token sequences and contiguous sampling groups. Refactor sampling logic in T2S scheduler to utilize new functionalities, improving efficiency and flexibility in token generation. baicai-1145 2026-03-09 21:24:16 +08:00
  • 845b181360 Implement batch processing for BERT and reference semantic tasks in TTS. Introduce StageLimiter for managing concurrent processing and enhance the TTS class with new methods for handling audio and semantic extraction. Update profiling metrics for better performance tracking during inference. baicai-1145 2026-03-09 05:19:28 +08:00
  • d245eb169c Refactor T2S scheduler and inference handling to improve attention mask management and memory tracking. Update T2SRunningRequest and T2SActiveBatch classes to include optional key padding masks. Introduce new benchmarking tools for API performance and memory usage analysis, enhancing overall system efficiency. baicai-1145 2026-03-09 01:42:04 +08:00
  • dc37b0b9ef Add WebAPI documentation and implement TTS API with endpoints for text-to-speech inference, control commands, and model switching. Enhance TTS class with methods for extracting prompt semantics and reference audio specifications. Introduce a scheduler prototype for managing T2S requests. baicai-1145 2026-03-09 00:22:59 +08:00
  • 30a4557d8d Implement last inference statistics tracking in Text2SemanticDecoder and enhance TTS class with prompt semantic extraction. This includes methods for setting and retrieving inference stats, as well as improvements to audio processing and feature extraction in TTS. baicai-1145 2026-03-08 23:08:27 +08:00
  • b250e62402 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. baicai-1145 2026-03-08 03:01:20 +08:00
  • 800acd45ff 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. baicai-1145 2026-03-07 05:47:22 +08:00
  • c0fe483288
    Merge 4820d5a101a5240b74657a55d8b75357a04d8ce3 into 2d9193b0d3c0eae0c3a14d8c68a839f1bae157dc FAN JIALI 2026-03-05 03:44:28 +00:00
  • 4820d5a101 fix: apply same Windows single-GPU gloo bypass to s2_train_v3 and s2_train_v3_lora fanfan-love-meatmeat 2026-03-05 11:44:25 +08:00
  • 832e5b6160 fix: bypass gloo DDP for Windows single-GPU training fanfan-love-meatmeat 2026-03-05 10:56:21 +08:00
  • 8b195a5adb security: replace eval() with safe boolean parsing changhaowuwu 2026-02-25 22:08:01 +01:00
  • 53b17bd2d2
    Merge pull request #1 from kaning123/Dev __kaning123__ 2026-02-25 14:01:46 +08:00
  • 69f1c9c2dd
    feat: Added path check __kaning123__ 2026-02-25 13:56:47 +08:00
  • 012eb93ef8
    feat:添加了是否启用参考音频的变量 __kaning123__ 2026-02-25 10:37:33 +08:00
  • f6e8ec8a78
    feat:Added .voice loader __kaning123__ 2026-02-25 10:20:48 +08:00
  • 1c54a945cb
    feat: Added entrys to save sv_emb and refers __kaning123__ 2026-02-25 07:53:03 +08:00
  • a6a53f7231
    feat: Added entry to disable checks __kaning123__ 2026-02-24 07:48:12 +08:00
  • 1671f54c1d
    Merge e8e794daa41ec71344611f6531c1b54b335c8cbb into 2d9193b0d3c0eae0c3a14d8c68a839f1bae157dc Masoud Azizi 2026-02-23 16:46:13 +01:00
  • a06011d838
    fix:fix import errors __kaning123__ 2026-02-23 14:29:40 +08:00