Commit Graph

  • 20bea3546b Merge branch 'main' into ppg-vc-init babysor00 2022-02-24 00:31:13 +0800
  • 0536874dec Add config file for pretrained babysor00 2022-02-23 09:37:39 +0800
  • fad5023fca FIx known issues babysor00 2022-02-20 11:56:58 +0800
  • a7a4a66bf7 hifigan support train from existed ckpt peijiyang 2022-02-14 11:43:57 +0800
  • f90cc1c208
    Merge branch 'babysor:main' into hifigan hertz 2022-02-14 10:04:39 +0800
  • 19eaa68202 add preprocess and training babysor00 2022-02-13 11:28:41 +0800
  • 4529479091
    指定librosa版本 (#378) 李子 2022-02-10 20:47:26 +0800
  • bbf24e804c
    fixed the issues #372 AyahaShirane 2022-02-10 16:54:17 +0800
  • 5d70c4fd7d 指定librosa版本 lizi 2022-02-10 14:22:44 +0800
  • bac116b9ee Merge branch 'babysor-main' into main lizi 2022-02-10 14:20:36 +0800
  • 0c24cf8e53 pr lizi 2022-02-10 14:19:04 +0800
  • 379fd2b9fd Init ppg extractor and ppg2mel babysor00 2022-02-09 00:44:43 +0800
  • 8ad9ba2b60 change naming logic of saving trained file for synthesizer to allow shorter interval babysor00 2022-01-15 17:56:14 +0800
  • 7ca667dd25
    Create SECURITY.md GITHUBGUY12357999 2022-01-04 13:07:09 +0530
  • de4e525a0d modified tacotron to tacotron2 Rita 2021-12-26 12:37:35 +0800
  • b56ec5ee1b
    Fix a UserWarning (#273) D-Blue 2021-12-20 20:33:12 +0800
  • 28d8f6138b
    Fix a UserWarning D-Blue 2021-12-16 00:16:24 +0800
  • 0bc34a5bc9
    Fix TypeError at line 459 in toolbox/ui.py when both PySide6(PyQt6) and PyQt5 installed (#255) CrystalRays 2021-12-15 12:41:10 +0800
  • 4ae2b8fcd1
    Fix TypeError at line 459 in toolbox/ui.py when both PySide6(PyQt6) and PyQt5 installed CrystalRays 2021-12-08 19:39:07 +0800
  • 875fe15069
    Update readme for training encoder (#250) Wings Music 2021-12-07 19:10:29 +0800
  • 6e6653766a Update readme for training encoder Jerryuhoo 2021-12-07 10:27:53 +0800
  • 4728863f9d
    Fix inference on cpu device (#241) zzxiang 2021-11-29 22:10:07 +0900
  • a4daf42868
    1k steps to save tmp hifigan model (#240) hertz 2021-11-29 21:09:54 +0800
  • 429d436407 Fix inference on cpu device 朱志翔 2021-11-29 19:21:00 +0900
  • 8e2116eb53 1k steps to save tmp hifigan model hertz-pj 2021-11-29 17:11:48 +0800
  • b50c7984ab
    tacotron.py-Multi GPU with DataParallel (#231) harian 2021-11-27 20:53:08 +0800
  • 14b4282959 tacotron.py-Multi GPU with DataParallel cocucola 2021-11-24 10:33:32 +0800
  • 26fe4a047d Differentiate GST token babysor00 2021-11-18 22:55:13 +0800
  • aff1b5313b Order of declared pytorch module matters babysor00 2021-11-17 00:12:27 +0800
  • 7dca74e032 Change default to use speaker embed for reference babysor 2021-11-13 10:57:45 +0800
  • a37b26a89c 模型兼容问题加强 Compatibility Enhance of Pretrained Models and code base #209 babysor00 2021-11-10 23:23:13 +0800
  • 902e1eb537 Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese babysor00 2021-11-09 21:08:33 +0800
  • 5c0e53a29a Fix #205 babysor00 2021-11-09 21:08:28 +0800
  • 4edebdfeba
    修复synthesizer/models/tacotron.Encoder注释错误 (#203) DragonDreamer 2021-11-09 13:59:19 +0800
  • 19661bc5ac 修复synthesizer/models/tacotron.Encoder注释错误 DragonDreamer 2021-11-09 11:58:12 +0800
  • 6c8f3f4515 Allow to select vocoder in web babysor00 2021-11-08 23:55:16 +0800
  • 1ef3d6a7aa
    Update README.md Mihir Bhasin 2021-11-07 20:22:00 +0530
  • 2bd323b7df Update readme babysor00 2021-11-07 21:59:03 +0800
  • 3674d8b5c6 Use speaker embedding anyway even with default style babysor00 2021-11-07 21:48:15 +0800
  • 13395fc862
    Update tacotron.py weida wang 2021-11-06 23:11:12 +0800
  • 80aaf32164 Add max steps control in toolbox babysor00 2021-11-06 13:27:11 +0800
  • c396792b22 Upload new models babysor00 2021-10-27 20:19:50 +0800
  • 7c58fe01d1 Concat GST output instead of adding directly with original output babysor00 2021-10-23 10:28:32 +0800
  • 724194a4de
    Add code to control finetune layers (#154) v0.0.1 Vega 2021-10-23 10:25:43 +0800
  • 7ac411adf6
    Merge branch 'main' into finetune Vega 2021-10-23 10:25:29 +0800
  • 31bc6656c3 Fix bug of importing GST and add more parameters in toolbox babysor00 2021-10-21 00:40:00 +0800
  • aa35fb3139
    docs: this repo -> 本代码库 (#157) 洛竹 2021-10-20 22:54:31 +0800
  • 727eafc51b Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese babysor00 2021-10-20 00:27:19 +0800
  • d328ecba81 Reconstruct UI of toolbox babysor00 2021-10-20 00:27:13 +0800
  • fad574118c
    Update README-CN.md Vega 2021-10-18 13:50:19 +0800
  • 7b34ac80a2
    docs: this repo -> 本代码库 洛竹 2021-10-18 10:31:51 +0800
  • b0c156a537 Add new dataset support to preprocess parameter babysor00 2021-10-17 17:21:49 +0800
  • 8cf8be3fcc Add code to control finetune layers babysor00 2021-10-16 16:48:24 +0800
  • 724809abf4
    Update README.md Vega 2021-10-15 14:34:29 +0800
  • 05cd1a54ea
    Add new pretrain model with gst Vega 2021-10-14 01:26:23 +0800
  • 245099c740
    支持data_aishell(SLR33)数据集 (#141) 李子 2021-10-12 23:40:27 +0800
  • 7c2db0e5be 更新readme desktop 2021-10-12 23:35:38 +0800
  • c1701ecdb2 支持data_aishell(SLR33)数据集 desktop 2021-10-12 23:20:38 +0800
  • 6dd2af49fe Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese babysor00 2021-10-12 20:02:05 +0800
  • 8b43ec9a64 Fix bug pre-processing magicdata babysor00 2021-10-12 20:01:37 +0800
  • 2a99f0ff05
    Add gst (#137) Vega 2021-10-12 19:43:29 +0800
  • 178787887b Add readme Add-GST babysor00 2021-10-12 19:38:53 +0800
  • a824b54122 补充预处理文档 babysor00 2021-10-12 09:22:10 +0800
  • 43c86eb411 Make it backward compatible babysor00 2021-10-12 09:12:58 +0800
  • 37f11ab9ce Commit with working GST babysor00 2021-10-11 21:52:15 +0800
  • 81befb91b0
    Update ui.py (#136) weida wang 2021-10-11 17:17:36 +0800
  • b903286ca8
    Update ui.py weida wang 2021-10-11 15:28:39 +0800
  • e2017d0314 Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese into main babysor00 2021-10-05 10:48:58 +0800
  • 547ac816df Update demo and training param babysor00 2021-10-05 10:48:54 +0800
  • 6b4ab39601
    add alternative download source for dataset (google drive) (#112) Ji Zhang 2021-10-02 19:10:40 -0700
  • 1e2407f42a add alternative download source for dataset (google drive) Ji Zhang 2021-10-01 18:21:40 -0700
  • b46e7a7866 New web with selecting wav files babysor00 2021-10-01 22:13:39 +0800
  • 8a384a1191 Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese into main babysor00 2021-10-01 09:33:31 +0800
  • 11154783d8
    web tool box update UI (#111) Nemo 2021-10-01 00:32:29 +0800
  • 3713d64cc7
    update img webtoolbox Nemo 2021-10-01 00:24:59 +0800
  • d52db0444e
    Update launch.json (#109) AkifSaeed20 2021-09-30 21:52:43 +0530
  • 790d11a58b Allow to train encoder babysor00 2021-10-01 00:01:33 +0800
  • 5e7cc82373 web tool box update UI Nemo 2021-09-30 23:48:45 +0800
  • c8a783e05e
    Update launch.json AkifSaeed20 2021-09-29 20:04:28 +0530
  • cb82fcfe58 Add Zhihu link (chinese Quora) to readme babysor00 2021-09-27 21:59:44 +0800
  • 26ecb7546d Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese into main babysor00 2021-09-27 21:45:55 +0800
  • f64914fca8 add new model babysor00 2021-09-27 21:45:34 +0800
  • 512da52775
    Update README-CN.md (#102) Jenkey2011 2021-09-27 21:22:20 +0800
  • e6b3f162aa
    Update README-CN.md Jenkey2011 2021-09-27 19:33:22 +0800
  • 9c219f05c2 Add file structure in readme babysor00 2021-09-26 12:27:57 +0800
  • 4d9e460063 Change synthesizer read to restful style babysor00 2021-09-26 10:01:50 +0800
  • 0d0b55d3e9
    Web server release v2 (#99) Vega 2021-09-25 17:07:46 +0800
  • 4acfee2a64
    Support tensorboard to trace the training of Synthesizer (#98) hertz 2021-09-25 17:06:51 +0800
  • c9b56bd5dd Refactor to restful style babysor00 2021-09-25 17:06:18 +0800
  • 99269b2046 [Fix bug] remove n processes of embed in pre.py babysor00 2021-09-24 20:52:33 +0800
  • 9ac942b6a7
    Merge branch 'babysor:main' into tensorboard hertz 2021-09-24 15:35:17 +0800
  • 1489b2db2c add log_every params hertz-pj 2021-09-24 12:41:52 +0800
  • 060bd8fb4d add tensorborad tracing hertz-pj 2021-09-24 10:53:09 +0800
  • 9acd5d78e9 Merge branch 'WebServer' of https://github.com/babysor/Realtime-Voice-Clone-Chinese into WebServer babysor00 2021-09-24 09:54:30 +0800
  • 952a101d87 fix training preprocess of vocoder babysor00 2021-09-23 21:21:39 +0800
  • 2ee752a19c Run web.py! babysor00 2021-09-21 15:43:56 +0800
  • b6b67e634d init server.py (#93) balala 2021-09-21 13:01:27 +0800
  • b5a30d51ba Init App babysor00 2021-09-19 00:27:56 +0800
  • 28e6bce570
    Web server: Add latest changes (#96) Vega 2021-09-24 09:47:51 +0800
  • 2ccab50649
    Merge branch 'main' into WebServer Vega 2021-09-24 09:47:43 +0800