|
3 | 3 | [Japanese](/README_ja.md) [Korean](/README_ko.md) |
4 | 4 |
|
5 | 5 | ## What's New! |
| 6 | +- Beatrice V2 Training Code Released!!! |
| 7 | + - [Training Code Repository](https://huggingface.co/fierce-cats/beatrice-trainer) |
| 8 | + - [Colab Version](https://github.com/w-okada/beatrice-trainer-colab) |
| 9 | +- v.2.0.47-alpha |
| 10 | + - [HERE](https://github.com/w-okada/voice-changer/tree/v.2) |
| 11 | + - feature: |
| 12 | + - Expanded extra frame |
| 13 | + - bugfix: |
| 14 | + - Changed the default speaker ID for Beatrice |
| 15 | + - Fixed errors when model file names are too long |
| 16 | + - Handled situation when monitor device is set to none. |
6 | 17 | - v2.0.45-alpha |
7 | 18 | - [HERE](https://github.com/w-okada/voice-changer/tree/v.2) |
8 | 19 | - bugfix |
9 | 20 | - volume control |
10 | | -- v2.0.44-alpha |
11 | | - - [HERE](https://github.com/w-okada/voice-changer/tree/v.2) |
12 | | - - bugfix |
13 | | - - Improvements for Unstable Behavior After Model Deletion |
14 | | -- v2.0.42-alpha |
15 | | - - [HERE](https://github.com/w-okada/voice-changer/tree/v.2) |
16 | | - - Feature |
17 | | - - Upload of Beatrice v2 custom model |
18 | | - - Improvement |
19 | | - - Improved RVC sound quality |
20 | | - - Enhanced RVC conversion speed |
21 | | - - Bugfix |
22 | | - - Pass-through |
23 | | - - Audio device reload |
24 | | -- v.2.0.40-alpha |
25 | | - - [HERE](https://github.com/w-okada/voice-changer/tree/v.2) |
26 | | - - Improvements |
27 | | - - Volume support |
28 | | - - ASIO support |
29 | | - - Web folder publishing |
30 | | - - You can extend language support by creating `web_front\assets\i18n\<lang>\translation.json` and adding it to `lang` in `web_front\assets\gui_settings\GUI.json`. |
31 | | -- v.2.0.32-alpha Colab version released. ⇒ [Here](./w_okada's_Voice_Changer_version_2_x.ipynb) |
32 | | - - ngrok is no longer needed. You can use it without a ngrok account. |
33 | | -- v.2.0.27-alpha -> [HERE](https://github.com/w-okada/voice-changer/tree/v.2) |
34 | | -- v.2.0.24-alpha Colab version released. ⇒ [Here](https://github.com/w-okada/voice-changer/tree/v.2/w_okada's_Voice_Changer_version_2_x.ipynb) |
35 | | - |
36 | | -- VCClient has rebooted as the second version. see [HERE](https://github.com/w-okada/voice-changer/tree/v.2) |
37 | | - - The Mac(Apple silicon) version has also been released. |
38 | | - |
39 | | -- v.1.5.3.18a |
40 | | - - Bugfix: FCPE |
41 | | - |
42 | | -- v.1.5.3.18 (removed.) |
43 | | - - New Feature: FCPE |
44 | | - - Easy-VC (experimental) |
45 | | -- v.1.5.3.17b |
46 | | - - bugfix: |
47 | | - - clear setting |
48 | | - - improve |
49 | | - - file sanitizer |
50 | | - - chage: |
51 | | - - default input chunk size: 192. |
52 | | - - decided by this chart.(https://rentry.co/VoiceChangerGuide#gpu-chart-for-known-working-chunkextra) |
53 | | - |
54 | | -- v.1.5.3.17a |
55 | | - - Bug Fixes: |
56 | | - - Server mode error |
57 | | - - RVC Model merger |
58 | | - - Misc |
59 | | - - Add RVC Sample Chihaya-Jinja (https://chihaya369.booth.pm/items/4701666) |
60 | | - |
61 | | -- v.1.5.3.17 |
62 | | - - New Features: |
63 | | - - Added similarity graph for Beatrice speaker selection |
64 | | - - Bug Fixes: |
65 | | - - Fixed crossfade issue with Beatrice speaker |
66 | | - |
67 | | -- v.1.5.3.16a |
68 | | - - Bug fix: |
69 | | - - Lazy load Beatrice. |
70 | | - |
71 | | - |
72 | | -- v.1.5.3.16 (Only for Windows, CPU dependent) |
73 | | - - New Feature: |
74 | | - - Beatrice is supported(experimental) |
75 | | - |
76 | | -- v.1.5.3.15 |
77 | | - - Improve: |
78 | | - - new rmvpe checkpoint for rvc (torch, onnx) |
79 | | - - Mac: upgrade torch version 2.1.0 |
80 | 21 |
|
81 | 22 |
|
82 | 23 | # What is VC Client |
|
87 | 28 | - [so-vits-svc](https://github.com/svc-develop-team/so-vits-svc) |
88 | 29 | - [RVC(Retrieval-based-Voice-Conversion)](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI) |
89 | 30 | - [DDSP-SVC](https://github.com/yxlllc/DDSP-SVC) |
90 | | -- [Beatrice JVS Corpus Edition](https://prj-beatrice.com/) * experimental, (***NOT MIT Licnsence*** see [readme](https://github.com/w-okada/voice-changer/blob/master/server/voice_changer/Beatrice/)) * Only for Windows, CPU dependent |
| 31 | +- [Beatrice JVS Corpus Edition](https://prj-beatrice.com/) * experimental, (***NOT MIT License*** see [readme](https://github.com/w-okada/voice-changer/blob/master/server/voice_changer/Beatrice/)) * Only for Windows, CPU dependent |
91 | 32 |
|
92 | 33 | 1. Distribute the load by running Voice Changer on a different PC |
93 | 34 | The real-time voice changer of this application works on a server-client configuration. By running the MMVC server on a separate PC, you can run it while minimizing the impact on other resource-intensive processes such as gaming commentary. |
|
0 commit comments