Commit
•
9ad5775
1
Parent(s):
7437edf
update README
Browse files- README.assets/tmp8ouz9kdr.mp3 +0 -0
- README.assets/tmp8ouz9kdr.wav +0 -0
- README.assets/tmpb34bl0o0.mp3 +0 -0
- README.assets/tmpb34bl0o0.wav +0 -0
- README.assets/tmpmqxkbbgm.mp3 +0 -0
- README.assets/tmpmqxkbbgm.wav +0 -0
- README.assets/tmpo1ftlmcz.mp3 +0 -0
- README.assets/tmpo1ftlmcz.wav +0 -0
- README.md +6 -4
README.assets/tmp8ouz9kdr.mp3
ADDED
Binary file (38.6 kB). View file
|
|
README.assets/tmp8ouz9kdr.wav
DELETED
Binary file (191 kB)
|
|
README.assets/tmpb34bl0o0.mp3
ADDED
Binary file (77.6 kB). View file
|
|
README.assets/tmpb34bl0o0.wav
DELETED
Binary file (398 kB)
|
|
README.assets/tmpmqxkbbgm.mp3
ADDED
Binary file (36 kB). View file
|
|
README.assets/tmpmqxkbbgm.wav
DELETED
Binary file (188 kB)
|
|
README.assets/tmpo1ftlmcz.mp3
ADDED
Binary file (111 kB). View file
|
|
README.assets/tmpo1ftlmcz.wav
DELETED
Binary file (598 kB)
|
|
README.md
CHANGED
@@ -30,24 +30,25 @@ tags:
|
|
30 |
|
31 |
<center>
|
32 |
<audio controls>
|
33 |
-
<source src="./README.assets/tmpb34bl0o0.
|
34 |
</audio>
|
35 |
<p>いいんじゃない。最近、一緒に歌ってる人の声に合わせられるようになってきたし</p>
|
36 |
<audio controls>
|
37 |
-
<source src="./README.assets/tmpmqxkbbgm.
|
38 |
</audio>
|
39 |
<p>ざーーこ、お兄ちゃんざーーこ!(杂鱼~哥哥是杂鱼❤)</p>
|
40 |
<audio controls>
|
41 |
-
<source src="./README.assets/tmpo1ftlmcz.
|
42 |
</audio>
|
43 |
<p>大家好,我是宁宁。我中文还不是很熟练,但是希望大家能喜欢我的声音,喵喵喵!</p>
|
44 |
<audio controls>
|
45 |
-
<source src="./README.assets/tmp8ouz9kdr.
|
46 |
</audio>
|
47 |
<p>The sun is shining brightly in the clear blue sky.</p>
|
48 |
</center>
|
49 |
|
50 |
|
|
|
51 |
可以默认选择 **nene30_e8_s328.pth**,经测试大部分情况下 nene30_e8_s328.pth > nene60_2_e4_s336.pth = nene60_test_e8_s280.pth > nene60_1_e8_s640.pth = nene60_2_e2_s168.pth,但在不同的情况下其他模型可能表现较好,在默认情况下表现不佳时可以切换模型 / 切换参考音频尝试
|
52 |
|
53 |
| SoVITS 模型 | 介绍 | 对应 GPT 模型 |
|
@@ -81,3 +82,4 @@ tags:
|
|
81 |
* [数据集](https://huggingface.co/datasets/MomoyamaSawa/Voice-KusanagiNene)
|
82 |
|
83 |
* [训练相关代码](https://github.com/MomoyamaSawa/GPT_SoVITS_Colab)
|
|
|
|
30 |
|
31 |
<center>
|
32 |
<audio controls>
|
33 |
+
<source src="./README.assets/tmpb34bl0o0.mp3" type="audio/mpeg">
|
34 |
</audio>
|
35 |
<p>いいんじゃない。最近、一緒に歌ってる人の声に合わせられるようになってきたし</p>
|
36 |
<audio controls>
|
37 |
+
<source src="./README.assets/tmpmqxkbbgm.mp3" type="audio/mpeg">
|
38 |
</audio>
|
39 |
<p>ざーーこ、お兄ちゃんざーーこ!(杂鱼~哥哥是杂鱼❤)</p>
|
40 |
<audio controls>
|
41 |
+
<source src="./README.assets/tmpo1ftlmcz.mp3" type="audio/mpeg">
|
42 |
</audio>
|
43 |
<p>大家好,我是宁宁。我中文还不是很熟练,但是希望大家能喜欢我的声音,喵喵喵!</p>
|
44 |
<audio controls>
|
45 |
+
<source src="./README.assets/tmp8ouz9kdr.mp3" type="audio/mpeg">
|
46 |
</audio>
|
47 |
<p>The sun is shining brightly in the clear blue sky.</p>
|
48 |
</center>
|
49 |
|
50 |
|
51 |
+
|
52 |
可以默认选择 **nene30_e8_s328.pth**,经测试大部分情况下 nene30_e8_s328.pth > nene60_2_e4_s336.pth = nene60_test_e8_s280.pth > nene60_1_e8_s640.pth = nene60_2_e2_s168.pth,但在不同的情况下其他模型可能表现较好,在默认情况下表现不佳时可以切换模型 / 切换参考音频尝试
|
53 |
|
54 |
| SoVITS 模型 | 介绍 | 对应 GPT 模型 |
|
|
|
82 |
* [数据集](https://huggingface.co/datasets/MomoyamaSawa/Voice-KusanagiNene)
|
83 |
|
84 |
* [训练相关代码](https://github.com/MomoyamaSawa/GPT_SoVITS_Colab)
|
85 |
+
|