Cool_Tools/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of synced 2024-11-24 07:30:16 +01:00
Code Releases Wiki Activity

Update Changelog_CN.md

Browse Source
This commit is contained in:
RVC-Boss 2023-06-13 16:22:17 +08:00 committed by GitHub
parent 78c88a4f75
commit c74727d487
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
Changelog_CN.md
View File

@ -8,11 +8,11 @@
- 废弃32k模型的训练
todolist：
- 特征检索增加时序维度
- ~~特征检索增加时序维度：寄，没啥效果~~
- 特征检索增加pre-kmeans可选项
- 特征检索增加PCAR降维可选项
- 支持onnx推理（附带仅推理的小压缩包）
- 训练时在音高、gender、eq、噪声等方面对输入进行随机增强
- ~~特征检索增加PCAR降维可选项：寄，数据大用kmeans缩小数据量，数据小降维操作耗时比省下的匹配耗时还多~~
- ~~支持onnx推理（附带仅推理的小压缩包）：寄，生成nsf还是需要pytorch~~
- ~~训练时在音高、gender、eq、噪声等方面对输入进行随机增强：寄，没啥效果~~
- 补全v2版本的48k预训练模型