mirror of
https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI.git
synced 2026-06-06 17:50:25 +08:00
fix: no attribute 'FILE_LIKE'' & update instructions
This commit is contained in:
@@ -9,7 +9,7 @@
|
||||

|
||||
|
||||
[](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
|
||||
[](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
|
||||
[](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)
|
||||
|
||||
[](https://discord.gg/HcsmBBGyVk)
|
||||
|
||||
@@ -101,7 +101,7 @@ sh ./run.sh
|
||||
- 如果您希望跳过启动时的资源完整性检查,请添加`--nocheck`参数
|
||||
|
||||
#### 手动下载资源
|
||||
> 所有资源文件均位于[Hugging Face space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
|
||||
> 所有资源文件均位于[Hugging Face space](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)
|
||||
|
||||
> 你可以在`tools`文件夹找到下载它们的脚本
|
||||
|
||||
@@ -132,14 +132,14 @@ sh ./run.sh
|
||||
|
||||
如果你想使用最新的RMVPE人声音高提取算法,则你需要下载音高提取模型参数并放置于`assets/rmvpe`。
|
||||
|
||||
- 下载[rmvpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)
|
||||
- 下载[rmvpe.pt](https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.pt)
|
||||
```bash
|
||||
rvcmd assets/rmvpe # RVC-Models-Downloader command
|
||||
```
|
||||
|
||||
#### 下载 rmvpe 的 dml 环境(可选, A卡/I卡用户)
|
||||
|
||||
- 下载[rmvpe.onnx](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx)
|
||||
- 下载[rmvpe.onnx](https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.onnx)
|
||||
```bash
|
||||
rvcmd assets/rmvpe # RVC-Models-Downloader command
|
||||
```
|
||||
|
||||
@@ -35,34 +35,7 @@
|
||||
可先跑通WebUI,消息窗内会显示数据集处理和训练用命令行;
|
||||
|
||||
|
||||
推理脚本:
|
||||
|
||||
https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/myinfer.py
|
||||
|
||||
|
||||
例子:
|
||||
|
||||
|
||||
runtime\python.exe myinfer.py 0 "E:\codes\py39\RVC-beta\todo-songs\1111.wav" "E:\codes\py39\logs\mi-test\added_IVF677_Flat_nprobe_7.index" harvest "test.wav" "weights/mi-test.pth" 0.6 cuda:0 True
|
||||
|
||||
|
||||
f0up_key=sys.argv[1]
|
||||
|
||||
input_path=sys.argv[2]
|
||||
|
||||
index_path=sys.argv[3]
|
||||
|
||||
f0method=sys.argv[4]#harvest or pm
|
||||
|
||||
opt_path=sys.argv[5]
|
||||
|
||||
model_path=sys.argv[6]
|
||||
|
||||
index_rate=float(sys.argv[7])
|
||||
|
||||
device=sys.argv[8]
|
||||
|
||||
is_half=bool(sys.argv[9])
|
||||
推理脚本:tool/cmd/infer_cli.py
|
||||
|
||||
|
||||
## Q7:Cuda error/Cuda out of memory.
|
||||
|
||||
Reference in New Issue
Block a user