You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
[](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)
> The dataset for the pre-training model uses nearly 50 hours of high quality VCTK open source dataset.
28
31
29
-
> 底模使用接近50小时的开源高质量VCTK训练集训练，无版权方面的顾虑，请大家放心使用
32
+
> High quality licensed song datasets will be added to training-set one after another for your use, without worrying about copyright infringement.
30
33
31
-
> 请期待RVCv3的底模，参数更大，数据更大，效果更好，基本持平的推理速度，需要训练数据量更少。
34
+
> Please look forward to the pretrained base model of RVCv3, which has larger parameters, more training data, better results, unchanged inference speed, and requires less training data for training.
+ Reduce tone leakage by replacing the source feature to training-set feature using top1 retrieval;
39
+
+ Easy and fast training, even on relatively poor graphics cards;
40
+
+ Training with a small amount of data also obtains relatively good results (>=10min low noise speech recommended);
41
+
+ Supporting model fusion to change timbres (using ckpt processing tab->ckpt merge);
42
+
+ Easy-to-use Webui interface;
43
+
+ Use the UVR5 model to quickly separate vocals and instruments.
44
+
+ Use the most powerful High-pitch Voice Extraction Algorithm [InterSpeech2023-RMVPE](#Credits) to prevent the muted sound problem. Provides the best results (significantly) and is faster, with even lower resource consumption than Crepe_full.
#For Windows + Nvidia Ampere Architecture(RTX30xx), you need to specify the cuda version corresponding to pytorch according to the experience of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/21
for AMD/Intel graphics cards on Windows (DirectML)：
82
+
pip install -r requirements-dml.txt
73
83
74
-
A卡/I卡：
75
-
pip install -r requirements-dml.txt
84
+
for Intel ARC graphics cards on Linux / WSL using Python 3.10:
85
+
pip install -r requirements-ipex.txt
76
86
87
+
for AMD graphics cards on Linux (ROCm):
88
+
pip install -r requirements-amd.txt
77
89
```
78
90
79
91
------
80
-
Mac 用户可以通过 `run.sh` 来安装依赖：
92
+
Mac users can install dependencies via `run.sh`:
81
93
```bash
82
94
sh ./run.sh
83
95
```
84
96
85
-
## 其他预模型准备
86
-
RVC需要其他一些预模型来推理和训练。
97
+
## Preparation of other Pre-models
98
+
RVC requires other pre-models to infer and train.
87
99
88
-
你可以从我们的[Hugging Face space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)下载到这些模型。
100
+
You need to download them from our [Huggingface space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/).
89
101
90
-
以下是一份清单，包括了所有RVC所需的预模型和其他文件的名称:
102
+
Here's a list of Pre-models and other files that RVC needs:
91
103
```bash
92
104
./assets/hubert/hubert_base.pt
93
105
94
106
./assets/pretrained
95
107
96
108
./assets/uvr5_weights
97
109
98
-
想测试v2版本模型的话，需要额外下载
110
+
Additional downloads are required if you want to test the v2 version of the model.
99
111
100
112
./assets/pretrained_v2
101
113
102
-
如果你正在使用Windows，则你可能需要这个文件，若ffmpeg和ffprobe已安装则跳过; ubuntu/debian 用户可以通过apt install ffmpeg来安装这2个库, Mac 用户则可以通过brew install ffmpeg来安装 (需要预先安装brew)
114
+
If you want to test the v2 version model (the v2 version model has changed the input from the 256 dimensional feature of 9-layer Hubert+final_proj to the 768 dimensional feature of 12-layer Hubert, and has added 3 period discriminators), you will need to download additional features
115
+
116
+
./assets/pretrained_v2
103
117
104
-
./ffmpeg
118
+
#If you are using Windows, you may also need these two files, skip if FFmpeg and FFprobe are installed
If you want to use the latest SOTA RMVPE vocal pitch extraction algorithm, you need to download the RMVPE weights and place them in the RVC root directory
If you are using Windows or macOS, you can download and extract `RVC-beta.7z` to use RVC directly by using `go-web.bat` on windows or `sh ./run.sh` on macOS to start Webui.
145
+
146
+
## ROCm Support for AMD graphic cards (Linux only)
147
+
To use ROCm on Linux install all required drivers as described [here](https://rocm.docs.amd.com/en/latest/deploy/linux/os-native/install.html).
148
+
149
+
On Arch use pacman to install the driver:
150
+
````
151
+
pacman -S rocm-hip-sdk rocm-opencl-sdk
152
+
````
153
+
154
+
You might also need to set these environment variables (e.g. on a RX6700XT):
155
+
````
156
+
export ROCM_PATH=/opt/rocm
157
+
export HSA_OVERRIDE_GFX_VERSION=10.3.0
158
+
````
159
+
Also make sure your user is part of the `render` and `video` group:
0 commit comments