fix: no attribute 'FILE_LIKE'' & update instructions

2026-06-05 01:10:22 +08:00 · 2025-06-19 17:25:21 +09:00
parent b88cc1e8fe
commit 6223116f6b
30 changed files with 106 additions and 587 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -2,7 +2,7 @@
 __pycache__
 /TEMP
 *.pyd
-.venv
+.venv*
 .vscode
 .idea
 xcuserdata
--- a/16
+++ b/16
@@ -30,17 +30,17 @@ COPY . .
 RUN python3 -m pip install --upgrade pip>=24.0
 RUN python3 -m pip install --no-cache-dir -r requirements/main.txt

-RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D40k.pth -d assets/pretrained_v2/ -o D40k.pth
-RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G40k.pth -d assets/pretrained_v2/ -o G40k.pth
-RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D40k.pth -d assets/pretrained_v2/ -o f0D40k.pth
-RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G40k.pth -d assets/pretrained_v2/ -o f0G40k.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/fumiama/RVC-Pretrained-Models/resolve/main/pretrained_v2/D40k.pth -d assets/pretrained_v2/ -o D40k.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/fumiama/RVC-Pretrained-Models/resolve/main/pretrained_v2/G40k.pth -d assets/pretrained_v2/ -o G40k.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/fumiama/RVC-Pretrained-Models/resolve/main/pretrained_v2/f0D40k.pth -d assets/pretrained_v2/ -o f0D40k.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/fumiama/RVC-Pretrained-Models/resolve/main/pretrained_v2/f0G40k.pth -d assets/pretrained_v2/ -o f0G40k.pth

-RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d assets/uvr5_weights/ -o HP2-人声vocals+非人声instrumentals.pth
-RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d assets/uvr5_weights/ -o HP5-主旋律人声vocals+其他instrumentals.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/fumiama/RVC-Pretrained-Models/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d assets/uvr5_weights/ -o HP2-人声vocals+非人声instrumentals.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/fumiama/RVC-Pretrained-Models/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d assets/uvr5_weights/ -o HP5-主旋律人声vocals+其他instrumentals.pth

-RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d assets/hubert -o hubert_base.pt
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/fumiama/RVC-Pretrained-Models/resolve/main/hubert/hubert_base.pt -d assets/hubert -o hubert_base.pt

-RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -d assets/rmvpe -o rmvpe.pt
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/fumiama/RVC-Pretrained-Models/resolve/main/rmvpe/rmvpe.pt -d assets/rmvpe -o rmvpe.pt

 VOLUME [ "/app/weights", "/app/opt" ]

--- a/README.md
+++ b/README.md
@@ -11,7 +11,7 @@ An easy-to-use voice conversion framework based on VITS.
 ![moe](https://counter.seku.su/cmoe?name=rvc&theme=r34)

 [![Licence](https://img.shields.io/github/license/fumiama/Retrieval-based-Voice-Conversion-WebUI?style=for-the-badge)](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
-[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)

 [![Discord](https://img.shields.io/badge/RVC%20Developers-Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/HcsmBBGyVk)

@@ -55,7 +55,7 @@ Check out our [Demo Video](https://www.bilibili.com/video/BV1pm4y1z7Gm/) here!
 > For the reason of the version limitation, please refer to this [bug](https://github.com/facebookresearch/fairseq/issues/5012).

 ```bash
-python --version # 3.8 <= Python < 3.11
+python --version # Recommend: 3.11
 ```

 ### Linux/MacOS One-click Dependency Installation & Startup Script
@@ -66,20 +66,35 @@ sh ./run.sh

 ### Manual Installation of Dependencies
 1. Install `pytorch` and its core dependencies, skip if already installed. Refer to: https://pytorch.org/get-started/locally/
+- General
 	```bash
 	pip install torch torchvision torchaudio
 	```
-2. If you are using Nvidia Ampere architecture (RTX30xx) in Windows, according to the experience of #21, you need to specify the cuda version corresponding to pytorch.
+- Nvidia GPU
+	Remember to specify the CUDA version that is the same as your platform, like
+	```bash
+	pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
+	```
+	If you are using Nvidia Ampere architecture (RTX30xx) in Windows, according to the experience of #21, you need to specify the cuda version corresponding to pytorch.
 	```bash
 	pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117
 	```
+- AMD ROCM (Linux)
+	If you are using an ROCM-capable AMD Radeon GPU, then you need to choose ROCM version of PyTorch.
+	```bash
+	pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.2
+	```
+- AMD/Intel GPU (DML)
+	```bash
+	pip install torch_directml torchvision torchaudio
+	```

-3. Install the corresponding dependencies according to your own graphics card.
+2. Install the corresponding dependencies according to your own graphics card.
 - Nvidia GPU
 	```bash
 	pip install -r requirements/main.txt
 	```
- AMD/Intel GPU
+- AMD/Intel GPU (DML)
 	```bash
 	pip install -r requirements/dml.txt
 	```
@@ -92,11 +107,6 @@ sh ./run.sh
 	pip install -r requirements/ipex.txt
 	```

-4.If you are using an ROCM-capable AMD Radeon GPU, then you need to choose ROCM version of PyTorch.
-	```bash
-	pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.2
-	```
-
 ## Preparation of Other Files
 ### 1. Assets
 > RVC requires some models located in the `assets` folder for inference and training.
@@ -109,7 +119,7 @@ sh ./run.sh
 - If you want to skip the resource integrity check at startup, please add the `--nocheck` parameter.

 #### Download Manually
-> All resource files are located in [Hugging Face space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+> All resource files are located in [Hugging Face space](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)

 > You can find some scripts to download them in the `tools` folder

@@ -140,14 +150,14 @@ If you want to use the v2 version of the model, you need to download additional

 If you want to use the latest RMVPE vocal pitch extraction algorithm, you need to download the pitch extraction model parameters and place them in `assets/rmvpe`.

- [rmvpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)
+- [rmvpe.pt](https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.pt)
 	```bash
 	rvcmd assets/rmvpe # RVC-Models-Downloader command
 	```

 #### Download DML environment of RMVPE (optional, for AMD/Intel GPU)

- [rmvpe.onnx](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx)
+- [rmvpe.onnx](https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.onnx)
 	```bash
 	rvcmd assets/rmvpe # RVC-Models-Downloader command
 	```
--- a/docs/cn/README.cn.md
+++ b/docs/cn/README.cn.md
@@ -9,7 +9,7 @@
 ![moe](https://counter.seku.su/cmoe?name=rvc&theme=r34)

 [![Licence](https://img.shields.io/github/license/fumiama/Retrieval-based-Voice-Conversion-WebUI?style=for-the-badge)](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
-[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)

 [![Discord](https://img.shields.io/badge/RVC%20Developers-Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](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
 	```
--- a/docs/cn/faq.md
+++ b/docs/cn/faq.md
@@ -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.
--- a/docs/en/README.en.md
+++ b/docs/en/README.en.md
@@ -1,221 +0,0 @@
-<div align="center">
-
-<h1>Retrieval-based-Voice-Conversion-WebUI</h1>
-An easy-to-use Voice Conversion framework based on VITS.<br><br>
-
-[![madewithlove](https://img.shields.io/badge/made_with-%E2%9D%A4-red?style=for-the-badge&labelColor=orange
-)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)
-
-<img src="https://counter.seku.su/cmoe?name=rvc&theme=r34" /><br>
-  
-[![Open In Colab](https://img.shields.io/badge/Colab-F9AB00?style=for-the-badge&logo=googlecolab&color=525252)](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)
-[![Licence](https://img.shields.io/github/license/RVC-Project/Retrieval-based-Voice-Conversion-WebUI?style=for-the-badge)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
-[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
-
-[![Discord](https://img.shields.io/badge/RVC%20Developers-Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/HcsmBBGyVk)
-
-[**Changelog**](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/docs/Changelog_EN.md) | [**FAQ (Frequently Asked Questions)**](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/wiki/FAQ-(Frequently-Asked-Questions)) 
-
-[**English**](../en/README.en.md) | [**中文简体**](../../README.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Français**](../fr/README.fr.md) | [**Türkçe**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)
-
-</div>
-
-> Check out our [Demo Video](https://www.bilibili.com/video/BV1pm4y1z7Gm/) here!
-
-<table>
-   <tr>
-		<td align="center">Training and inference Webui</td>
-		<td align="center">Real-time voice changing GUI</td>
-	</tr>
-  <tr>
-		<td align="center"><img src="https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/assets/129054828/092e5c12-0d49-4168-a590-0b0ef6a4f630"></td>
-    <td align="center"><img src="https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/assets/129054828/730b4114-8805-44a1-ab1a-04668f3c30a6"></td>
-	</tr>
-	<tr>
-		<td align="center">go-web.bat</td>
-		<td align="center">go-realtime-gui.bat</td>
-	</tr>
-  <tr>
-    <td align="center">You can freely choose the action you want to perform.</td>
-		<td align="center">We have achieved an end-to-end latency of 170ms. With the use of ASIO input and output devices, we have managed to achieve an end-to-end latency of 90ms, but it is highly dependent on hardware driver support.</td>
-	</tr>
-</table>
-
-> The dataset for the pre-training model uses nearly 50 hours of high quality audio from the VCTK open source dataset.
-
-> High quality licensed song datasets will be added to the training-set often for your use, without having to worry about copyright infringement.
-
-> 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.
-
-## Features:
-+ Reduce tone leakage by replacing the source feature to training-set feature using top1 retrieval;
-+ Easy + fast training, even on poor graphics cards;
-+ Training with a small amounts of data (>=10min low noise speech recommended);
-+ Model fusion to change timbres (using ckpt processing tab->ckpt merge);
-+ Easy-to-use WebUI;
-+ UVR5 model to quickly separate vocals and instruments;
-+ High-pitch Voice Extraction Algorithm [InterSpeech2023-RMVPE](#Credits) to prevent a muted sound problem. Provides the best results (significantly) and is faster with lower resource consumption than Crepe_full;
-+ AMD/Intel graphics cards acceleration supported;
-+ Intel ARC graphics cards acceleration with IPEX supported.
-
-## Preparing the environment
-The following commands need to be executed with Python 3.8 or higher.
-
-(Windows/Linux)
-First install the main dependencies through pip:
-```bash
-# Install PyTorch-related core dependencies, skip if installed
-# Reference: https://pytorch.org/get-started/locally/
-pip install torch torchvision torchaudio
-
-#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
-#pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117
-
-#For Linux + AMD Cards, you need to use the following pytorch versions:
-#pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.2
-```
-
-Then can use poetry to install the other dependencies:
-```bash
-# Install the Poetry dependency management tool, skip if installed
-# Reference: https://python-poetry.org/docs/#installation
-curl -sSL https://install.python-poetry.org | python3 -
-
-# Install the project dependencies
-poetry install
-```
-
-You can also use pip to install them:
-```bash
-
-for Nvidia graphics cards
-  pip install -r requirements.txt
-
-for AMD/Intel graphics cards on Windows (DirectML)：
-  pip install -r requirements-dml.txt
-
-for Intel ARC graphics cards on Linux / WSL using Python 3.10: 
-  pip install -r requirements-ipex.txt
-
-for AMD graphics cards on Linux (ROCm):
-  pip install -r requirements-amd.txt
-```
-
------
-Mac users can install dependencies via `run.sh`:
-```bash
-sh ./run.sh
-```
-
-## Preparation of other Pre-models
-RVC requires other pre-models to infer and train.
-
-```bash
-#Download all needed models from https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/
-python tools/download_models.py
-```
-
-Or just download them by yourself from our [Huggingface space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/).
-
-Here's a list of Pre-models and other files that RVC needs:
-```bash
-./assets/hubert/hubert_base.pt
-
-./assets/pretrained 
-
-./assets/uvr5_weights
-
-Additional downloads are required if you want to test the v2 version of the model.
-
-./assets/pretrained_v2
-
-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
-
-./assets/pretrained_v2
-
-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
-
-https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt
-
-    For AMD/Intel graphics cards users you need download:
-
-    https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx
-
-```
-
-### 2. Install FFmpeg
-If you have FFmpeg and FFprobe installed on your computer, you can skip this step.
-
-#### For Ubuntu/Debian users
-```bash
-sudo apt install ffmpeg
-```
-#### For MacOS users
-```bash
-brew install ffmpeg
-```
-#### For Windows users
-Download these files and place them in the root folder:
- [ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe)
-
- [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe)
-
-## ROCm Support for AMD graphic cards (Linux only)
-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).
-
-On Arch use pacman to install the driver:
-````
-pacman -S rocm-hip-sdk rocm-opencl-sdk
-````
-
-You might also need to set these environment variables (e.g. on a RX6700XT):
-````
-export ROCM_PATH=/opt/rocm #Set ROCM Executables Path
-export HSA_OVERRIDE_GFX_VERSION=10.3.0 #Spoof GPU Model for ROCM
-````
-
-And overwrite PyTorch with its ROCM version after installing dependencies.
-````
-pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.2
-````
-
-Make sure your user is part of the `render` and `video` group:
-````
-sudo usermod -aG render $USERNAME
-sudo usermod -aG video $USERNAME
-````
-
-## Get started
-### start up directly
-Use the following command to start WebUI:
-```bash
-python infer-web.py
-```
-### Use the integration package
-Download and extract file `RVC-beta.7z`, then follow the steps below according to your system:
-#### For Windows users
-Double click `go-web.bat`
-#### For MacOS users
-```bash
-sh ./run.sh
-```
-### For Intel IPEX users (Linux Only)
-```bash
-source /opt/intel/oneapi/setvars.sh
-```
-## Credits
-+ [ContentVec](https://github.com/auspicious3000/contentvec/)
-+ [VITS](https://github.com/jaywalnut310/vits)
-+ [HIFIGAN](https://github.com/jik876/hifi-gan)
-+ [Gradio](https://github.com/gradio-app/gradio)
-+ [FFmpeg](https://github.com/FFmpeg/FFmpeg)
-+ [Ultimate Vocal Remover](https://github.com/Anjok07/ultimatevocalremovergui)
-+ [audio-slicer](https://github.com/openvpi/audio-slicer)
-+ [Vocal pitch extraction:RMVPE](https://github.com/Dream-High/RMVPE)
-  + The pretrained model is trained and tested by [yxlllc](https://github.com/yxlllc/RMVPE) and [RVC-Boss](https://github.com/RVC-Boss).
-  
-## Thanks to all contributors for their efforts
-<a href="https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/graphs/contributors" target="_blank">
-  <img src="https://contrib.rocks/image?repo=RVC-Project/Retrieval-based-Voice-Conversion-WebUI" />
-</a>
-
--- a/docs/en/faq_en.md
+++ b/docs/en/faq_en.md
@@ -23,24 +23,7 @@ Please disable system LAN proxy/global proxy and then refresh.<br>
 Training script:<br>
 You can run training in WebUI first, and the command-line versions of dataset preprocessing and training will be displayed in the message window.<br>

-Inference script:<br>
-https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/myinfer.py<br>
-
-
-e.g.<br>
-
-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<br>
-
-
-f0up_key=sys.argv[1]<br>
-input_path=sys.argv[2]<br>
-index_path=sys.argv[3]<br>
-f0method=sys.argv[4]#harvest or pm<br>
-opt_path=sys.argv[5]<br>
-model_path=sys.argv[6]<br>
-index_rate=float(sys.argv[7])<br>
-device=sys.argv[8]<br>
-is_half=bool(sys.argv[9])<br>
+Inference script: tool/cmd/infer_cli.py

 ## Q7:Cuda error/Cuda out of memory.
 There is a small chance that there is a problem with the CUDA configuration or the device is not supported; more likely, there is not enough memory (out of memory).<br>
--- a/docs/fr/README.fr.md
+++ b/docs/fr/README.fr.md
@@ -11,7 +11,7 @@ Un framework simple et facile à utiliser pour la conversion vocale (modificateu
 ![moe](https://counter.seku.su/cmoe?name=rvc&theme=r34)

 [![Licence](https://img.shields.io/github/license/fumiama/Retrieval-based-Voice-Conversion-WebUI?style=for-the-badge)](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
-[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)

 [![Discord](https://img.shields.io/badge/RVC%20Developers-Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/HcsmBBGyVk)

@@ -21,7 +21,7 @@ Un framework simple et facile à utiliser pour la conversion vocale (modificateu

 ------

-[**English**](../en/README.en.md) | [ **中文简体**](../../README.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Français**](../fr/README.fr.md) | [**Turc**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)
+[**English**](../../README.md) | [ **中文简体**](../cn/README.cn.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Français**](../fr/README.fr.md) | [**Turc**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)

 Cliquez ici pour voir notre [vidéo de démonstration](https://www.bilibili.com/video/BV1pm4y1z7Gm/) !

@@ -94,11 +94,10 @@ sh ./run.sh
 RVC nécessite d'autres modèles pré-entraînés pour l'inférence et la formation.

 ```bash
-#Télécharger tous les modèles depuis https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/
 python tools/download_models.py
 ```

-Ou vous pouvez télécharger ces modèles depuis notre [espace Hugging Face](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/).
+Ou vous pouvez télécharger ces modèles depuis notre [espace Hugging Face](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/).

 Voici une liste des modèles et autres fichiers requis par RVC :
 ```bash
@@ -114,11 +113,11 @@ Voici une liste des modèles et autres fichiers requis par RVC :

 # Si vous souhaitez utiliser le dernier algorithme RMVPE de pitch vocal, téléchargez les paramètres du modèle de pitch et placez-les dans le répertoire racine de RVC.

-https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt
+https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.pt

    # Les utilisateurs de cartes AMD/Intel nécessitant l'environnement DML doivent télécharger :

-    https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx
+    https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.onnx

 ```
 Pour les utilisateurs d'Intel ARC avec IPEX, exécutez d'abord `source /opt/intel/oneapi/setvars.sh`.
--- a/docs/fr/faq_fr.md
+++ b/docs/fr/faq_fr.md
@@ -23,22 +23,7 @@ Veuillez désactiver le proxy système LAN/proxy global puis rafraîchir.<br>
 Script d'entraînement :<br>
 Vous pouvez d'abord lancer l'entraînement dans WebUI, et les versions en ligne de commande de la préparation du jeu de données et de l'entraînement seront affichées dans la fenêtre de message.<br>

-Script d'inférence :<br>
-https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/myinfer.py<br>
-
-Par exemple :<br>
-
-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" récolte "test.wav" "weights/mi-test.pth" 0.6 cuda:0 True<br>
-
-f0up_key=sys.argv[1]<br>
-input_path=sys.argv[2]<br>
-index_path=sys.argv[3]<br>
-f0method=sys.argv[4]#récolte ou pm<br>
-opt_path=sys.argv[5]<br>
-model_path=sys.argv[6]<br>
-index_rate=float(sys.argv[7])<br>
-device=sys.argv[8]<br>
-is_half=bool(sys.argv[9])<br>
+Script d'inférence : tool/cmd/infer_cli.py

 ### Explication des arguments :

--- a/docs/jp/README.ja.md
+++ b/docs/jp/README.ja.md
@@ -10,13 +10,13 @@ VITSに基づく使いやすい音声変換（voice changer）framework
 ![moe](https://counter.seku.su/cmoe?name=rvc&theme=r34)

 [![Licence](https://img.shields.io/github/license/fumiama/Retrieval-based-Voice-Conversion-WebUI?style=for-the-badge)](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
-[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)

 [![Discord](https://img.shields.io/badge/RVC%20Developers-Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/HcsmBBGyVk)

 [**よくある質問**](./faq_ja.md) | [**AutoDLで推論(中国語のみ)**](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/wiki/Autodl%E8%AE%AD%E7%BB%83RVC%C2%B7AI%E6%AD%8C%E6%89%8B%E6%95%99%E7%A8%8B) | [**対照実験記録**](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/wiki/%E5%AF%B9%E7%85%A7%E5%AE%9E%E9%AA%8C%C2%B7%E5%AE%9E%E9%AA%8C%E8%AE%B0%E5%BD%95) | [**オンラインデモ(中国語のみ)**](https://modelscope.cn/studios/FlowerCry/RVCv2demo)

-[**English**](../en/README.en.md) | [**中文简体**](../../README.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Français**](../fr/README.fr.md) | [**Türkçe**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)
+[**English**](../../README.md) | [**中文简体**](../cn/README.cn.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Français**](../fr/README.fr.md) | [**Türkçe**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)

 </div>

@@ -105,7 +105,7 @@ sh ./run.sh
 - 起動時のリソース完全性チェックを不要の場合は、`--nocheck`パラメータを追加してください。

 #### リソースのマニュアルダウンロード
-> すべてのリソースファイルは[Hugging Face space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)にあります。
+> すべてのリソースファイルは[Hugging Face space](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)にあります。

 > `tools`フォルダでそれらをダウンロードするスクリプトを見つけることができます。

@@ -136,14 +136,14 @@ v2バージョンのモデルを使用したい場合は、追加ダウンロー

 最新のRMVPE人声音高抽出アルゴリズムを使用したい場合は、音高抽出モデルをダウンロードし、`assets/rmvpe`に配置する必要があります。

- [rmvpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)
+- [rmvpe.pt](https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.pt)
 	```bash
 	rvcmd assets/rmvpe # RVC-Models-Downloader command
 	```

 #### RMVPE(dml環境)のダウンロード（オプション、AMD/Intel GPU ユーザー）

- [rmvpe.onnx](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx)
+- [rmvpe.onnx](https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.onnx)
 	```bash
 	rvcmd assets/rmvpe # RVC-Models-Downloader command
 	```
--- a/docs/jp/faq_ja.md
+++ b/docs/jp/faq_ja.md
@@ -29,22 +29,7 @@ rvc_root/logs/実験名の下に保存されている pth は、推論に使用
 トレーニングスクリプト：<br>
 まず WebUI を実行し、メッセージウィンドウにデータセット処理とトレーニング用のコマンドラインが表示されます。<br>

-推論スクリプト：<br>
-https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/myinfer.py<br>
-
-例：<br>
-
-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<br>
-
-f0up_key=sys.argv[1]<br>
-input_path=sys.argv[2]<br>
-index_path=sys.argv[3]<br>
-f0method=sys.argv[4]#harvest or pm<br>
-opt_path=sys.argv[5]<br>
-model_path=sys.argv[6]<br>
-index_rate=float(sys.argv[7])<br>
-device=sys.argv[8]<br>
-is_half=bool(sys.argv[9])<br>
+推論スクリプト：tool/cmd/infer_cli.py

 ## Q7: Cuda error/Cuda out of memory

--- a/docs/kr/README.ko.han.md
+++ b/docs/kr/README.ko.han.md
@@ -11,7 +11,7 @@ VITS基盤의 簡單하고使用하기 쉬운音聲變換틀
 ![moe](https://counter.seku.su/cmoe?name=rvc&theme=r34)

 [![Licence](https://img.shields.io/github/license/fumiama/Retrieval-based-Voice-Conversion-WebUI?style=for-the-badge)](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
-[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)

 [![Discord](https://img.shields.io/badge/RVC%20Developers-Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/HcsmBBGyVk)

@@ -19,7 +19,7 @@ VITS基盤의 簡單하고使用하기 쉬운音聲變換틀

 ------

-[**English**](../en/README.en.md) | [**中文简体**](../../README.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Français**](../fr/README.fr.md) | [**Türkçe**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)
+[**English**](../../README.md) | [**中文简体**](../cn/README.cn.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Français**](../fr/README.fr.md) | [**Türkçe**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)

 > [示範映像](https://www.bilibili.com/video/BV1pm4y1z7Gm/)을 確認해 보세요!

@@ -66,7 +66,7 @@ pip install -r requirements/main.txt
 ## 其他預備모델準備
 RVC 모델은 推論과訓練을 依하여 다른 預備모델이 必要합니다.

-[Huggingface space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)를 通해서 다운로드 할 수 있습니다.
+[Huggingface space](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)를 通해서 다운로드 할 수 있습니다.

 다음은 RVC에 必要한 預備모델 및 其他 파일 目錄입니다:
 ```bash
--- a/docs/kr/README.ko.md
+++ b/docs/kr/README.ko.md
@@ -8,13 +8,13 @@ VITS 기반의 간단하고 사용하기 쉬운 음성 변환 프레임워크.
 ![moe](https://counter.seku.su/cmoe?name=rvc&theme=r34)

 [![Licence](https://img.shields.io/github/license/fumiama/Retrieval-based-Voice-Conversion-WebUI?style=for-the-badge)](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
-[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)

 [![Discord](https://img.shields.io/badge/RVC%20Developers-Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/HcsmBBGyVk)

 [**자주 묻는 질문**](./faq_ko.md) | [**AutoDL·5원으로 AI 가수 훈련**](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/wiki/Autodl%E8%AE%AD%E7%BB%83RVC%C2%B7AI%E6%AD%8C%E6%89%8B%E6%95%99%E7%A8%8B) | [**대조 실험 기록**](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/wiki/%E5%AF%B9%E7%85%A7%E5%AE%9E%E9%AA%8C%C2%B7%E5%AE%9E%E9%AA%8C%E8%AE%B0%E5%BD%95) | [**온라인 데모**](https://modelscope.cn/studios/FlowerCry/RVCv2demo)

-[**English**](../en/README.en.md) | [**中文简体**](../../README.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Français**](../fr/README.fr.md) | [**Türkçe**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)
+[**English**](../../README.md) | [**中文简体**](../cn/README.cn.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Français**](../fr/README.fr.md) | [**Türkçe**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)

 </div>

@@ -117,119 +117,6 @@ poetry install
 sh ./run.sh
 ```

-<!--
-
-## 其他资源准备
-### 1. assets
-> RVC需要位于`assets`文件夹下的一些模型资源进行推理和训练。
-#### 自动检查/下载资源(默认)
-> 默认情况下，RVC可在主程序启动时自动检查所需资源的完整性。
-
-> 即使资源不完整，程序也将继续启动。
-
- 如果您希望下载所有资源，请添加`--update`参数
- 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/)
-
-> 你可以在`tools`文件夹找到下载它们的脚本
-
-> 你也可以使用模型/整合包/工具的一键下载器：[RVC-Models-Downloader](https://github.com/fumiama/RVC-Models-Downloader)
-
-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。
-
- ./assets/hubert/hubert_base.pt
-	```bash
-	rvcmd assets/hubert # RVC-Models-Downloader command
-	```
- ./assets/pretrained
-	```bash
-	rvcmd assets/v1 # RVC-Models-Downloader command
-	```
- ./assets/uvr5_weights
-	```bash
-	rvcmd assets/uvr5 # RVC-Models-Downloader command
-	```
-想使用v2版本模型的话，需要额外下载
-
- ./assets/pretrained_v2
-	```bash
-	rvcmd assets/v2 # RVC-Models-Downloader command
-	```
-
-### 3. 下载 rmvpe 人声音高提取算法所需文件
-
-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)
-	```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)
-	```bash
-	rvcmd assets/rmvpe # RVC-Models-Downloader command
-	```
-
-### 4. AMD显卡Rocm(可选, 仅Linux)
-
-如果你想基于AMD的Rocm技术在Linux系统上运行RVC，请先在[这里](https://rocm.docs.amd.com/en/latest/deploy/linux/os-native/install.html)安装所需的驱动。
-
-若你使用的是Arch Linux，可以使用pacman来安装所需驱动：
-````
-pacman -S rocm-hip-sdk rocm-opencl-sdk
-````
-对于某些型号的显卡，你可能需要额外配置如下的环境变量（如：RX6700XT）：
-````
-export ROCM_PATH=/opt/rocm
-export HSA_OVERRIDE_GFX_VERSION=10.3.0
-````
-同时确保你的当前用户处于`render`与`video`用户组内：
-````
-sudo usermod -aG render $USERNAME
-sudo usermod -aG video $USERNAME
-````
-
-## 开始使用
-### 直接启动
-使用以下指令来启动 WebUI
-```bash
-python web.py
-```
-### Linux/MacOS 用户
-```bash
-./run.sh
-```
-### 对于需要使用IPEX技术的I卡用户(仅Linux)
-```bash
-source /opt/intel/oneapi/setvars.sh
-./run.sh
-```
-### 使用整合包 (Windows 用户)
-下载并解压`RVC-beta.7z`，解压后双击`go-web.bat`即可一键启动。
-```bash
-rvcmd packs/general/latest # RVC-Models-Downloader command
-```
-
-## 参考项目
-+ [ContentVec](https://github.com/auspicious3000/contentvec/)
-+ [VITS](https://github.com/jaywalnut310/vits)
-+ [HIFIGAN](https://github.com/jik876/hifi-gan)
-+ [Gradio](https://github.com/gradio-app/gradio)
-+ [Ultimate Vocal Remover](https://github.com/Anjok07/ultimatevocalremovergui)
-+ [audio-slicer](https://github.com/openvpi/audio-slicer)
-+ [Vocal pitch extraction:RMVPE](https://github.com/Dream-High/RMVPE)
-  + The pretrained model is trained and tested by [yxlllc](https://github.com/yxlllc/RMVPE) and [RVC-Boss](https://github.com/RVC-Boss).
-
-## 感谢所有贡献者作出的努力
-[![contributors](https://contrib.rocks/image?repo=fumiama/Retrieval-based-Voice-Conversion-WebUI)](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/graphs/contributors)
-
-translate to Korean
-->
-
 ## 기타 사전 훈련된 모델 준비

 ### assets
@@ -247,7 +134,7 @@ translate to Korean

 #### 리소스 수동 다운로드

-> 모든 리소스 파일은 [Hugging Face space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)에 있습니다.
+> 모든 리소스 파일은 [Hugging Face space](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)에 있습니다.

 > 이들을 다운로드하는 스크립트는 `tools` 폴더에서 찾을 수 있습니다.

@@ -283,11 +170,11 @@ v2 버전 모델을 사용하려면 추가로 다음을 다운로드해야 합

 최신 RMVPE 인간 음성 피치 추출 알고리즘을 사용하려면 음피치 추출 모델 매개변수를 다운로드하고 RVC 루트 디렉토리에 배치해야 합니다.

- [rmvpe.pt 다운로드](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)
+- [rmvpe.pt 다운로드](https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.pt)

 #### dml 환경의 RMVPE 다운로드(선택사항, A카드/I카드 사용자)

- [rmvpe.onnx 다운로드](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx)
+- [rmvpe.onnx 다운로드](https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.onnx)

 ### 3. AMD 그래픽 카드 Rocm(선택사항, Linux만 해당)

--- a/docs/kr/faq_ko.md
+++ b/docs/kr/faq_ko.md
@@ -31,22 +31,7 @@ logs 폴더 아래 수백 MB의 pth 파일을 weights 폴더에 복사/공유하
 트레이닝 스크립트: <br>
 먼저 WebUI를 실행하여 데이터 세트 처리 및 트레이닝에 사용되는 명령줄을 메시지 창에서 확인할 수 있습니다. <br>

-추론 스크립트: <br>
-https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/myinfer.py <br>
-
-예제: <br>
-
-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 <br>
-
-f0up_key=sys.argv[1] <br>
-input_path=sys.argv[2] <br>
-index_path=sys.argv[3] <br>
-f0method=sys.argv[4]#harvest 또는 pm <br>
-opt_path=sys.argv[5] <br>
-model_path=sys.argv[6] <br>
-index_rate=float(sys.argv[7]) <br>
-device=sys.argv[8] <br>
-is_half=bool(sys.argv[9]) <br>
+추론 스크립트: tool/cmd/infer_cli.py

 ## Q7:Cuda 오류/Cuda 메모리 부족

--- a/docs/pt/README.pt.md
+++ b/docs/pt/README.pt.md
@@ -9,7 +9,7 @@ Uma estrutura de conversão de voz fácil de usar baseada em VITS.
 ![moe](https://counter.seku.su/cmoe?name=rvc&theme=r34)

 [![Licence](https://img.shields.io/github/license/fumiama/Retrieval-based-Voice-Conversion-WebUI?style=for-the-badge)](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
-[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)

 [![Discord](https://img.shields.io/badge/RVC%20Developers-Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/HcsmBBGyVk)

@@ -18,7 +18,7 @@ Uma estrutura de conversão de voz fácil de usar baseada em VITS.
 ------
 [**FAQ (Frequently Asked Questions)**](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/wiki/FAQ-(Frequently-Asked-Questions)) 

-[**English**](../en/README.en.md) | [**中文简体**](../../README.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Türkçe**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)
+[**English**](../../README.md) | [**中文简体**](../cn/README.cn.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Türkçe**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)


 Confira nosso [Vídeo de demonstração](https://www.bilibili.com/video/BV1pm4y1z7Gm/) aqui!
@@ -101,11 +101,10 @@ sh ./run.sh
 RVC requer outros pré-modelos para inferir e treinar.

 ```bash
-#Baixe todos os modelos necessários em https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/
 python tools/download_models.py
 ```

-Ou apenas baixe-os você mesmo em nosso [Huggingface space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/).
+Ou apenas baixe-os você mesmo em nosso [Huggingface space](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/).

 Aqui está uma lista de pré-modelos e outros arquivos que o RVC precisa:
 ```bash
@@ -125,11 +124,11 @@ Se você deseja testar o modelo da versão v2 (o modelo da versão v2 alterou a

 Se quiser usar o algoritmo de extração de tom vocal SOTA RMVPE mais recente, você precisa baixar os pesos RMVPE e colocá-los no diretório raiz RVC

-https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt
+https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.pt

    Para usuários de placas gráficas AMD/Intel, você precisa baixar:

-    https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx
+    https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.onnx

 ```

--- a/docs/pt/faq_pt.md
+++ b/docs/pt/faq_pt.md
@@ -130,24 +130,7 @@ Desative o proxy LAN do sistema/proxy global e atualize.<hr>
 Script de treinamento:
 <br>Você pode executar o treinamento em WebUI primeiro, e as versões de linha de comando do pré-processamento e treinamento do conjunto de dados serão exibidas na janela de mensagens.<br>

-Script de inference:
-<br>https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/myinfer.py<br>
-
-
-por exemplo<br>
-
-``runtime\python.exe myinfer.py 0 "E:\audios\1111.wav" "E:\RVC\logs\minha-voz\added_IVF677_Flat_nprobe_7.index" harvest "test.wav" "weights/mi-test.pth" 0.6 cuda:0 True``<br>
-
-
-f0up_key=sys.argv[1]<br>
-input_path=sys.argv[2]<br>
-index_path=sys.argv[3]<br>
-f0method=sys.argv[4]#harvest or pm<br>
-opt_path=sys.argv[5]<br>
-model_path=sys.argv[6]<br>
-index_rate=float(sys.argv[7])<br>
-device=sys.argv[8]<br>
-is_half=bool(sys.argv[9])<hr>
+Script de inference: tool/cmd/infer_cli.py

 ## <b><span style="color: #337dff;">Q7: Erro Cuda/Cuda sem memória.</span></b>
 Há uma pequena chance de que haja um problema com a configuração do CUDA ou o dispositivo não seja suportado; mais provavelmente, não há memória suficiente (falta de memória).<br>
--- a/docs/tr/README.tr.md
+++ b/docs/tr/README.tr.md
@@ -10,7 +10,7 @@ VITS'e dayalı kullanımı kolay bir Ses Dönüşümü çerçevesi.
 ![moe](https://counter.seku.su/cmoe?name=rvc&theme=r34)

 [![Licence](https://img.shields.io/github/license/fumiama/Retrieval-based-Voice-Conversion-WebUI?style=for-the-badge)](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
-[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
+[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/)

 [![Discord](https://img.shields.io/badge/RVC%20Geliştiricileri-Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/HcsmBBGyVk)

@@ -19,7 +19,7 @@ VITS'e dayalı kullanımı kolay bir Ses Dönüşümü çerçevesi.
 ------
 [**SSS (Sıkça Sorulan Sorular)**](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/wiki/SSS-(Sıkça-Sorulan-Sorular)) 

-[**İngilizce**](../en/README.en.md) | [**中文简体**](../../README.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Français**](../fr/README.fr.md) | [**Türkçe**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)
+[**İngilizce**](../../README.md) | [**中文简体**](../cn/README.cn.md) | [**日本語**](../jp/README.ja.md) | [**한국어**](../kr/README.ko.md) ([**韓國語**](../kr/README.ko.han.md)) | [**Français**](../fr/README.fr.md) | [**Türkçe**](../tr/README.tr.md) | [**Português**](../pt/README.pt.md)

 Burada [Demo Video'muzu](https://www.bilibili.com/video/BV1pm4y1z7Gm/) izleyebilirsiniz!

@@ -90,7 +90,7 @@ sh ./run.sh
 ## Diğer Ön Modellerin Hazırlanması
 RVC'nin çıkarım ve eğitim yapması için diğer ön modellere ihtiyacı vardır.

-Bu ön modelleri [Huggingface alanımızdan](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/) indirmeniz gerekecektir.
+Bu ön modelleri [Huggingface alanımızdan](https://huggingface.co/fumiama/RVC-Pretrained-Models/tree/main/) indirmeniz gerekecektir.

 İşte RVC'nin ihtiyaç duyduğu diğer ön modellerin ve dosyaların bir listesi:
 ```bash
@@ -110,11 +110,11 @@ V2 sürüm modelini test etmek isterseniz (v2 sürüm modeli, 9 katmanlı Hubert

 En son SOTA RMVPE vokal ton çıkarma algoritmasını kullanmak istiyorsanız, RMVPE ağırlıklarını indirip RVC kök dizinine koymalısınız.

-https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt
+https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.pt

    AMD/Intel grafik kartları kullanıcıları için indirmeniz gereken:

-    https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx
+    https://huggingface.co/fumiama/RVC-Pretrained-Models/blob/main/rmvpe/rmvpe.onnx

 ```

--- a/docs/tr/faq_tr.md
+++ b/docs/tr/faq_tr.md
@@ -23,24 +23,7 @@ Lütfen sistem LAN proxy/global proxy'sini devre dışı bırakın ve ardından
 Eğitim komut dosyası:<br>
 Önce WebUI'de eğitimi çalıştırabilirsiniz, ardından veri seti önişleme ve eğitiminin komut satırı sürümleri mesaj penceresinde görüntülenecektir.<br>

-Tahmin komut dosyası:<br>
-https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/myinfer.py<br>
-
-
-örn:<br>
-
-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<br>
-
-
-f0up_key=sys.argv[1]<br>
-input_path=sys.argv[2]<br>
-index_path=sys.argv[3]<br>
-f0method=sys.argv[4]#harvest or pm<br>
-opt_path=sys.argv[5]<br>
-model_path=sys.argv[6]<br>
-index_rate=float(sys.argv[7])<br>
-device=sys.argv[8]<br>
-is_half=bool(sys.argv[9])<br>
+Tahmin komut dosyası: tool/cmd/infer_cli.py

 ## Q7: Cuda Hatası/Cuda Bellek Yetersizliği
 Küçük bir ihtimalle CUDA konfigürasyonunda bir problem olabilir veya cihaz desteklenmiyor olabilir; daha muhtemel olarak yetersiz bellek olabilir (bellek yetersizliği).<br>
--- a/infer/lib/rtrvc.py
+++ b/infer/lib/rtrvc.py
@@ -13,6 +13,7 @@ from torchaudio.transforms import Resample

 from rvc.f0 import Generator
 from rvc.synthesizer import load_synthesizer
+from rvc.utils import FileLike


 class RVC:
@@ -20,7 +21,7 @@ class RVC:
        self,
        key: Union[int, float],
        formant: Union[int, float],
-        pth_path: torch.serialization.FILE_LIKE,
+        pth_path: FileLike, # type: ignore
        index_path: str,
        index_rate: Union[int, float],
        n_cpu: int = os.cpu_count(),
--- a/infer/modules/train/extract_feature_print.py
+++ b/infer/modules/train/extract_feature_print.py
@@ -40,7 +40,7 @@ if "privateuseone" not in device:
    elif torch.backends.mps.is_available():
        device = "mps"
 else:
-    import torch_directml
+    import torch_directml # type: ignore

    device = torch_directml.device(torch_directml.default_device())

@@ -89,7 +89,7 @@ printt("load model(s) from {}".format(model_path))
 # if hubert model is exist
 if os.access(model_path, os.F_OK) == False:
    printt(
-        "Error: Extracting is shut down because %s does not exist, you may download it from https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main"
+        "Error: Extracting is shut down because %s does not exist."
        % model_path
    )
    exit(0)
--- a/requirements/amd.txt
+++ b/requirements/amd.txt
@@ -1,12 +1,12 @@
 tensorflow-rocm
 joblib>=1.1.0
-numba==0.56.4
-numpy==1.23.5
+numba
+numpy
 scipy
 librosa>=0.10.2
-llvmlite==0.39.0
-fairseq==0.12.2
-faiss-cpu==1.7.3
+llvmlite
+fairseq @ git+https://github.com/One-sixth/fairseq.git
+faiss-cpu
 gradio
 Cython
 pydub>=0.25.1
--- a/requirements/dml.txt
+++ b/requirements/dml.txt
@@ -1,11 +1,11 @@
 joblib>=1.1.0
-numba==0.56.4
-numpy==1.23.5
+numba
+numpy
 scipy
 librosa>=0.10.2
-llvmlite==0.39.0
-fairseq==0.12.2
-faiss-cpu==1.7.3
+llvmlite
+fairseq @ git+https://github.com/One-sixth/fairseq.git
+faiss-cpu
 gradio
 Cython
 pydub>=0.25.1
--- a/requirements/ipex.txt
+++ b/requirements/ipex.txt
@@ -5,12 +5,12 @@ https://github.com/Disty0/Retrieval-based-Voice-Conversion-WebUI/releases/downlo
 --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 joblib>=1.1.0
 numba==0.56.4
-numpy==1.23.5
+numpy
 scipy
 librosa>=0.10.2
 llvmlite==0.39.0
-fairseq==0.12.2
-faiss-cpu==1.7.3
+fairseq @ git+https://github.com/One-sixth/fairseq.git
+faiss-cpu
 gradio
 Cython
 pydub>=0.25.1
--- a/requirements/main.txt
+++ b/requirements/main.txt
@@ -1,10 +1,10 @@
 joblib>=1.1.0
 numba
-numpy==1.23.5
+numpy
 scipy
 librosa>=0.10.2
 llvmlite
-fairseq
+fairseq @ git+https://github.com/One-sixth/fairseq.git
 faiss-cpu
 gradio
 Cython
--- a/requirements/py311.txt
+++ b/requirements/py311.txt
@@ -1,46 +0,0 @@
-joblib>=1.1.0
-numba
-numpy
-scipy
-librosa>=0.10.2
-llvmlite
-fairseq @ git+https://github.com/One-sixth/fairseq.git
-faiss-cpu
-gradio
-Cython
-pydub>=0.25.1
-tensorboardX
-Jinja2>=3.1.2
-json5
-Markdown
-matplotlib>=3.7.0
-matplotlib-inline>=0.1.3
-praat-parselmouth>=0.4.2
-Pillow>=9.1.1
-resampy>=0.4.2
-scikit-learn
-tensorboard
-tqdm>=4.63.1
-tornado>=6.1
-Werkzeug>=2.2.3
-uc-micro-py>=1.0.1
-sympy>=1.11.1
-tabulate>=0.8.10
-PyYAML>=6.0
-pyasn1>=0.4.8
-pyasn1-modules>=0.2.8
-fsspec>=2022.11.0
-absl-py>=1.2.0
-audioread
-uvicorn>=0.21.1
-colorama>=0.4.5
-pyworld==0.3.2
-httpx
-onnxruntime; sys_platform == 'darwin'
-onnxruntime-gpu; sys_platform != 'darwin'
-torchcrepe>=0.0.23
-fastapi
-torchfcpe
-python-dotenv>=1.0.0
-av
-pybase16384
--- a/rvc/jit/jit.py
+++ b/rvc/jit/jit.py
@@ -5,6 +5,8 @@ import os

 import torch

+from rvc.utils import FileLike
+

 def load_pickle(path: str):
    with open(path, "rb") as f:
@@ -16,7 +18,7 @@ def save_pickle(ckpt: dict, save_path: str):
        pickle.dump(ckpt, f)


-def load_inputs(path: torch.serialization.FILE_LIKE, device: str, is_half=False):
+def load_inputs(path: FileLike, device: str, is_half=False): # type: ignore
    parm = torch.load(path, map_location=torch.device("cpu"))
    for key in parm.keys():
        parm[key] = parm[key].to(device)
--- a/rvc/synthesizer.py
+++ b/rvc/synthesizer.py
@@ -4,6 +4,7 @@ import torch

 from .layers.synthesizers import SynthesizerTrnMsNSFsid
 from .jit import load_inputs, export_jit_model, save_pickle
+from .utils import FileLike


 def get_synthesizer(cpt: OrderedDict, device=torch.device("cpu")):
@@ -28,7 +29,7 @@ def get_synthesizer(cpt: OrderedDict, device=torch.device("cpu")):


 def load_synthesizer(
-    pth_path: torch.serialization.FILE_LIKE, device=torch.device("cpu")
+    pth_path: FileLike, device=torch.device("cpu") # type: ignore
 ):
    return get_synthesizer(
        torch.load(pth_path, map_location=torch.device("cpu"), weights_only=True),
--- a/rvc/utils/init.py
+++ b/rvc/utils/init.py
@@ -0,0 +1 @@
+from .io import FileLike
--- a/rvc/utils/io.py
+++ b/rvc/utils/io.py
@@ -0,0 +1,10 @@
+import os
+from typing import Union, IO
+import torch
+
+if hasattr(torch.serialization, "FILE_LIKE"):
+    FileLike = torch.serialization.FILE_LIKE
+elif hasattr(torch.types, "FILE_LIKE"):
+    FileLike = torch.types.FileLike
+else:
+    FileLike = Union[str, os.PathLike, IO[bytes]]
--- a/tools/web/infer-only.py
+++ b/tools/web/infer-only.py
@@ -1,7 +1,6 @@
 import logging
 import os

-# os.system("wget -P cvec/ https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt")
 import gradio as gr
 from dotenv import load_dotenv