优化代码结构

.gitignore

@@ -4,3 +4,4 @@ __pycache__
 *.pyd
 hubert_base.pt
 /logs
+.venv

LICENSE

@@ -1,21 +1,64 @@
-MIT License
-
-Copyright (c) 2023 liujing04
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+MIT License
+
+Copyright (c) 2023 liujing04
+Copyright (c) 2023 源文雨
+
+        本软件及其相关代码以MIT协议开源，作者不对软件具备任何控制力，使用软件者、传播软件导出的声音者自负全责。
+        如不认可该条款，则不能使用或引用软件包内任何代码和文件。
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+特此授予任何获得本软件和相关文档文件（以下简称“软件”）副本的人免费使用、复制、修改、合并、出版、分发、再授权和/或销售本软件的权利，以及授予本软件所提供的人使用本软件的权利，但须符合以下条件：
+上述版权声明和本许可声明应包含在软件的所有副本或实质部分中。
+软件是“按原样”提供的，没有任何明示或暗示的保证，包括但不限于适销性、适用于特定目的和不侵权的保证。在任何情况下，作者或版权持有人均不承担因软件或软件的使用或其他交易而产生、产生或与之相关的任何索赔、损害赔偿或其他责任，无论是在合同诉讼、侵权诉讼还是其他诉讼中。
+
+
+The LICENCEs for related libraries are as follows.
+相关引用库协议如下：
+
+ContentVec
+https://github.com/auspicious3000/contentvec/blob/main/LICENSE
+MIT License
+
+VITS
+https://github.com/jaywalnut310/vits/blob/main/LICENSE
+MIT License
+
+HIFIGAN
+https://github.com/jik876/hifi-gan/blob/master/LICENSE
+MIT License
+
+gradio
+https://github.com/gradio-app/gradio/blob/main/LICENSE
+Apache License 2.0
+
+ffmpeg
+https://github.com/FFmpeg/FFmpeg/blob/master/COPYING.LGPLv3
+https://github.com/BtbN/FFmpeg-Builds/releases/download/autobuild-2021-02-28-12-32/ffmpeg-n4.3.2-160-gfbb9368226-win64-lgpl-4.3.zip
+LPGLv3 License
+MIT License
+
+ultimatevocalremovergui
+https://github.com/Anjok07/ultimatevocalremovergui/blob/master/LICENSE
+https://github.com/yang123qwe/vocal_separation_by_uvr5
+MIT License
+
+audio-slicer
+https://github.com/openvpi/audio-slicer/blob/main/LICENSE
+MIT License

MDXNet.py

@@ -1,11 +1,9 @@
 import soundfile as sf
-import torch, pdb, time, argparse, os, warnings, sys, librosa
+import torch, pdb, os, warnings, librosa
 import numpy as np
 import onnxruntime as ort
-from scipy.io.wavfile import write
 from tqdm import tqdm
 import torch
-import torch.nn as nn
 
 dim_c = 4
 

README.md

@@ -8,7 +8,7 @@
 <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/%E4%BD%BF%E7%94%A8%E9%9C%80%E9%81%B5%E5%AE%88%E7%9A%84%E5%8D%8F%E8%AE%AE-LICENSE.txt)
+[![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)

app.py

@@ -1,19 +1,16 @@
-import io
 import os
 import torch
 
 # os.system("wget -P cvec/ https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt")
 import gradio as gr
 import librosa
 import numpy as np
-import soundfile
 import logging
 from fairseq import checkpoint_utils
-from my_utils import load_audio
 from vc_infer_pipeline import VC
 import traceback
 from config import Config
-from infer_pack.models import (
+from lib.infer_pack.models import (
     SynthesizerTrnMs256NSFsid,
     SynthesizerTrnMs256NSFsid_nono,
     SynthesizerTrnMs768NSFsid,

config.py

@@ -81,11 +81,11 @@ def device_config(self) -> tuple:
                 or "1070" in self.gpu_name
                 or "1080" in self.gpu_name
             ):
-                print("16|10|P40 series, force to fp32")
+                print("Found GPU", self.gpu_name, ", force to fp32")
                 self.is_half = False
                 use_fp32_config()
             else:
-                self.gpu_name = None
+                print("Found GPU", self.gpu_name)
             self.gpu_mem = int(
                 torch.cuda.get_device_properties(i_device).total_memory
                 / 1024
@@ -99,12 +99,12 @@ def device_config(self) -> tuple:
                 with open("trainset_preprocess_pipeline_print.py", "w") as f:
                     f.write(strr)
         elif self.has_mps():
-            print("No supported Nvidia GPU, use MPS instead")
+            print("No supported Nvidia GPU found, use MPS instead")
             self.device = "mps"
             self.is_half = False
             use_fp32_config()
         else:
-            print("No supported Nvidia GPU, use CPU instead")
+            print("No supported Nvidia GPU found, use CPU instead")
             self.device = "cpu"
             self.is_half = False
             use_fp32_config()

configs/32k.json

@@ -7,7 +7,7 @@
     "betas": [0.8, 0.99],
     "eps": 1e-9,
     "batch_size": 4,
-    "fp16_run": true,
+    "fp16_run": false,
     "lr_decay": 0.999875,
     "segment_size": 12800,
     "init_lr_ratio": 1,

configs/40k.json

@@ -7,7 +7,7 @@
     "betas": [0.8, 0.99],
     "eps": 1e-9,
     "batch_size": 4,
-    "fp16_run": true,
+    "fp16_run": false,
     "lr_decay": 0.999875,
     "segment_size": 12800,
     "init_lr_ratio": 1,

configs/48k.json

@@ -7,7 +7,7 @@
     "betas": [0.8, 0.99],
     "eps": 1e-9,
     "batch_size": 4,
-    "fp16_run": true,
+    "fp16_run": false,
     "lr_decay": 0.999875,
     "segment_size": 11520,
     "init_lr_ratio": 1,

docs/Changelog_CN.md

@@ -29,7 +29,7 @@ todolist：
 - 废弃32k模型的训练
 
 ### 20230513更新
-- 清除一键包内部老版本runtime内残留的infer_pack和uvr5_pack
+- 清除一键包内部老版本runtime内残留的lib.infer_pack和uvr5_pack
 - 修复训练集预处理伪多进程的bug
 - 增加harvest识别音高可选通过中值滤波削弱哑音现象，可调整中值滤波半径
 - 导出音频增加后处理重采样

docs/Changelog_EN.md

@@ -27,7 +27,7 @@ todolist：
 - v1 32k model training is no more supported
 
 ### 2023-05-13
-- Clear the redundant codes in the old version of runtime in the one-click-package: infer_pack and uvr5_pack
+- Clear the redundant codes in the old version of runtime in the one-click-package: lib.infer_pack and uvr5_pack
 - Fix pseudo multiprocessing bug in training set preprocessing
 - Adding median filtering radius adjustment for harvest pitch recognize algorithm
 - Support post processing resampling for exporting audio

docs/Changelog_KO.md

@@ -33,7 +33,7 @@
 
 ### 2023년 5월 13일 업데이트
 
-- 원클릭 패키지의 이전 버전 런타임 내, 불필요한 코드(infer_pack 및 uvr5_pack) 제거.
+- 원클릭 패키지의 이전 버전 런타임 내, 불필요한 코드(lib.infer_pack 및 uvr5_pack) 제거.
 - 훈련 세트 전처리의 유사 다중 처리 버그 수정.
 - Harvest 피치 인식 알고리즘에 대한 중위수 필터링 반경 조정 추가.
 - 오디오 내보낼 때, 후처리 리샘플링 지원.

docs/README.en.md

@@ -8,7 +8,7 @@ An easy-to-use Voice Conversion framework based on VITS.<br><br>
 <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/%E4%BD%BF%E7%94%A8%E9%9C%80%E9%81%B5%E5%AE%88%E7%9A%84%E5%8D%8F%E8%AE%AE-LICENSE.txt)
+[![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)

docs/README.ja.md

@@ -8,7 +8,7 @@ VITSに基づく使いやすい音声変換（voice changer）framework<br><br>
 <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/%E4%BD%BF%E7%94%A8%E9%9C%80%E9%81%B5%E5%AE%88%E7%9A%84%E5%8D%8F%E8%AE%AE-LICENSE.txt)
+[![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)

docs/README.ko.han.md

@@ -8,7 +8,7 @@ VITS基盤의 簡單하고使用하기 쉬운音聲變換틀<br><br>
 <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/%E4%BD%BF%E7%94%A8%E9%9C%80%E9%81%B5%E5%AE%88%E7%9A%84%E5%8D%8F%E8%AE%AE-LICENSE.txt)
+[![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)

docs/README.ko.md

@@ -8,7 +8,7 @@ VITS 기반의 간단하고 사용하기 쉬운 음성 변환 프레임워크.<b
 <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/%E4%BD%BF%E7%94%A8%E9%9C%80%E9%81%B5%E5%AE%88%E7%9A%84%E5%8D%8F%E8%AE%AE-LICENSE.txt)
+[![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)

extract_f0_print.py

@@ -4,7 +4,6 @@
 sys.path.append(now_dir)
 from my_utils import load_audio
 import pyworld
-from scipy.io import wavfile
 import numpy as np, logging
 
 logging.getLogger("numba").setLevel(logging.WARNING)

gui.py

@@ -31,7 +31,7 @@
 
 
 # import matplotlib.pyplot as plt
-from infer_pack.models import (
+from lib.infer_pack.models import (
     SynthesizerTrnMs256NSFsid,
     SynthesizerTrnMs256NSFsid_nono,
     SynthesizerTrnMs768NSFsid,

i18n/en_US.json

@@ -7,7 +7,7 @@
     "step3a:正在训练模型": "Step 3a: Model training started",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "Training complete. You can check the training logs in the console or the 'train.log' file under the experiment folder.",
     "全流程结束！": "All processes have been completed!",
-    "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责. <br>如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录<b>使用需遵守的协议-LICENSE.txt</b>.": "This software is open source under the MIT license. The author does not have any control over the software. Users who use the software and distribute the sounds exported by the software are solely responsible. <br>If you do not agree with this clause, you cannot use or reference any codes and files within the software package. See the root directory <b>Agreement-LICENSE.txt</b> for details.",
+    "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责. <br>如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录<b>LICENSE</b>.": "This software is open source under the MIT license. The author does not have any control over the software. Users who use the software and distribute the sounds exported by the software are solely responsible. <br>If you do not agree with this clause, you cannot use or reference any codes and files within the software package. See the root directory <b>Agreement-LICENSE.txt</b> for details.",
     "模型推理": "Model Inference",
     "推理音色": "Inferencing voice:",
     "刷新音色列表和索引路径": "Refresh voice list and index path",

i18n/es_ES.json

@@ -7,7 +7,7 @@
     "step3a:正在训练模型": "Paso 3a: Entrenando el modelo",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "Entrenamiento finalizado, puede ver el registro de entrenamiento en la consola o en el archivo train.log en la carpeta del experimento",
     "全流程结束！": "¡Todo el proceso ha terminado!",
-    "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责. <br>如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录<b>使用需遵守的协议-LICENSE.txt</b>.": "Este software es de código abierto bajo la licencia MIT, el autor no tiene ningún control sobre el software, y aquellos que usan el software y difunden los sonidos exportados por el software son los únicos responsables.<br>Si no está de acuerdo con esta cláusula , no puede utilizar ni citar ningún código ni archivo del paquete de software Consulte el directorio raíz <b>Agreement-LICENSE.txt</b> para obtener más información.",
+    "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责. <br>如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录<b>LICENSE</b>.": "Este software es de código abierto bajo la licencia MIT, el autor no tiene ningún control sobre el software, y aquellos que usan el software y difunden los sonidos exportados por el software son los únicos responsables.<br>Si no está de acuerdo con esta cláusula , no puede utilizar ni citar ningún código ni archivo del paquete de software Consulte el directorio raíz <b>Agreement-LICENSE.txt</b> para obtener más información.",
     "模型推理": "inferencia del modelo",
     "推理音色": "inferencia de voz",
     "刷新音色列表和索引路径": "Actualizar la lista de timbres e índice de rutas",