storytold/storyteller-ml
2
0
Fork 0
mirror of https://github.com/storytold/storyteller-ml.git synced 2026-10-17 00:23:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add files via upload

Browse Source
This commit is contained in:
Justin John
2023-09-17 11:28:21 +05:30
committed by GitHub
parent 0e19a34098
commit 949acbafb6
26 changed files with 8267 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
voice_conversion/rvc-v2-justin/Dockerfile
+55
View File
@@ -0,0 +1,55 @@
# syntax=docker/dockerfile:1
#FROM python:3.10-bullseye
# Alternatively,
FROM nvidia/cuda:12.0.1-runtime-ubuntu22.04
ENV DEBIAN_FRONTEND=noninteractive
# NB: ffmpeg for transcoding opus -> wav
# NB(bt,2023-05-04): Installing lsof, htop, ripgrep, and other debugging tools
# NB(bt,2023-05-04): Installing rsync to monitor time it takes for files to sync
RUN apt-get update && apt-get install -y \
build-essential \
curl \
ffmpeg \
htop \
libsndfile1 \
lsof \
nvidia-driver-515 \
python3-pip \
python3.10 \
python3.10-dev \
python3.10-venv \
ripgrep \
rsync \
vim \
wget \
--no-install-recommends \
&& apt-get clean autoclean && apt-get autoremove -y && rm -rf /var/lib/{apt,dpkg,cache,log}/
#ENV DEBIAN_FRONTEND=noninteractive
#
#RUN apt-get update && apt-get install -y \
# rsync \
# --no-install-recommends \
# && apt-get clean autoclean && apt-get autoremove -y && rm -rf /var/lib/{apt,dpkg,cache,log}/
RUN mkdir /python_install
RUN mkdir /model_code
WORKDIR /python_install
COPY requirements.txt .
# NB: Kubernetes will copy over the venv we create here.
RUN python3 -m venv python \
&& . python/bin/activate \
&& pip install -r requirements.txt
&& pip install piper-tts
# NB: The model code is uploaded next
WORKDIR /model_code
COPY . .
voice_conversion/rvc-v2-justin/LICENSE
+23
View File
@@ -0,0 +1,23 @@
MIT License
Copyright (c) 2023 liujing04
Copyright (c) 2023 源文雨
Copyright (c) 2023 Ftps
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.
voice_conversion/rvc-v2-justin/MIT协议暨相关引用库协议
+45
View File
@@ -0,0 +1,45 @@
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。
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
PySimpleGUI
https://github.com/PySimpleGUI/PySimpleGUI/blob/master/license.txt
LPGLv3 License
voice_conversion/rvc-v2-justin/README.md
+144
View File
@@ -0,0 +1,144 @@
<div align="center">
<h1>Retrieval-based-Voice-Conversion-WebUI</h1>
一个基于VITS的简单易用的语音转换（变声器）框架<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/badge/LICENSE-MIT-green.svg?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)
[**更新日志**](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/docs/Changelog_CN.md) | [**常见问题解答**](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/wiki/%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98%E8%A7%A3%E7%AD%94) | [**AutoDL·5毛钱训练AI歌手**](https://github.com/RVC-Project/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) | [**对照实验记录**](https://github.com/RVC-Project/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](https://github.com/RVC-Project/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)) | [**在线演示**](https://huggingface.co/spaces/Ricecake123/RVC-demo)
</div>
------
[**English**](./docs/en/README.en.md) | [**中文简体**](./README.md) | [**日本語**](./docs/jp/README.ja.md) | [**한국어**](./docs/kr/README.ko.md) ([**韓國語**](./docs/kr/README.ko.han.md)) | [**Français**](./docs/fr/README.fr.md)| [**Türkçe**](./docs/tr/README.tr.md)
点此查看我们的[演示视频](https://www.bilibili.com/video/BV1pm4y1z7Gm/) !
> 使用了RVC的实时语音转换: [w-okada/voice-changer](https://github.com/w-okada/voice-changer)
> 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
> 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。
## 简介
本仓库具有以下特点
+ 使用top1检索替换输入源特征为训练集特征来杜绝音色泄漏
+ 即便在相对较差的显卡上也能快速训练
+ 使用少量数据进行训练也能得到较好结果(推荐至少收集10分钟低底噪语音数据)
+ 可以通过模型融合来改变音色(借助ckpt处理选项卡中的ckpt-merge)
+ 简单易用的网页界面
+ 可调用UVR5模型来快速分离人声和伴奏
+ 使用最先进的[人声音高提取算法InterSpeech2023-RMVPE](#参考项目)根绝哑音问题。效果最好（显著地）但比crepe_full更快、资源占用更小
+ A卡I卡加速支持
## 环境配置
以下指令需在 Python 版本大于3.8的环境中执行。
(Windows/Linux)
首先通过 pip 安装主要依赖:
```bash
# 安装Pytorch及其核心依赖，若已安装则跳过
# 参考自: https://pytorch.org/get-started/locally/
pip install torch torchvision torchaudio
#如果是win系统+Nvidia Ampere架构(RTX30xx)，根据 #21 的经验，需要指定pytorch对应的cuda版本
#pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117
```
可以使用 poetry 来安装依赖：
```bash
# 安装 Poetry 依赖管理工具, 若已安装则跳过
# 参考自: https://python-poetry.org/docs/#installation
curl -sSL https://install.python-poetry.org | python3 -
# 通过poetry安装依赖
poetry install
```
你也可以通过 pip 来安装依赖：
```bash
N卡：
pip install -r requirements.txt
A卡/I卡：
pip install -r requirements-dml.txt
```
------
Mac 用户可以通过 `run.sh` 来安装依赖：
```bash
sh ./run.sh
```
## 其他预模型准备
RVC需要其他一些预模型来推理和训练。
你可以从我们的[Hugging Face space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)下载到这些模型。
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:
```bash
./assets/hubert/hubert_base.pt
./assets/pretrained
./assets/uvr5_weights
想测试v2版本模型的话，需要额外下载
./assets/pretrained_v2
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)
./ffmpeg
https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe
./ffprobe
https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe
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RVC根目录
https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt
A卡I卡用户需要的dml环境要请下载
https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx
```
之后使用以下指令来启动WebUI:
```bash
python infer-web.py
```
如果你正在使用Windows 或 macOS，你可以直接下载并解压`RVC-beta.7z`，前者可以运行`go-web.bat`以启动WebUI，后者则运行命令`sh ./run.sh`以启动WebUI。
仓库内还有一份`小白简易教程.doc`以供参考。
## 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)
+ [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).
## 感谢所有贡献者作出的努力
<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>
voice_conversion/rvc-v2-justin/Retrieval_based_Voice_Conversion_WebUI.ipynb
+403
View File
@@ -0,0 +1,403 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# [Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) Training notebook"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "ZFFCx5J80SGa"
},
"source": [
"[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "GmFP6bN9dvOq"
},
"outputs": [],
"source": [
"# @title 查看显卡\n",
"!nvidia-smi"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "jwu07JgqoFON"
},
"outputs": [],
"source": [
"# @title 挂载谷歌云盘\n",
"\n",
"from google.colab import drive\n",
"\n",
"drive.mount(\"/content/drive\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "wjddIFr1oS3W"
},
"outputs": [],
"source": [
"# @title 安装依赖\n",
"!apt-get -y install build-essential python3-dev ffmpeg\n",
"!pip3 install --upgrade setuptools wheel\n",
"!pip3 install --upgrade pip\n",
"!pip3 install faiss-cpu==1.7.2 fairseq gradio==3.14.0 ffmpeg ffmpeg-python praat-parselmouth pyworld numpy==1.23.5 numba==0.56.4 librosa==0.9.2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ge_97mfpgqTm"
},
"outputs": [],
"source": [
"# @title 克隆仓库\n",
"\n",
"!git clone --depth=1 -b stable https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI\n",
"%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
"!mkdir -p pretrained uvr5_weights"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "BLDEZADkvlw1"
},
"outputs": [],
"source": [
"# @title 更新仓库（一般无需执行）\n",
"!git pull"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "pqE0PrnuRqI2"
},
"outputs": [],
"source": [
"# @title 安装aria2\n",
"!apt -y install -qq aria2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "UG3XpUwEomUz"
},
"outputs": [],
"source": [
"# @title 下载底模\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D32k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D40k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D48k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G32k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G40k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G48k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D32k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D40k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D48k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G32k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G40k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G48k.pth"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "HugjmZqZRuiF"
},
"outputs": [],
"source": [
"# @title 下载人声分离模型\n",
"!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 /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP2-人声vocals+非人声instrumentals.pth\n",
"!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 /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP5-主旋律人声vocals+其他instrumentals.pth"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "2RCaT9FTR0ej"
},
"outputs": [],
"source": [
"# @title 下载hubert_base\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o hubert_base.pt"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# @title #下载rmvpe模型\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o rmvpe.pt"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Mwk7Q0Loqzjx"
},
"outputs": [],
"source": [
"# @title 从谷歌云盘加载打包好的数据集到/content/dataset\n",
"\n",
"# @markdown 数据集位置\n",
"DATASET = (\n",
" \"/content/drive/MyDrive/dataset/lulu20230327_32k.zip\" # @param {type:\"string\"}\n",
")\n",
"\n",
"!mkdir -p /content/dataset\n",
"!unzip -d /content/dataset -B {DATASET}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "PDlFxWHWEynD"
},
"outputs": [],
"source": [
"# @title 重命名数据集中的重名文件\n",
"!ls -a /content/dataset/\n",
"!rename 's/(\\w+)\\.(\\w+)~(\\d*)/$1_$3.$2/' /content/dataset/*.*~*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "7vh6vphDwO0b"
},
"outputs": [],
"source": [
"# @title 启动web\n",
"%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
"# %load_ext tensorboard\n",
"# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",
"!python3 infer-web.py --colab --pycmd python3"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "FgJuNeAwx5Y_"
},
"outputs": [],
"source": [
"# @title 手动将训练后的模型文件备份到谷歌云盘\n",
"# @markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
"\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 模型epoch\n",
"MODELEPOCH = 9600 # @param {type:\"integer\"}\n",
"\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/added_*.index /content/drive/MyDrive/\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/total_*.npy /content/drive/MyDrive/\n",
"\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "OVQoLQJXS7WX"
},
"outputs": [],
"source": [
"# @title 从谷歌云盘恢复pth\n",
"# @markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
"\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 模型epoch\n",
"MODELEPOCH = 7500 # @param {type:\"integer\"}\n",
"\n",
"!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
"\n",
"!cp /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
"!cp /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
"!cp /content/drive/MyDrive/*.index /content/\n",
"!cp /content/drive/MyDrive/*.npy /content/\n",
"!cp /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ZKAyuKb9J6dz"
},
"outputs": [],
"source": [
"# @title 手动预处理（不推荐）\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 采样率\n",
"BITRATE = 48000 # @param {type:\"integer\"}\n",
"# @markdown 使用的进程数\n",
"THREADCOUNT = 8 # @param {type:\"integer\"}\n",
"\n",
"!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "CrxJqzAUKmPJ"
},
"outputs": [],
"source": [
"# @title 手动提取特征（不推荐）\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 使用的进程数\n",
"THREADCOUNT = 8 # @param {type:\"integer\"}\n",
"# @markdown 音高提取算法\n",
"ALGO = \"harvest\" # @param {type:\"string\"}\n",
"\n",
"!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",
"\n",
"!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "IMLPLKOaKj58"
},
"outputs": [],
"source": [
"# @title 手动训练（不推荐）\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 使用的GPU\n",
"USEGPU = \"0\" # @param {type:\"string\"}\n",
"# @markdown 批大小\n",
"BATCHSIZE = 32 # @param {type:\"integer\"}\n",
"# @markdown 停止的epoch\n",
"MODELEPOCH = 3200 # @param {type:\"integer\"}\n",
"# @markdown 保存epoch间隔\n",
"EPOCHSAVE = 100 # @param {type:\"integer\"}\n",
"# @markdown 采样率\n",
"MODELSAMPLE = \"48k\" # @param {type:\"string\"}\n",
"# @markdown 是否缓存训练集\n",
"CACHEDATA = 1 # @param {type:\"integer\"}\n",
"# @markdown 是否仅保存最新的ckpt文件\n",
"ONLYLATEST = 0 # @param {type:\"integer\"}\n",
"\n",
"!python3 train_nsf_sim_cache_sid_load_pretrain.py -e lulu -sr {MODELSAMPLE} -f0 1 -bs {BATCHSIZE} -g {USEGPU} -te {MODELEPOCH} -se {EPOCHSAVE} -pg pretrained/f0G{MODELSAMPLE}.pth -pd pretrained/f0D{MODELSAMPLE}.pth -l {ONLYLATEST} -c {CACHEDATA}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "haYA81hySuDl"
},
"outputs": [],
"source": [
"# @title 删除其它pth，只留选中的（慎点，仔细看代码）\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 选中模型epoch\n",
"MODELEPOCH = 9600 # @param {type:\"integer\"}\n",
"\n",
"!echo \"备份选中的模型。。。\"\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
"\n",
"!echo \"正在删除。。。\"\n",
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
"!rm /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*.pth\n",
"\n",
"!echo \"恢复选中的模型。。。\"\n",
"!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
"!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
"\n",
"!echo \"删除完成\"\n",
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "QhSiPTVPoIRh"
},
"outputs": [],
"source": [
"# @title 清除项目下所有文件，只留选中的模型（慎点，仔细看代码）\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 选中模型epoch\n",
"MODELEPOCH = 9600 # @param {type:\"integer\"}\n",
"\n",
"!echo \"备份选中的模型。。。\"\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
"\n",
"!echo \"正在删除。。。\"\n",
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
"!rm -rf /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*\n",
"\n",
"!echo \"恢复选中的模型。。。\"\n",
"!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
"!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
"\n",
"!echo \"删除完成\"\n",
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"private_outputs": true,
"provenance": []
},
"gpuClass": "standard",
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
voice_conversion/rvc-v2-justin/Retrieval_based_Voice_Conversion_WebUI_v2.ipynb
+422
View File
@@ -0,0 +1,422 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# [Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) Training notebook"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"id": "ZFFCx5J80SGa"
},
"source": [
"[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI_v2.ipynb)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "GmFP6bN9dvOq"
},
"outputs": [],
"source": [
"# @title #查看显卡\n",
"!nvidia-smi"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "jwu07JgqoFON"
},
"outputs": [],
"source": [
"# @title 挂载谷歌云盘\n",
"\n",
"from google.colab import drive\n",
"\n",
"drive.mount(\"/content/drive\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "wjddIFr1oS3W"
},
"outputs": [],
"source": [
"# @title #安装依赖\n",
"!apt-get -y install build-essential python3-dev ffmpeg\n",
"!pip3 install --upgrade setuptools wheel\n",
"!pip3 install --upgrade pip\n",
"!pip3 install faiss-cpu==1.7.2 fairseq gradio==3.14.0 ffmpeg ffmpeg-python praat-parselmouth pyworld numpy==1.23.5 numba==0.56.4 librosa==0.9.2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ge_97mfpgqTm"
},
"outputs": [],
"source": [
"# @title #克隆仓库\n",
"\n",
"!mkdir Retrieval-based-Voice-Conversion-WebUI\n",
"%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
"!git init\n",
"!git remote add origin https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git\n",
"!git fetch origin cfd984812804ddc9247d65b14c82cd32e56c1133 --depth=1\n",
"!git reset --hard FETCH_HEAD"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "BLDEZADkvlw1"
},
"outputs": [],
"source": [
"# @title #更新仓库（一般无需执行）\n",
"!git pull"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "pqE0PrnuRqI2"
},
"outputs": [],
"source": [
"# @title #安装aria2\n",
"!apt -y install -qq aria2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "UG3XpUwEomUz"
},
"outputs": [],
"source": [
"# @title 下载底模\n",
"\n",
"# v1\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D32k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D40k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D48k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G32k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G40k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G48k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D32k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D40k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D48k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G32k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G40k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G48k.pth\n",
"\n",
"# v2\n",
"# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o D32k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o D40k.pth\n",
"# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o D48k.pth\n",
"# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o G32k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o G40k.pth\n",
"# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o G48k.pth\n",
"# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0D32k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0D40k.pth\n",
"# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0D48k.pth\n",
"# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0G32k.pth\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0G40k.pth\n",
"# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0G48k.pth"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "HugjmZqZRuiF"
},
"outputs": [],
"source": [
"# @title #下载人声分离模型\n",
"!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 /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP2-人声vocals+非人声instrumentals.pth\n",
"!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 /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP5-主旋律人声vocals+其他instrumentals.pth"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "2RCaT9FTR0ej"
},
"outputs": [],
"source": [
"# @title #下载hubert_base\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o hubert_base.pt"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# @title #下载rmvpe模型\n",
"!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o rmvpe.pt"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Mwk7Q0Loqzjx"
},
"outputs": [],
"source": [
"# @title #从谷歌云盘加载打包好的数据集到/content/dataset\n",
"\n",
"# @markdown 数据集位置\n",
"DATASET = (\n",
" \"/content/drive/MyDrive/dataset/lulu20230327_32k.zip\" # @param {type:\"string\"}\n",
")\n",
"\n",
"!mkdir -p /content/dataset\n",
"!unzip -d /content/dataset -B {DATASET}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "PDlFxWHWEynD"
},
"outputs": [],
"source": [
"# @title #重命名数据集中的重名文件\n",
"!ls -a /content/dataset/\n",
"!rename 's/(\\w+)\\.(\\w+)~(\\d*)/$1_$3.$2/' /content/dataset/*.*~*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "7vh6vphDwO0b"
},
"outputs": [],
"source": [
"# @title #启动webui\n",
"%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
"# %load_ext tensorboard\n",
"# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",
"!python3 infer-web.py --colab --pycmd python3"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "FgJuNeAwx5Y_"
},
"outputs": [],
"source": [
"# @title #手动将训练后的模型文件备份到谷歌云盘\n",
"# @markdown #需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
"\n",
"# @markdown #模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown #模型epoch\n",
"MODELEPOCH = 9600 # @param {type:\"integer\"}\n",
"\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/added_*.index /content/drive/MyDrive/\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/total_*.npy /content/drive/MyDrive/\n",
"\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "OVQoLQJXS7WX"
},
"outputs": [],
"source": [
"# @title 从谷歌云盘恢复pth\n",
"# @markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
"\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 模型epoch\n",
"MODELEPOCH = 7500 # @param {type:\"integer\"}\n",
"\n",
"!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
"\n",
"!cp /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
"!cp /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
"!cp /content/drive/MyDrive/*.index /content/\n",
"!cp /content/drive/MyDrive/*.npy /content/\n",
"!cp /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ZKAyuKb9J6dz"
},
"outputs": [],
"source": [
"# @title 手动预处理（不推荐）\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 采样率\n",
"BITRATE = 48000 # @param {type:\"integer\"}\n",
"# @markdown 使用的进程数\n",
"THREADCOUNT = 8 # @param {type:\"integer\"}\n",
"\n",
"!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "CrxJqzAUKmPJ"
},
"outputs": [],
"source": [
"# @title 手动提取特征（不推荐）\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 使用的进程数\n",
"THREADCOUNT = 8 # @param {type:\"integer\"}\n",
"# @markdown 音高提取算法\n",
"ALGO = \"harvest\" # @param {type:\"string\"}\n",
"\n",
"!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",
"\n",
"!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "IMLPLKOaKj58"
},
"outputs": [],
"source": [
"# @title 手动训练（不推荐）\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 使用的GPU\n",
"USEGPU = \"0\" # @param {type:\"string\"}\n",
"# @markdown 批大小\n",
"BATCHSIZE = 32 # @param {type:\"integer\"}\n",
"# @markdown 停止的epoch\n",
"MODELEPOCH = 3200 # @param {type:\"integer\"}\n",
"# @markdown 保存epoch间隔\n",
"EPOCHSAVE = 100 # @param {type:\"integer\"}\n",
"# @markdown 采样率\n",
"MODELSAMPLE = \"48k\" # @param {type:\"string\"}\n",
"# @markdown 是否缓存训练集\n",
"CACHEDATA = 1 # @param {type:\"integer\"}\n",
"# @markdown 是否仅保存最新的ckpt文件\n",
"ONLYLATEST = 0 # @param {type:\"integer\"}\n",
"\n",
"!python3 train_nsf_sim_cache_sid_load_pretrain.py -e lulu -sr {MODELSAMPLE} -f0 1 -bs {BATCHSIZE} -g {USEGPU} -te {MODELEPOCH} -se {EPOCHSAVE} -pg pretrained/f0G{MODELSAMPLE}.pth -pd pretrained/f0D{MODELSAMPLE}.pth -l {ONLYLATEST} -c {CACHEDATA}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "haYA81hySuDl"
},
"outputs": [],
"source": [
"# @title 删除其它pth，只留选中的（慎点，仔细看代码）\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 选中模型epoch\n",
"MODELEPOCH = 9600 # @param {type:\"integer\"}\n",
"\n",
"!echo \"备份选中的模型。。。\"\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
"\n",
"!echo \"正在删除。。。\"\n",
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
"!rm /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*.pth\n",
"\n",
"!echo \"恢复选中的模型。。。\"\n",
"!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
"!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
"\n",
"!echo \"删除完成\"\n",
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "QhSiPTVPoIRh"
},
"outputs": [],
"source": [
"# @title 清除项目下所有文件，只留选中的模型（慎点，仔细看代码）\n",
"# @markdown 模型名\n",
"MODELNAME = \"lulu\" # @param {type:\"string\"}\n",
"# @markdown 选中模型epoch\n",
"MODELEPOCH = 9600 # @param {type:\"integer\"}\n",
"\n",
"!echo \"备份选中的模型。。。\"\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
"\n",
"!echo \"正在删除。。。\"\n",
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
"!rm -rf /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*\n",
"\n",
"!echo \"恢复选中的模型。。。\"\n",
"!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
"!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
"\n",
"!echo \"删除完成\"\n",
"!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"private_outputs": true,
"provenance": []
},
"gpuClass": "standard",
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
voice_conversion/rvc-v2-justin/docker-compose.yml
+20
View File
@@ -0,0 +1,20 @@
version: "3.8"
services:
rvc:
build:
context: .
dockerfile: Dockerfile
container_name: rvc
volumes:
- ./weights:/app/assets/weights
- ./opt:/app/opt
# - ./dataset:/app/dataset # you can use this folder in order to provide your dataset for model training
ports:
- 7865:7865
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
voice_conversion/rvc-v2-justin/environment_dml.yaml
+186
View File
@@ -0,0 +1,186 @@
name: pydml
channels:
- pytorch
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge/
- defaults
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/fastai/
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/bioconda/
dependencies:
- abseil-cpp=20211102.0=hd77b12b_0
- absl-py=1.3.0=py310haa95532_0
- aiohttp=3.8.3=py310h2bbff1b_0
- aiosignal=1.2.0=pyhd3eb1b0_0
- async-timeout=4.0.2=py310haa95532_0
- attrs=22.1.0=py310haa95532_0
- blas=1.0=mkl
- blinker=1.4=py310haa95532_0
- bottleneck=1.3.5=py310h9128911_0
- brotli=1.0.9=h2bbff1b_7
- brotli-bin=1.0.9=h2bbff1b_7
- brotlipy=0.7.0=py310h2bbff1b_1002
- bzip2=1.0.8=he774522_0
- c-ares=1.19.0=h2bbff1b_0
- ca-certificates=2023.05.30=haa95532_0
- cachetools=4.2.2=pyhd3eb1b0_0
- certifi=2023.5.7=py310haa95532_0
- cffi=1.15.1=py310h2bbff1b_3
- charset-normalizer=2.0.4=pyhd3eb1b0_0
- click=8.0.4=py310haa95532_0
- colorama=0.4.6=py310haa95532_0
- contourpy=1.0.5=py310h59b6b97_0
- cryptography=39.0.1=py310h21b164f_0
- cycler=0.11.0=pyhd3eb1b0_0
- fonttools=4.25.0=pyhd3eb1b0_0
- freetype=2.12.1=ha860e81_0
- frozenlist=1.3.3=py310h2bbff1b_0
- giflib=5.2.1=h8cc25b3_3
- glib=2.69.1=h5dc1a3c_2
- google-auth=2.6.0=pyhd3eb1b0_0
- google-auth-oauthlib=0.4.4=pyhd3eb1b0_0
- grpc-cpp=1.48.2=hf108199_0
- grpcio=1.48.2=py310hf108199_0
- gst-plugins-base=1.18.5=h9e645db_0
- gstreamer=1.18.5=hd78058f_0
- icu=58.2=ha925a31_3
- idna=3.4=py310haa95532_0
- intel-openmp=2023.1.0=h59b6b97_46319
- jpeg=9e=h2bbff1b_1
- kiwisolver=1.4.4=py310hd77b12b_0
- krb5=1.19.4=h5b6d351_0
- lerc=3.0=hd77b12b_0
- libbrotlicommon=1.0.9=h2bbff1b_7
- libbrotlidec=1.0.9=h2bbff1b_7
- libbrotlienc=1.0.9=h2bbff1b_7
- libclang=14.0.6=default_hb5a9fac_1
- libclang13=14.0.6=default_h8e68704_1
- libdeflate=1.17=h2bbff1b_0
- libffi=3.4.4=hd77b12b_0
- libiconv=1.16=h2bbff1b_2
- libogg=1.3.5=h2bbff1b_1
- libpng=1.6.39=h8cc25b3_0
- libprotobuf=3.20.3=h23ce68f_0
- libtiff=4.5.0=h6c2663c_2
- libuv=1.44.2=h2bbff1b_0
- libvorbis=1.3.7=he774522_0
- libwebp=1.2.4=hbc33d0d_1
- libwebp-base=1.2.4=h2bbff1b_1
- libxml2=2.10.3=h0ad7f3c_0
- libxslt=1.1.37=h2bbff1b_0
- lz4-c=1.9.4=h2bbff1b_0
- markdown=3.4.1=py310haa95532_0
- markupsafe=2.1.1=py310h2bbff1b_0
- matplotlib=3.7.1=py310haa95532_1
- matplotlib-base=3.7.1=py310h4ed8f06_1
- mkl=2023.1.0=h8bd8f75_46356
- mkl-service=2.4.0=py310h2bbff1b_1
- mkl_fft=1.3.6=py310h4ed8f06_1
- mkl_random=1.2.2=py310h4ed8f06_1
- multidict=6.0.2=py310h2bbff1b_0
- munkres=1.1.4=py_0
- numexpr=2.8.4=py310h2cd9be0_1
- numpy=1.24.3=py310h055cbcc_1
- numpy-base=1.24.3=py310h65a83cf_1
- oauthlib=3.2.2=py310haa95532_0
- openssl=1.1.1t=h2bbff1b_0
- packaging=23.0=py310haa95532_0
- pandas=1.5.3=py310h4ed8f06_0
- pcre=8.45=hd77b12b_0
- pillow=9.4.0=py310hd77b12b_0
- pip=23.0.1=py310haa95532_0
- ply=3.11=py310haa95532_0
- protobuf=3.20.3=py310hd77b12b_0
- pyasn1=0.4.8=pyhd3eb1b0_0
- pyasn1-modules=0.2.8=py_0
- pycparser=2.21=pyhd3eb1b0_0
- pyjwt=2.4.0=py310haa95532_0
- pyopenssl=23.0.0=py310haa95532_0
- pyparsing=3.0.9=py310haa95532_0
- pyqt=5.15.7=py310hd77b12b_0
- pyqt5-sip=12.11.0=py310hd77b12b_0
- pysocks=1.7.1=py310haa95532_0
- python=3.10.11=h966fe2a_2
- python-dateutil=2.8.2=pyhd3eb1b0_0
- pytorch-mutex=1.0=cpu
- pytz=2022.7=py310haa95532_0
- pyyaml=6.0=py310h2bbff1b_1
- qt-main=5.15.2=he8e5bd7_8
- qt-webengine=5.15.9=hb9a9bb5_5
- qtwebkit=5.212=h2bbfb41_5
- re2=2022.04.01=hd77b12b_0
- requests=2.29.0=py310haa95532_0
- requests-oauthlib=1.3.0=py_0
- rsa=4.7.2=pyhd3eb1b0_1
- setuptools=67.8.0=py310haa95532_0
- sip=6.6.2=py310hd77b12b_0
- six=1.16.0=pyhd3eb1b0_1
- sqlite=3.41.2=h2bbff1b_0
- tbb=2021.8.0=h59b6b97_0
- tensorboard=2.10.0=py310haa95532_0
- tensorboard-data-server=0.6.1=py310haa95532_0
- tensorboard-plugin-wit=1.8.1=py310haa95532_0
- tk=8.6.12=h2bbff1b_0
- toml=0.10.2=pyhd3eb1b0_0
- tornado=6.2=py310h2bbff1b_0
- tqdm=4.65.0=py310h9909e9c_0
- typing_extensions=4.5.0=py310haa95532_0
- tzdata=2023c=h04d1e81_0
- urllib3=1.26.16=py310haa95532_0
- vc=14.2=h21ff451_1
- vs2015_runtime=14.27.29016=h5e58377_2
- werkzeug=2.2.3=py310haa95532_0
- wheel=0.38.4=py310haa95532_0
- win_inet_pton=1.1.0=py310haa95532_0
- xz=5.4.2=h8cc25b3_0
- yaml=0.2.5=he774522_0
- yarl=1.8.1=py310h2bbff1b_0
- zlib=1.2.13=h8cc25b3_0
- zstd=1.5.5=hd43e919_0
- pip:
- antlr4-python3-runtime==4.8
- appdirs==1.4.4
- audioread==3.0.0
- bitarray==2.7.4
- cython==0.29.35
- decorator==5.1.1
- fairseq==0.12.2
- faiss-cpu==1.7.4
- filelock==3.12.0
- hydra-core==1.0.7
- jinja2==3.1.2
- joblib==1.2.0
- lazy-loader==0.2
- librosa==0.10.0.post2
- llvmlite==0.40.0
- lxml==4.9.2
- mpmath==1.3.0
- msgpack==1.0.5
- networkx==3.1
- noisereduce==2.0.1
- numba==0.57.0
- omegaconf==2.0.6
- opencv-python==4.7.0.72
- pooch==1.6.0
- portalocker==2.7.0
- pysimplegui==4.60.5
- pywin32==306
- pyworld==0.3.3
- regex==2023.5.5
- sacrebleu==2.3.1
- scikit-learn==1.2.2
- scipy==1.10.1
- sounddevice==0.4.6
- soundfile==0.12.1
- soxr==0.3.5
- sympy==1.12
- tabulate==0.9.0
- threadpoolctl==3.1.0
- torch==2.0.0
- torch-directml==0.2.0.dev230426
- torchaudio==2.0.1
- torchvision==0.15.1
- wget==3.2
prefix: D:\ProgramData\anaconda3_\envs\pydml
voice_conversion/rvc-v2-justin/fakeyou_infer.py
+273
View File
@@ -0,0 +1,273 @@
import os, sys, pdb, torch
print("Env vars:")
print(os.environ)
def print_gpu_info():
print('========================================')
print('Python interpreter', sys.executable)
print('PyTorch version', torch.__version__)
print('CUDA Available?', torch.cuda.is_available())
print('CUDA Device count', torch.cuda.device_count())
print('CUDA architectures library was compiled for', torch.cuda.get_arch_list())
#try:
# from tensorflow.python.client import device_lib
# print('local devices', str(device_lib.list_local_devices()).replace("\n", "\n "))
#except ImportError:
# print('no tensorflow - cannot list devices')
# pass
print('========================================', flush=True)
print_gpu_info()
now_dir = os.getcwd()
sys.path.append(now_dir)
import sys
import torch
import tqdm as tq
from multiprocessing import cpu_count
class Config:
def __init__(self, device, is_half):
self.device = device
self.is_half = is_half
self.n_cpu = 0
self.gpu_name = None
self.gpu_mem = None
self.x_pad, self.x_query, self.x_center, self.x_max = self.device_config()
def device_config(self) -> tuple:
if torch.cuda.is_available():
i_device = int(self.device.split(":")[-1])
self.gpu_name = torch.cuda.get_device_name(i_device)
if (
("16" in self.gpu_name and "V100" not in self.gpu_name.upper())
or "P40" in self.gpu_name.upper()
or "1060" in self.gpu_name
or "1070" in self.gpu_name
or "1080" in self.gpu_name
):
print("16系/10系显卡和P40强制单精度")
self.is_half = False
for config_file in ["32k.json", "40k.json", "48k.json"]:
with open(f"configs/{config_file}", "r") as f:
strr = f.read().replace("true", "false")
with open(f"configs/{config_file}", "w") as f:
f.write(strr)
with open("trainset_preprocess_pipeline_print.py", "r") as f:
strr = f.read().replace("3.7", "3.0")
with open("trainset_preprocess_pipeline_print.py", "w") as f:
f.write(strr)
else:
self.gpu_name = None
self.gpu_mem = int(
torch.cuda.get_device_properties(i_device).total_memory
/ 1024
/ 1024
/ 1024
+ 0.4
)
if self.gpu_mem <= 4:
with open("trainset_preprocess_pipeline_print.py", "r") as f:
strr = f.read().replace("3.7", "3.0")
with open("trainset_preprocess_pipeline_print.py", "w") as f:
f.write(strr)
elif torch.backends.mps.is_available():
print("没有发现支持的N卡, 使用MPS进行推理")
self.device = "mps"
else:
print("没有发现支持的N卡, 使用CPU进行推理")
self.device = "cpu"
self.is_half = True
if self.n_cpu == 0:
self.n_cpu = cpu_count()
if self.is_half:
# 6G显存配置
x_pad = 3
x_query = 10
x_center = 60
x_max = 65
else:
# 5G显存配置
x_pad = 1
x_query = 6
x_center = 38
x_max = 41
if self.gpu_mem != None and self.gpu_mem <= 4:
x_pad = 1
x_query = 5
x_center = 30
x_max = 32
return x_pad, x_query, x_center, x_max
import argparse
parser = argparse.ArgumentParser(description='Run VC inference')
parser.add_argument('--model_path', type=str, help='path to the .pth file', required=True)
parser.add_argument('--model_index_path', type=str, help='path to the .index file (empty string for none)', required=False, default='')
parser.add_argument('--hubert_model_path', type=str, help='path to the hubert model .pth file (default hubert_base.pt)',
required=False, default='hubert_base.pt')
parser.add_argument('--input_audio_filename', type=str, help='source audio file', required=True)
parser.add_argument('--output_audio_filename', type=str, help='result audio file', required=True)
########
# Default values are taken from the Gradio UI
########
parser.add_argument('--f0_up_key', type=str,
help='the f0 key for the input audio file(default "0")',
required=False, default='0')
parser.add_argument('--f0_method', type=str,
help='f0 estimation method to use: harvest (default), crepe, or pm',
required=False, default='harvest')
parser.add_argument('--index_rate', type=float,
help='The rate for the index (search feature ratio) (default 0.75)',
required=False, default=0.75) # Gradio default 0.75
parser.add_argument('--filter_radius', type=int,
help='The radius of the filter. If >=3, apply median filtering to harvested pitch results. Represents the filter radius and can reduce breathiness. (default 3)',
required=False, default=3) # Gradio default 3
parser.add_argument('--resample_sr', type=int,
help='The sample rate for resampling (post process). Set to zero for no resample. (default 0)',
required=False, default=0)
parser.add_argument('--rms_mix_rate', type=float,
help='RMS mix rate. Use the volume envelope of the input to replace or mix with the volume envelope of the output. The closer the ratio to 1, the more the output envelope is used (default 0.25)',
required=False, default=0.25) # Gradio default 0.25
parser.add_argument('--protect', type=float,
help='The protect value. Protect voiceless consonants and breath sounds to prevent artifacts such as tearing in electronic music. Set to 0.5 to disable. Decrease the value to increase protection, but may reduce indexing accuracy (default 0.33 ???)',
required=False, default=0.33) # Gradio default 0.33
# Device / precision
parser.add_argument('--device', type=str, help='compute device (eg. "cuda:0"), default "cuda:0".', required=False, default='cuda:0')
parser.add_argument('--is_half', type=bool, help='halfwidth tensors (default false)', required=False, default=False)
args = parser.parse_args()
f0up_key = args.f0_up_key
input_path = args.input_audio_filename
index_path = args.model_index_path
f0method = args.f0_method
opt_path = args.output_audio_filename
model_path = args.model_path
index_rate = args.index_rate
device = args.device
is_half = args.is_half
filter_radius = args.filter_radius
resample_sr = args.resample_sr
rms_mix_rate = args.rms_mix_rate
protect = args.protect
hubert_path = args.hubert_model_path
config = Config(device, is_half)
now_dir = os.getcwd()
sys.path.append(now_dir)
from lib.train.vc_infer_pipeline import VC
from lib.infer_pack.models import (
SynthesizerTrnMs256NSFsid,
SynthesizerTrnMs256NSFsid_nono,
SynthesizerTrnMs768NSFsid,
SynthesizerTrnMs768NSFsid_nono,
)
from lib.audio import load_audio
from fairseq import checkpoint_utils
from scipy.io import wavfile
hubert_model = None
def load_hubert(hubert_path="hubert_base.pt"):
global hubert_model
models, saved_cfg, task = checkpoint_utils.load_model_ensemble_and_task(
[hubert_path],
suffix="",
)
hubert_model = models[0]
hubert_model = hubert_model.to(device)
if is_half:
hubert_model = hubert_model.half()
else:
hubert_model = hubert_model.float()
hubert_model.eval()
def vc_single(sid, input_audio, f0_up_key, f0_file, f0_method, file_index, index_rate, hubert_path="hubert_base.pt"):
global tgt_sr, net_g, vc, hubert_model, version
if input_audio is None:
return "You need to upload an audio", None
f0_up_key = int(f0_up_key)
audio = load_audio(input_audio, 16000)
times = [0, 0, 0]
if hubert_model == None:
load_hubert(hubert_path)
if_f0 = cpt.get("f0", 1)
# audio_opt=vc.pipeline(hubert_model,net_g,sid,audio,times,f0_up_key,f0_method,file_index,file_big_npy,index_rate,if_f0,f0_file=f0_file)
audio_opt = vc.pipeline(
hubert_model,
net_g,
sid,
audio,
input_audio,
times,
f0_up_key,
f0_method,
file_index,
index_rate,
if_f0,
filter_radius,
tgt_sr,
resample_sr,
rms_mix_rate,
version,
protect,
f0_file=f0_file,
)
print(times)
return audio_opt
def get_vc(model_path):
global n_spk, tgt_sr, net_g, vc, cpt, device, is_half, version
print("loading pth %s" % model_path)
cpt = torch.load(model_path, map_location="cpu")
tgt_sr = cpt["config"][-1]
cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0] # n_spk
if_f0 = cpt.get("f0", 1)
version = cpt.get("version", "v1")
if version == "v1":
if if_f0 == 1:
net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=is_half)
else:
net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
elif version == "v2":
if if_f0 == 1: #
net_g = SynthesizerTrnMs768NSFsid(*cpt["config"], is_half=is_half)
else:
net_g = SynthesizerTrnMs768NSFsid_nono(*cpt["config"])
del net_g.enc_q
print(net_g.load_state_dict(cpt["weight"], strict=False)) # 不加这一行清不干净，真奇葩
net_g.eval().to(device)
if is_half:
net_g = net_g.half()
else:
net_g = net_g.float()
vc = VC(tgt_sr, config)
n_spk = cpt["config"][-3]
# return {"visible": True,"maximum": n_spk, "__type__": "update"}
get_vc(model_path)
file_path = input_path
wav_opt = vc_single(
0, file_path, f0up_key, None, f0method, index_path, index_rate, hubert_path
)
out_path = opt_path
wavfile.write(out_path, tgt_sr, wav_opt)
voice_conversion/rvc-v2-justin/fakeyou_rvc_tts_infer.py
+148
View File
@@ -0,0 +1,148 @@
import os, sys, pdb, torch
from piper import PiperVoice
import wave
import argparse
from scipy.io import wavfile
print("Env vars:")
print(os.environ)
print('========================================')
print('Python interpreter', sys.executable)
print('PyTorch version', torch.__version__)
print('CUDA Available?', torch.cuda.is_available())
print('CUDA Device count', torch.cuda.device_count())
print('CUDA architectures library was compiled for', torch.cuda.get_arch_list())
print('========================================', flush=True)
now_dir = os.getcwd()
sys.path.append(now_dir)
import sys
import torch
import tqdm as tq
from multiprocessing import cpu_count
class Config:
def __init__(self, device, is_half):
self.device = device
self.is_half = is_half
self.n_cpu = 0
self.gpu_name = None
self.gpu_mem = None
self.x_pad, self.x_query, self.x_center, self.x_max = self.device_config()
def device_config(self) -> tuple:
if torch.cuda.is_available():
i_device = int(self.device.split(":")[-1])
self.gpu_name = torch.cuda.get_device_name(i_device)
elif torch.backends.mps.is_available():
self.device = "mps"
else:
self.device = "cpu"
self.is_half = True
if self.n_cpu == 0:
self.n_cpu = cpu_count()
if self.is_half:
x_pad = 3
x_query = 10
x_center = 60
x_max = 65
else:
x_pad = 1
x_query = 6
x_center = 38
x_max = 41
if self.gpu_mem != None and self.gpu_mem <= 4:
x_pad = 1
x_query = 5
x_center = 30
x_max = 32
return x_pad, x_query, x_center, x_max
parser = argparse.ArgumentParser(description='Run TTS and VC inference')
parser.add_argument('--tts_model_path', type=str, required=True)
parser.add_argument('--tts_config_path', type=str, required=True)
parser.add_argument('--text', type=str, required=True)
parser.add_argument('--model_path', type=str, required=True)
parser.add_argument('--model_index_path', type=str, required=False, default='')
parser.add_argument('--hubert_model_path', type=str, required=False, default='hubert_base.pt')
parser.add_argument('--input_audio_filename', type=str, required=True)
parser.add_argument('--output_audio_filename', type=str, required=True)
parser.add_argument('--f0_up_key', type=str, required=False, default='0')
parser.add_argument('--f0_method', type=str, required=False, default='harvest')
parser.add_argument('--index_rate', type=float, required=False, default=0.75)
parser.add_argument('--filter_radius', type=int, required=False, default=3)
parser.add_argument('--resample_sr', type=int, required=False, default=0)
parser.add_argument('--rms_mix_rate', type=float, required=False, default=0.25)
parser.add_argument('--protect', type=float, required=False, default=0.33)
parser.add_argument('--device', type=str, required=False, default='cuda:0')
parser.add_argument('--is_half', type=bool, required=False, default=False)
args = parser.parse_args()
voice = PiperVoice.load(model_path=args.tts_model_path, config_path=args.tts_config_path)
with wave.open('temp.wav', "wb") as wav_file:
voice.synthesize(args.text, wav_file)
config = Config(args.device, args.is_half)
now_dir = os.getcwd()
sys.path.append(now_dir)
from lib.train.vc_infer_pipeline import VC
from lib.infer_pack.models import SynthesizerTrnMs256NSFsid, SynthesizerTrnMs256NSFsid_nono, SynthesizerTrnMs768NSFsid, SynthesizerTrnMs768NSFsid_nono
from lib.audio import load_audio
from fairseq import checkpoint_utils
hubert_model = None
def load_hubert(hubert_path="hubert_base.pt"):
global hubert_model
models, saved_cfg, task = checkpoint_utils.load_model_ensemble_and_task([hubert_path])
hubert_model = models[0]
hubert_model = hubert_model.to(args.device)
if args.is_half:
hubert_model = hubert_model.half()
def vc_single(sid, input_audio, f0_up_key, f0_file, f0_method, file_index, index_rate):
global tgt_sr, net_g, vc, hubert_model, version
if input_audio is None:
return "You need to upload an audio", None
f0_up_key = int(f0_up_key)
audio = load_audio(input_audio, 16000)
times = [0, 0, 0]
if hubert_model == None:
load_hubert()
if_f0 = cpt.get("f0", 1)
audio_opt = vc.pipeline(hubert_model, net_g, sid, audio, input_audio, times, f0_up_key, f0_method, file_index, index_rate, if_f0, args.filter_radius, tgt_sr, args.resample_sr, args.rms_mix_rate, version, args.protect, f0_file=f0_file)
print(times)
return audio_opt
def get_vc(model_path):
global tgt_sr, net_g, vc, cpt, version
cpt = torch.load(model_path, map_location="cpu")
tgt_sr = cpt["config"][-1]
cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]
if_f0 = cpt.get("f0", 1)
version = cpt.get("version", "v1")
if version == "v1":
if if_f0 == 1:
net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=args.is_half)
else:
net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
elif version == "v2":
if if_f0 == 1:
net_g = SynthesizerTrnMs768NSFsid(*cpt["config"], is_half=args.is_half)
else:
net_g = SynthesizerTrnMs768NSFsid_nono(*cpt["config"])
del net_g.enc_q
net_g.load_state_dict(cpt["weight"], strict=False)
net_g.eval().to(args.device)
if args.is_half:
net_g = net_g.half()
vc = VC(tgt_sr, config)
get_vc(args.model_path)
file_path = args.input_audio_filename
wav_opt = vc_single(0, file_path, args.f0_up_key, None, args.f0_method, args.model_index_path, args.index_rate)
out_path = args.output_audio_filename
wavfile.write(out_path, tgt_sr, wav_opt)
voice_conversion/rvc-v2-justin/go-realtime-gui-dml.bat
+2
View File
@@ -0,0 +1,2 @@
runtime\python.exe gui_v1.py --pycmd runtime\python.exe --dml
pause
voice_conversion/rvc-v2-justin/go-realtime-gui.bat
+2
View File
@@ -0,0 +1,2 @@
runtime\python.exe gui_v1.py
pause
voice_conversion/rvc-v2-justin/go-web-dml.bat
+2
View File
@@ -0,0 +1,2 @@
runtime\python.exe infer-web.py --pycmd runtime\python.exe --port 7897 --dml
pause
voice_conversion/rvc-v2-justin/go-web.bat
+2
View File
@@ -0,0 +1,2 @@
runtime\python.exe infer-web.py --pycmd runtime\python.exe --port 7897
pause
voice_conversion/rvc-v2-justin/gui_v1.py
+772
View File
@@ -0,0 +1,772 @@
import os
import logging
import sys
from dotenv import load_dotenv
load_dotenv()
os.environ["OMP_NUM_THREADS"] = "4"
if sys.platform == "darwin":
os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
now_dir = os.getcwd()
sys.path.append(now_dir)
import multiprocessing
logger = logging.getLogger(__name__)
class Harvest(multiprocessing.Process):
def __init__(self, inp_q, opt_q):
multiprocessing.Process.__init__(self)
self.inp_q = inp_q
self.opt_q = opt_q
def run(self):
import numpy as np
import pyworld
while 1:
idx, x, res_f0, n_cpu, ts = self.inp_q.get()
f0, t = pyworld.harvest(
x.astype(np.double),
fs=16000,
f0_ceil=1100,
f0_floor=50,
frame_period=10,
)
res_f0[idx] = f0
if len(res_f0.keys()) >= n_cpu:
self.opt_q.put(ts)
if __name__ == "__main__":
import json
import multiprocessing
import re
import threading
import time
import traceback
from multiprocessing import Queue, cpu_count
from queue import Empty
import librosa
from tools.torchgate import TorchGate
import numpy as np
import PySimpleGUI as sg
import sounddevice as sd
import torch
import torch.nn.functional as F
import torchaudio.transforms as tat
import tools.rvc_for_realtime as rvc_for_realtime
from i18n.i18n import I18nAuto
i18n = I18nAuto()
device = rvc_for_realtime.config.device
# device = torch.device(
# "cuda"
# if torch.cuda.is_available()
# else ("mps" if torch.backends.mps.is_available() else "cpu")
# )
current_dir = os.getcwd()
inp_q = Queue()
opt_q = Queue()
n_cpu = min(cpu_count(), 8)
for _ in range(n_cpu):
Harvest(inp_q, opt_q).start()
class GUIConfig:
def __init__(self) -> None:
self.pth_path: str = ""
self.index_path: str = ""
self.pitch: int = 0
self.samplerate: int = 40000
self.block_time: float = 1.0 # s
self.buffer_num: int = 1
self.threhold: int = -60
self.crossfade_time: float = 0.04
self.extra_time: float = 2.0
self.I_noise_reduce = False
self.O_noise_reduce = False
self.rms_mix_rate = 0.0
self.index_rate = 0.3
self.n_cpu = min(n_cpu, 6)
self.f0method = "harvest"
self.sg_input_device = ""
self.sg_output_device = ""
class GUI:
def __init__(self) -> None:
self.config = GUIConfig()
self.flag_vc = False
self.launcher()
def load(self):
input_devices, output_devices, _, _ = self.get_devices()
try:
with open("configs/config.json", "r") as j:
data = json.load(j)
data["pm"] = data["f0method"] == "pm"
data["harvest"] = data["f0method"] == "harvest"
data["crepe"] = data["f0method"] == "crepe"
data["rmvpe"] = data["f0method"] == "rmvpe"
except:
with open("configs/config.json", "w") as j:
data = {
"pth_path": " ",
"index_path": " ",
"sg_input_device": input_devices[sd.default.device[0]],
"sg_output_device": output_devices[sd.default.device[1]],
"threhold": "-60",
"pitch": "0",
"index_rate": "0",
"rms_mix_rate": "0",
"block_time": "0.25",
"crossfade_length": "0.04",
"extra_time": "2",
"f0method": "rmvpe",
}
data["pm"] = data["f0method"] == "pm"
data["harvest"] = data["f0method"] == "harvest"
data["crepe"] = data["f0method"] == "crepe"
data["rmvpe"] = data["f0method"] == "rmvpe"
return data
def launcher(self):
data = self.load()
sg.theme("LightBlue3")
input_devices, output_devices, _, _ = self.get_devices()
layout = [
[
sg.Frame(
title=i18n("加载模型"),
layout=[
[
sg.Input(
default_text=data.get("pth_path", ""),
key="pth_path",
),
sg.FileBrowse(
i18n("选择.pth文件"),
initial_folder=os.path.join(
os.getcwd(), "assets/weights"
),
file_types=((". pth"),),
),
],
[
sg.Input(
default_text=data.get("index_path", ""),
key="index_path",
),
sg.FileBrowse(
i18n("选择.index文件"),
initial_folder=os.path.join(os.getcwd(), "logs"),
file_types=((". index"),),
),
],
],
)
],
[
sg.Frame(
layout=[
[
sg.Text(i18n("输入设备")),
sg.Combo(
input_devices,
key="sg_input_device",
default_value=data.get("sg_input_device", ""),
),
],
[
sg.Text(i18n("输出设备")),
sg.Combo(
output_devices,
key="sg_output_device",
default_value=data.get("sg_output_device", ""),
),
],
[sg.Button(i18n("重载设备列表"), key="reload_devices")],
],
title=i18n("音频设备(请使用同种类驱动)"),
)
],
[
sg.Frame(
layout=[
[
sg.Text(i18n("响应阈值")),
sg.Slider(
range=(-60, 0),
key="threhold",
resolution=1,
orientation="h",
default_value=data.get("threhold", "-60"),
enable_events=True,
),
],
[
sg.Text(i18n("音调设置")),
sg.Slider(
range=(-24, 24),
key="pitch",
resolution=1,
orientation="h",
default_value=data.get("pitch", "0"),
enable_events=True,
),
],
[
sg.Text(i18n("Index Rate")),
sg.Slider(
range=(0.0, 1.0),
key="index_rate",
resolution=0.01,
orientation="h",
default_value=data.get("index_rate", "0"),
enable_events=True,
),
],
[
sg.Text(i18n("响度因子")),
sg.Slider(
range=(0.0, 1.0),
key="rms_mix_rate",
resolution=0.01,
orientation="h",
default_value=data.get("rms_mix_rate", "0"),
enable_events=True,
),
],
[
sg.Text(i18n("音高算法")),
sg.Radio(
"pm",
"f0method",
key="pm",
default=data.get("pm", "") == True,
enable_events=True,
),
sg.Radio(
"harvest",
"f0method",
key="harvest",
default=data.get("harvest", "") == True,
enable_events=True,
),
sg.Radio(
"crepe",
"f0method",
key="crepe",
default=data.get("crepe", "") == True,
enable_events=True,
),
sg.Radio(
"rmvpe",
"f0method",
key="rmvpe",
default=data.get("rmvpe", "") == True,
enable_events=True,
),
],
],
title=i18n("常规设置"),
),
sg.Frame(
layout=[
[
sg.Text(i18n("采样长度")),
sg.Slider(
range=(0.05, 2.4),
key="block_time",
resolution=0.01,
orientation="h",
default_value=data.get("block_time", "0.25"),
enable_events=True,
),
],
[
sg.Text(i18n("harvest进程数")),
sg.Slider(
range=(1, n_cpu),
key="n_cpu",
resolution=1,
orientation="h",
default_value=data.get(
"n_cpu", min(self.config.n_cpu, n_cpu)
),
enable_events=True,
),
],
[
sg.Text(i18n("淡入淡出长度")),
sg.Slider(
range=(0.01, 0.15),
key="crossfade_length",
resolution=0.01,
orientation="h",
default_value=data.get("crossfade_length", "0.04"),
enable_events=True,
),
],
[
sg.Text(i18n("额外推理时长")),
sg.Slider(
range=(0.05, 5.00),
key="extra_time",
resolution=0.01,
orientation="h",
default_value=data.get("extra_time", "2.0"),
enable_events=True,
),
],
[
sg.Checkbox(
i18n("输入降噪"),
key="I_noise_reduce",
enable_events=True,
),
sg.Checkbox(
i18n("输出降噪"),
key="O_noise_reduce",
enable_events=True,
),
],
],
title=i18n("性能设置"),
),
],
[
sg.Button(i18n("开始音频转换"), key="start_vc"),
sg.Button(i18n("停止音频转换"), key="stop_vc"),
sg.Text(i18n("推理时间(ms):")),
sg.Text("0", key="infer_time"),
],
]
self.window = sg.Window("RVC - GUI", layout=layout, finalize=True)
self.event_handler()
def event_handler(self):
while True:
event, values = self.window.read()
if event == sg.WINDOW_CLOSED:
self.flag_vc = False
exit()
if event == "reload_devices":
prev_input = self.window["sg_input_device"].get()
prev_output = self.window["sg_output_device"].get()
input_devices, output_devices, _, _ = self.get_devices(update=True)
if prev_input not in input_devices:
self.config.sg_input_device = input_devices[0]
else:
self.config.sg_input_device = prev_input
self.window["sg_input_device"].Update(values=input_devices)
self.window["sg_input_device"].Update(
value=self.config.sg_input_device
)
if prev_output not in output_devices:
self.config.sg_output_device = output_devices[0]
else:
self.config.sg_output_device = prev_output
self.window["sg_output_device"].Update(values=output_devices)
self.window["sg_output_device"].Update(
value=self.config.sg_output_device
)
if event == "start_vc" and self.flag_vc == False:
if self.set_values(values) == True:
logger.info("cuda_is_available: %s", torch.cuda.is_available())
self.start_vc()
settings = {
"pth_path": values["pth_path"],
"index_path": values["index_path"],
"sg_input_device": values["sg_input_device"],
"sg_output_device": values["sg_output_device"],
"threhold": values["threhold"],
"pitch": values["pitch"],
"rms_mix_rate": values["rms_mix_rate"],
"index_rate": values["index_rate"],
"block_time": values["block_time"],
"crossfade_length": values["crossfade_length"],
"extra_time": values["extra_time"],
"n_cpu": values["n_cpu"],
"f0method": ["pm", "harvest", "crepe", "rmvpe"][
[
values["pm"],
values["harvest"],
values["crepe"],
values["rmvpe"],
].index(True)
],
}
with open("configs/config.json", "w") as j:
json.dump(settings, j)
if event == "stop_vc" and self.flag_vc == True:
self.flag_vc = False
# Parameter hot update
if event == "threhold":
self.config.threhold = values["threhold"]
elif event == "pitch":
self.config.pitch = values["pitch"]
if hasattr(self, "rvc"):
self.rvc.change_key(values["pitch"])
elif event == "index_rate":
self.config.index_rate = values["index_rate"]
if hasattr(self, "rvc"):
self.rvc.change_index_rate(values["index_rate"])
elif event == "rms_mix_rate":
self.config.rms_mix_rate = values["rms_mix_rate"]
elif event in ["pm", "harvest", "crepe", "rmvpe"]:
self.config.f0method = event
elif event == "I_noise_reduce":
self.config.I_noise_reduce = values["I_noise_reduce"]
elif event == "O_noise_reduce":
self.config.O_noise_reduce = values["O_noise_reduce"]
elif event != "start_vc" and self.flag_vc == True:
# Other parameters do not support hot update
self.flag_vc = False
def set_values(self, values):
if len(values["pth_path"].strip()) == 0:
sg.popup(i18n("请选择pth文件"))
return False
if len(values["index_path"].strip()) == 0:
sg.popup(i18n("请选择index文件"))
return False
pattern = re.compile("[^\x00-\x7F]+")
if pattern.findall(values["pth_path"]):
sg.popup(i18n("pth文件路径不可包含中文"))
return False
if pattern.findall(values["index_path"]):
sg.popup(i18n("index文件路径不可包含中文"))
return False
self.set_devices(values["sg_input_device"], values["sg_output_device"])
self.config.pth_path = values["pth_path"]
self.config.index_path = values["index_path"]
self.config.threhold = values["threhold"]
self.config.pitch = values["pitch"]
self.config.block_time = values["block_time"]
self.config.crossfade_time = values["crossfade_length"]
self.config.extra_time = values["extra_time"]
self.config.I_noise_reduce = values["I_noise_reduce"]
self.config.O_noise_reduce = values["O_noise_reduce"]
self.config.rms_mix_rate = values["rms_mix_rate"]
self.config.index_rate = values["index_rate"]
self.config.n_cpu = values["n_cpu"]
self.config.f0method = ["pm", "harvest", "crepe", "rmvpe"][
[
values["pm"],
values["harvest"],
values["crepe"],
values["rmvpe"],
].index(True)
]
return True
def start_vc(self):
torch.cuda.empty_cache()
self.flag_vc = True
self.rvc = rvc_for_realtime.RVC(
self.config.pitch,
self.config.pth_path,
self.config.index_path,
self.config.index_rate,
self.config.n_cpu,
inp_q,
opt_q,
device,
self.rvc if hasattr(self, "rvc") else None,
)
self.config.samplerate = self.rvc.tgt_sr
self.zc = self.rvc.tgt_sr // 100
self.block_frame = (
int(np.round(self.config.block_time * self.config.samplerate / self.zc))
* self.zc
)
self.block_frame_16k = 160 * self.block_frame // self.zc
self.crossfade_frame = (
int(
np.round(
self.config.crossfade_time * self.config.samplerate / self.zc
)
)
* self.zc
)
self.sola_search_frame = self.zc
self.extra_frame = (
int(np.round(self.config.extra_time * self.config.samplerate / self.zc))
* self.zc
)
self.input_wav: torch.Tensor = torch.zeros(
self.extra_frame
+ self.crossfade_frame
+ self.sola_search_frame
+ self.block_frame,
device=device,
dtype=torch.float32,
)
self.input_wav_res: torch.Tensor = torch.zeros(
160 * self.input_wav.shape[0] // self.zc,
device=device,
dtype=torch.float32,
)
self.pitch: np.ndarray = np.zeros(
self.input_wav.shape[0] // self.zc,
dtype="int32",
)
self.pitchf: np.ndarray = np.zeros(
self.input_wav.shape[0] // self.zc,
dtype="float64",
)
self.sola_buffer: torch.Tensor = torch.zeros(
self.crossfade_frame, device=device, dtype=torch.float32
)
self.nr_buffer: torch.Tensor = self.sola_buffer.clone()
self.output_buffer: torch.Tensor = self.input_wav.clone()
self.res_buffer: torch.Tensor = torch.zeros(
2 * self.zc, device=device, dtype=torch.float32
)
self.valid_rate = 1 - (self.extra_frame - 1) / self.input_wav.shape[0]
self.fade_in_window: torch.Tensor = (
torch.sin(
0.5
* np.pi
* torch.linspace(
0.0,
1.0,
steps=self.crossfade_frame,
device=device,
dtype=torch.float32,
)
)
** 2
)
self.fade_out_window: torch.Tensor = 1 - self.fade_in_window
self.resampler = tat.Resample(
orig_freq=self.config.samplerate, new_freq=16000, dtype=torch.float32
).to(device)
self.tg = TorchGate(
sr=self.config.samplerate, n_fft=4 * self.zc, prop_decrease=0.9
).to(device)
thread_vc = threading.Thread(target=self.soundinput)
thread_vc.start()
def soundinput(self):
"""
接受音频输入
"""
channels = 1 if sys.platform == "darwin" else 2
with sd.Stream(
channels=channels,
callback=self.audio_callback,
blocksize=self.block_frame,
samplerate=self.config.samplerate,
dtype="float32",
):
while self.flag_vc:
time.sleep(self.config.block_time)
logger.debug("Audio block passed.")
logger.debug("ENDing VC")
def audio_callback(
self, indata: np.ndarray, outdata: np.ndarray, frames, times, status
):
"""
音频处理
"""
start_time = time.perf_counter()
indata = librosa.to_mono(indata.T)
if self.config.threhold > -60:
rms = librosa.feature.rms(
y=indata, frame_length=4 * self.zc, hop_length=self.zc
)
db_threhold = (
librosa.amplitude_to_db(rms, ref=1.0)[0] < self.config.threhold
)
for i in range(db_threhold.shape[0]):
if db_threhold[i]:
indata[i * self.zc : (i + 1) * self.zc] = 0
self.input_wav[: -self.block_frame] = self.input_wav[
self.block_frame :
].clone()
self.input_wav[-self.block_frame :] = torch.from_numpy(indata).to(device)
self.input_wav_res[: -self.block_frame_16k] = self.input_wav_res[
self.block_frame_16k :
].clone()
# input noise reduction and resampling
if self.config.I_noise_reduce:
input_wav = self.input_wav[
-self.crossfade_frame - self.block_frame - 2 * self.zc :
]
input_wav = self.tg(
input_wav.unsqueeze(0), self.input_wav.unsqueeze(0)
)[0, 2 * self.zc :]
input_wav[: self.crossfade_frame] *= self.fade_in_window
input_wav[: self.crossfade_frame] += (
self.nr_buffer * self.fade_out_window
)
self.nr_buffer[:] = input_wav[-self.crossfade_frame :]
input_wav = torch.cat(
(self.res_buffer[:], input_wav[: self.block_frame])
)
self.res_buffer[:] = input_wav[-2 * self.zc :]
self.input_wav_res[-self.block_frame_16k - 160 :] = self.resampler(
input_wav
)[160:]
else:
self.input_wav_res[-self.block_frame_16k - 160 :] = self.resampler(
self.input_wav[-self.block_frame - 2 * self.zc :]
)[160:]
# infer
f0_extractor_frame = self.block_frame_16k + 800
if self.config.f0method == "rmvpe":
f0_extractor_frame = 5120 * ((f0_extractor_frame - 1) // 5120 + 1)
infer_wav = self.rvc.infer(
self.input_wav_res,
self.input_wav_res[-f0_extractor_frame:].cpu().numpy(),
self.block_frame_16k,
self.valid_rate,
self.pitch,
self.pitchf,
self.config.f0method,
)
infer_wav = infer_wav[
-self.crossfade_frame - self.sola_search_frame - self.block_frame :
]
# output noise reduction
if self.config.O_noise_reduce:
self.output_buffer[: -self.block_frame] = self.output_buffer[
self.block_frame :
].clone()
self.output_buffer[-self.block_frame :] = infer_wav[-self.block_frame :]
infer_wav = self.tg(
infer_wav.unsqueeze(0), self.output_buffer.unsqueeze(0)
).squeeze(0)
# volume envelop mixing
if self.config.rms_mix_rate < 1:
rms1 = librosa.feature.rms(
y=self.input_wav_res[-160 * infer_wav.shape[0] // self.zc :]
.cpu()
.numpy(),
frame_length=640,
hop_length=160,
)
rms1 = torch.from_numpy(rms1).to(device)
rms1 = F.interpolate(
rms1.unsqueeze(0),
size=infer_wav.shape[0] + 1,
mode="linear",
align_corners=True,
)[0, 0, :-1]
rms2 = librosa.feature.rms(
y=infer_wav[:].cpu().numpy(),
frame_length=4 * self.zc,
hop_length=self.zc,
)
rms2 = torch.from_numpy(rms2).to(device)
rms2 = F.interpolate(
rms2.unsqueeze(0),
size=infer_wav.shape[0] + 1,
mode="linear",
align_corners=True,
)[0, 0, :-1]
rms2 = torch.max(rms2, torch.zeros_like(rms2) + 1e-3)
infer_wav *= torch.pow(
rms1 / rms2, torch.tensor(1 - self.config.rms_mix_rate)
)
# SOLA algorithm from https://github.com/yxlllc/DDSP-SVC
conv_input = infer_wav[
None, None, : self.crossfade_frame + self.sola_search_frame
]
cor_nom = F.conv1d(conv_input, self.sola_buffer[None, None, :])
cor_den = torch.sqrt(
F.conv1d(
conv_input**2,
torch.ones(1, 1, self.crossfade_frame, device=device),
)
+ 1e-8
)
if sys.platform == "darwin":
_, sola_offset = torch.max(cor_nom[0, 0] / cor_den[0, 0])
sola_offset = sola_offset.item()
else:
sola_offset = torch.argmax(cor_nom[0, 0] / cor_den[0, 0])
logger.debug("sola_offset = %d", int(sola_offset))
infer_wav = infer_wav[
sola_offset : sola_offset + self.block_frame + self.crossfade_frame
]
infer_wav[: self.crossfade_frame] *= self.fade_in_window
infer_wav[: self.crossfade_frame] += self.sola_buffer * self.fade_out_window
self.sola_buffer[:] = infer_wav[-self.crossfade_frame :]
if sys.platform == "darwin":
outdata[:] = (
infer_wav[: -self.crossfade_frame].cpu().numpy()[:, np.newaxis]
)
else:
outdata[:] = (
infer_wav[: -self.crossfade_frame].repeat(2, 1).t().cpu().numpy()
)
total_time = time.perf_counter() - start_time
self.window["infer_time"].update(int(total_time * 1000))
logger.info("Infer time: %.2f", total_time)
def get_devices(self, update: bool = True):
"""获取设备列表"""
if update:
sd._terminate()
sd._initialize()
devices = sd.query_devices()
hostapis = sd.query_hostapis()
for hostapi in hostapis:
for device_idx in hostapi["devices"]:
devices[device_idx]["hostapi_name"] = hostapi["name"]
input_devices = [
f"{d['name']} ({d['hostapi_name']})"
for d in devices
if d["max_input_channels"] > 0
]
output_devices = [
f"{d['name']} ({d['hostapi_name']})"
for d in devices
if d["max_output_channels"] > 0
]
input_devices_indices = [
d["index"] if "index" in d else d["name"]
for d in devices
if d["max_input_channels"] > 0
]
output_devices_indices = [
d["index"] if "index" in d else d["name"]
for d in devices
if d["max_output_channels"] > 0
]
return (
input_devices,
output_devices,
input_devices_indices,
output_devices_indices,
)
def set_devices(self, input_device, output_device):
"""设置输出设备"""
(
input_devices,
output_devices,
input_device_indices,
output_device_indices,
) = self.get_devices()
sd.default.device[0] = input_device_indices[
input_devices.index(input_device)
]
sd.default.device[1] = output_device_indices[
output_devices.index(output_device)
]
logger.info("Input device: %s:%s", str(sd.default.device[0]), input_device)
logger.info(
"Output device: %s:%s", str(sd.default.device[1]), output_device
)
gui = GUI()
voice_conversion/rvc-v2-justin/infer-web.py
+1506
View File
File diff suppressed because it is too large Load Diff
voice_conversion/rvc-v2-justin/poetry.lock
Generated
+3885
View File
File diff suppressed because it is too large Load Diff
voice_conversion/rvc-v2-justin/pyproject.toml
+63
View File
@@ -0,0 +1,63 @@
[tool.poetry]
name = "rvc-beta"
version = "0.1.0"
description = ""
authors = ["lj1995"]
license = "MIT"
[tool.poetry.dependencies]
python = "^3.8"
torch = "^2.0.0"
torchaudio = "^2.0.1"
Cython = "^0.29.34"
gradio = "^3.34.0"
future = "^0.18.3"
pydub = "^0.25.1"
soundfile = "^0.12.1"
ffmpeg-python = "^0.2.0"
tensorboardX = "^2.6"
functorch = "^2.0.0"
fairseq = "^0.12.2"
faiss-cpu = "^1.7.2"
Jinja2 = "^3.1.2"
json5 = "^0.9.11"
librosa = "0.9.1"
llvmlite = "0.39.0"
Markdown = "^3.4.3"
matplotlib = "^3.7.1"
matplotlib-inline = "^0.1.6"
numba = "0.56.4"
numpy = "1.23.5"
scipy = "1.9.3"
praat-parselmouth = "^0.4.3"
Pillow = "9.3.0"
pyworld = "^0.3.2"
resampy = "^0.4.2"
scikit-learn = "^1.2.2"
starlette = "^0.27.0"
tensorboard = "^2.12.1"
tensorboard-data-server = "^0.7.0"
tensorboard-plugin-wit = "^1.8.1"
torchgen = "^0.0.1"
tqdm = "^4.65.0"
tornado = "^6.3"
Werkzeug = "^2.2.3"
uc-micro-py = "^1.0.1"
sympy = "^1.11.1"
tabulate = "^0.9.0"
PyYAML = "^6.0"
pyasn1 = "^0.4.8"
pyasn1-modules = "^0.2.8"
fsspec = "^2023.3.0"
absl-py = "^1.4.0"
audioread = "^3.0.0"
uvicorn = "^0.21.1"
colorama = "^0.4.6"
torchcrepe = "0.0.20"
python-dotenv = "^1.0.0"
[tool.poetry.dev-dependencies]
[build-system]
requires = ["poetry-core>=1.0.0"]
build-backend = "poetry.core.masonry.api"
voice_conversion/rvc-v2-justin/requirements-amd.txt
+48
View File
@@ -0,0 +1,48 @@
tensorflow-rocm
joblib>=1.1.0
numba==0.56.4
numpy==1.23.5
scipy
librosa==0.9.1
llvmlite==0.39.0
fairseq==0.12.2
faiss-cpu==1.7.3
gradio==3.34.0
Cython
pydub>=0.25.1
soundfile>=0.12.1
ffmpeg-python>=0.2.0
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
onnxruntime-gpu
torchcrepe==0.0.20
fastapi==0.88
ffmpy==0.3.1
python-dotenv>=1.0.0
av
voice_conversion/rvc-v2-justin/requirements-dml.txt
+46
View File
@@ -0,0 +1,46 @@
joblib>=1.1.0
numba==0.56.4
numpy==1.23.5
scipy
librosa==0.9.1
llvmlite==0.39.0
fairseq==0.12.2
faiss-cpu==1.7.3
gradio==3.34.0
Cython
pydub>=0.25.1
soundfile>=0.12.1
ffmpeg-python>=0.2.0
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-directml
torchcrepe==0.0.20
fastapi==0.88
ffmpy==0.3.1
python-dotenv>=1.0.0
av
voice_conversion/rvc-v2-justin/requirements-ipex.txt
+54
View File
@@ -0,0 +1,54 @@
torch==2.0.1a0
intel_extension_for_pytorch==2.0.110+xpu
torchvision==0.15.2a0
https://github.com/Disty0/Retrieval-based-Voice-Conversion-WebUI/releases/download/torchaudio_wheels_for_ipex/torchaudio-2.0.2+31de77d-cp310-cp310-linux_x86_64.whl
-f https://developer.intel.com/ipex-whl-stable-xpu
joblib>=1.1.0
numba==0.56.4
numpy==1.23.5
scipy
librosa==0.9.1
llvmlite==0.39.0
fairseq==0.12.2
faiss-cpu==1.7.3
gradio==3.34.0
Cython
pydub>=0.25.1
soundfile>=0.12.1
ffmpeg-python>=0.2.0
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==0.0.20
fastapi==0.88
ffmpy==0.3.1
python-dotenv>=1.0.0
av
PySimpleGUI
sounddevice
voice_conversion/rvc-v2-justin/requirements-win-for-realtime_vc_gui-dml.txt
+29
View File
@@ -0,0 +1,29 @@
#1.Install torch from pytorch.org:
#torch 2.0 with cuda 11.8
#pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
#torch 1.11.0 with cuda 11.3
#pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0 --extra-index-url https://download.pytorch.org/whl/cu113
einops
fairseq
flask
flask_cors
gin
gin_config
librosa
local_attention
matplotlib
praat-parselmouth
pyworld
PyYAML
resampy
scikit_learn
scipy
SoundFile
tensorboard
tqdm
wave
PySimpleGUI
sounddevice
gradio
noisereduce
onnxruntime-directml
voice_conversion/rvc-v2-justin/requirements-win-for-realtime_vc_gui.txt
+28
View File
@@ -0,0 +1,28 @@
#1.Install torch from pytorch.org:
#torch 2.0 with cuda 11.8
#pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
#torch 1.11.0 with cuda 11.3
#pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0 --extra-index-url https://download.pytorch.org/whl/cu113
einops
fairseq
flask
flask_cors
gin
gin_config
librosa
local_attention
matplotlib
praat-parselmouth
pyworld
PyYAML
resampy
scikit_learn
scipy
SoundFile
tensorboard
tqdm
wave
PySimpleGUI
sounddevice
gradio
noisereduce
voice_conversion/rvc-v2-justin/requirements.txt
+47
View File
@@ -0,0 +1,47 @@
joblib>=1.1.0
numba==0.56.4
numpy==1.23.5
scipy
librosa==0.9.1
llvmlite==0.39.0
fairseq==0.12.2
faiss-cpu==1.7.3
gradio==3.34.0
Cython
pydub>=0.25.1
soundfile>=0.12.1
ffmpeg-python>=0.2.0
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==0.0.20
fastapi==0.88
ffmpy==0.3.1
python-dotenv>=1.0.0
av
voice_conversion/rvc-v2-justin/run.sh
+61
View File
@@ -0,0 +1,61 @@
#!/bin/bash
if [[ "$(uname)" == "Darwin" ]]; then
# macOS specific env:
export PYTORCH_ENABLE_MPS_FALLBACK=1
export PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0
elif [[ "$(uname)" != "Linux" ]]; then
echo "Unsupported operating system."
exit 1
fi
if [ -d ".venv" ]; then
echo "Activate venv..."
source .venv/bin/activate
else
echo "Create venv..."
requirements_file="requirements.txt"
# Check if Python 3.8 is installed
if ! command -v python3 &> /dev/null; then
echo "Python 3 not found. Attempting to install 3.8..."
if [[ "$(uname)" == "Darwin" ]] && command -v brew &> /dev/null; then
brew install python@3.8
elif [[ "$(uname)" == "Linux" ]] && command -v apt-get &> /dev/null; then
sudo apt-get update
sudo apt-get install python3.8
else
echo "Please install Python 3.8 manually."
exit 1
fi
fi
python3 -m venv .venv
source .venv/bin/activate
# Check if required packages are installed and install them if not
if [ -f "${requirements_file}" ]; then
installed_packages=$(python3 -m pip freeze)
while IFS= read -r package; do
[[ "${package}" =~ ^#.* ]] && continue
package_name=$(echo "${package}" | sed 's/[<>=!].*//')
if ! echo "${installed_packages}" | grep -q "${package_name}"; then
echo "${package_name} not found. Attempting to install..."
python3 -m pip install --upgrade "${package}"
fi
done < "${requirements_file}"
else
echo "${requirements_file} not found. Please ensure the requirements file with required packages exists."
exit 1
fi
fi
# Download models
./tools/dlmodels.sh
if [[ $? -ne 0 ]]; then
exit 1
fi
# Run the main script
python3 infer-web.py --pycmd python3
voice_conversion/rvc-v2-justin/venv.sh
+1
View File
@@ -0,0 +1 @@
python3.8 -m venv .venv