From 10b74d70a5ccba1bd42a55c15481c1b6f20423e6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=BA=90=E6=96=87=E9=9B=A8?= <41315874+fumiama@users.noreply.github.com> Date: Sat, 1 Apr 2023 19:58:33 +0800 Subject: [PATCH] add colab --- README.md | 2 + Retrieval_based_Voice_Conversion_WebUI.ipynb | 211 +++++++++++++++++++ infer-web.py | 1 + 3 files changed, 214 insertions(+) create mode 100644 Retrieval_based_Voice_Conversion_WebUI.ipynb diff --git a/README.md b/README.md index 98d576a..37cba22 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,7 @@ # Retrieval-based-Voice-Conversion-WebUI +[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb) + 缺失的2个文件夹和2个文件： hubert_base.pt diff --git a/Retrieval_based_Voice_Conversion_WebUI.ipynb b/Retrieval_based_Voice_Conversion_WebUI.ipynb new file mode 100644 index 0000000..125beb1 --- /dev/null +++ b/Retrieval_based_Voice_Conversion_WebUI.ipynb @@ -0,0 +1,211 @@ +{ + "cells": [ + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/liujing04/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": "markdown", + "metadata": {}, + "source": [] + }, + { + "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-gpu fairseq gradio 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 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": "UG3XpUwEomUz" + }, + "outputs": [], + "source": [ + "!apt -y install -qq aria2\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", + "!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\n", + "\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": { + "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 = \"/content/drive/MyDrive/dataset/lulu20230327.zip\" #@param {type:\"string\"}\n", + "\n", + "from google.colab import drive\n", + "drive.mount('/content/drive')\n", + "!mkdir -p /content/dataset\n", + "!unzip -d /content/dataset {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", + "!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 = 3540 #@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 = 730 #@param {type:\"integer\"}\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" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "ZKAyuKb9J6dz" + }, + "outputs": [], + "source": [ + "#@title 手动训练（不推荐）\n", + "#@markdown 模型名\n", + "MODELNAME = \"lulu\" #@param {type:\"string\"}\n", + "\n", + "!python3 trainset_preprocess_pipeline_print.py /content/dataset 32000 8 logs/{MODELNAME} True\n", + "\n", + "!python3 extract_feature_print.py 1 0 0 logs/{MODELNAME}\n", + "\n", + "!python3 train_nsf_sim_cache_sid_load_pretrain.py -e lulu -sr 32k -f0 0 -g 0 -bs 4 -te 10 -se 5 -pg pretrained/G32k.pth -pd pretrained/D32k.pth -l 0 -c 0\n" + ] + } + ], + "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 +} diff --git a/infer-web.py b/infer-web.py index db875a2..403ac7c 100644 --- a/infer-web.py +++ b/infer-web.py @@ -182,6 +182,7 @@ def get_vc(sid): return {"visible": True,"maximum": n_spk, "__type__": "update"} def change_choices(): + names=[] for name in os.listdir(weight_root): if name.endswith(".pth"): names.append(name) return {"choices": sorted(names), "__type__": "update"}