PublicMirrors/voice-changer
1
0
Fork 0
mirror of https://github.com/w-okada/voice-changer.git synced 2025-01-23 05:25:01 +03:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'master' of github.com:w-okada/voice-changer

Browse Source
This commit is contained in:
w-okada 2023-09-23 03:28:43 +09:00
commit 25cba16e5f
8 changed files with 327 additions and 326 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
.github/FAQ.md vendored Normal file
View File

@ -0,0 +1,24 @@
# Frequently Asked Questions
Please read this FAQ before asking or making a bug report.
### General fixes:
*Do all these steps so you can fix some issues.*
- Restart the application
- Go to your Windows %AppData% (Win + R, then put %appdata% and press Enter) and delete the "**voice-changer-native-client**" folder
- Extract your .zip to a new location and avoid folders with space or specials characters (also avoid long file paths)
- If you don't have a GPU or have a too old GPU, try using the [Colab Version](https://colab.research.google.com/github/w-okada/voice-changer/blob/master/Realtime_Voice_Changer_on_Colab.ipynb) instead
### 1. AMD GPU don't appear or not working
> Please download the **latest DirectML version**, use the **f0 det. rmvpe_onnx** and .ONNX models only! (.pth models do not work properly, use the "Export to ONNX" it can take a while)
### 2. NVidia GPU don't appear or not working
> Make sure that the [NVidia CUDA Toolkit](https://developer.nvidia.com/cuda-downloads) drivers are installed on your PC and up-to-date
### 3. High CPU usage
> Decrease your EXTRA value and put the index feature to 0
### 4. High Latency
> Decrease your chunk value until you find a good mix of quality and response time
### 5. I'm hearing my voice without changes
> Make sure to disable **passthru** mode

22
.github/ISSUE_TEMPLATE/feature-request.yaml vendored Normal file
View File

@ -0,0 +1,22 @@
name: Feature Request
description: Do you have some feature request? Use this template
title: "[REQUEST]: "
body:
- type: markdown
attributes:
value: When creating a feature request, please be aware that **we do not guarantee that your idea will be implemented**. We are always working to make our software better, so please be pacient and do not put pressure on our devs.
- type: input
id: few-words
attributes:
label: In a few words, describe your idea
description: With a few words, briefly describe your idea
placeholder: ex. My idea is to implement rmvpe!
validations:
required: true
- type: textarea
id: request
attributes:
label: More information
description: If you have a complex idea, please use this field to describe it more, please provide enough information so we can understand and implement your idea
validations:
required: false

120
.github/ISSUE_TEMPLATE/issue.yaml vendored
View File

@ -1,132 +1,66 @@
name: Issue
name: Issue or Bug Report
description: Please provide as much detail as possible to convey the history of your problem.
title: "[ISSUE]: "
body:
- type: dropdown
id: issue-type
- type: markdown
attributes:
label: Issue Type
description: What type of issue would you like to report?
multiple: true
options:
- Feature Request
- Documentation Feature Request
- Bug Report
- Question
- Others
validations:
required: true
value: Please read our [FAQ](https://github.com/w-okada/voice-changer/blob/master/.github/FAQ.md) before making a bug report!
- type: input
id: vc-client-version
attributes:
label: vc client version number
description: filename of you download(.zip)
label: Voice Changer Version
description: Downloaded File Name (.zip)
placeholder: MMVCServerSIO_xxx_yyyy-zzzz_v.x.x.x.x.zip
validations:
required: true
- type: input
id: OS
attributes:
label: OS
description: OS name and version. e.g. Windows 10, Ubuntu 20.04, if you use mac, M1 or Intel.(Intel is not supported) and version venture, monterey, big sur.
label: Operational System
description: e.g. Windows 10, Ubuntu 20.04, MacOS Venture, MacOS Monterey, etc...
placeholder: Windows 10
validations:
required: true
- type: input
id: GPU
attributes:
label: GPU
description: GPU. If you have no gpu, please input none.
description: If you have no gpu, please input none.
validations:
required: true
- type: dropdown
id: clear-setting
- type: checkboxes
id: checks
attributes:
label: Clear setting
description: Have you tried clear setting?
label: Read carefully and check the options
options:
- "no"
- "yes"
validations:
required: true
- type: dropdown
id: sample-model
attributes:
label: Sample model
description: Sample model work fine
options:
- "no"
- "yes"
validations:
required: true
- type: dropdown
id: input-chunk-num
attributes:
label: Input chunk num
description: Have you tried to change input chunk num?
options:
- "no"
- "yes"
validations:
required: true
- type: dropdown
id: wait-for-launch
attributes:
label: Wait for a while
description: If the GUI won't start up, wait a several minutes. Alternatively, have you excluded it from your virus-checking software (at your own risk)?
options:
- "The GUI successfully launched."
- "no"
- "yes"
validations:
required: true
- type: dropdown
id: read-tutorial
attributes:
label: read tutorial
description: Have you read the tutorial? https://github.com/w-okada/voice-changer/blob/master/tutorials/tutorial_rvc_en_latest.md
options:
- "no"
- "yes"
validations:
required: true
- type: dropdown
id: extract-to-new-folder
attributes:
label: Extract files to a new folder.
description: Extract files from a zip file to a new folder, different from the previous version.(If you have.)
options:
- "no"
- "yes"
validations:
required: true
- label: I've tried to Clear Settings
- label: Sample/Default Models are working
- label: I've tried to change the Chunk Size
- label: GUI was successfully launched
- label: I've read the [tutorial](https://github.com/w-okada/voice-changer/blob/master/tutorials/tutorial_rvc_en_latest.md)
- label: I've tried to extract to another folder (or re-extract) the .zip file
- type: input
id: vc-type
attributes:
label: Voice Changer type
description: Which type of voice changer you use? e.g. MMVC v1.3, RVC
label: Model Type
description: MMVC, so-vits-rvc, RVC, DDSP-SVC
placeholder: RVC
validations:
required: true
- type: input
id: model-type
attributes:
label: Model type
description: List up the type of model you use? e.g. pyTorch, ONNX, f0, no f0
validations:
required: true
- type: textarea
id: issue
attributes:
label: Situation
description: Developers spend a lot of time developing new features and resolving issues. If you really want to get it solved, please provide as much reproducible information and logs as possible. Provide logs on the terminal and capture the appkication window.
label: Issue Description
description: Please provide as much reproducible information and logs as possible
- type: textarea
id: capture
attributes:
label: application window capture
description: the appkication window.
label: Application Screenshot
description: Please provide a screenshot of your application so we can see your settings (you can paste or drag-n-drop)
- type: textarea
id: logs-on-terminal
attributes:
label: logs on terminal
description: logs on terminal.
label: Logs on console
description: Copy and paste the log on your console here
validations:
required: true

13
.github/ISSUE_TEMPLATE/question.yaml vendored Normal file
View File

@ -0,0 +1,13 @@
name: Question or Other
description: Do you any question? Use this template
body:
- type: markdown
attributes:
value: We are always working to make our software better, so please be pacient and wait for a response
- type: textarea
id: question
attributes:
label: Description
description: What is your question? (or other non-related to bugs/feature-request)
validations:
required: true

99
Kaggle_RealtimeVoiceChanger.ipynb Normal file
View File

@ -0,0 +1,99 @@
{
"metadata":{
"kernelspec":{
"language":"python",
"display_name":"Python 3",
"name":"python3"
},
"language_info":{
"name":"python",
"version":"3.10.12",
"mimetype":"text/x-python",
"codemirror_mode":{
"name":"ipython",
"version":3
},
"pygments_lexer":"ipython3",
"nbconvert_exporter":"python",
"file_extension":".py"
}
},
"nbformat_minor":4,
"nbformat":4,
"cells":[
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://www.kaggle.com/code/rafacasari/wokada-voice-changer\" target=\"_parent\"><img src=\"https://img.shields.io/badge/Open%20In%20Kaggle-035a7d?style=for-the-badge&logo=kaggle&logoColor=white\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type":"markdown",
"source":"### [w-okada's Voice Changer](https://github.com/w-okada/voice-changer) | **Kaggle**\n\n---\n\n## **⬇ VERY IMPORTANT ⬇**\n\nYou can use the following settings for better results:\n\nIf you're using a index: `f0: RMVPE_ONNX | Chunk: 112 or higher | Extra: 8192`<br>\nIf you're not using a index: `f0: RMVPE_ONNX | Chunk: 96 or higher | Extra: 16384`<br>\n**Don't forget to select a GPU in the GPU field, <b>NEVER</b> use CPU!\n> Seems that PTH models performance better than ONNX for now, you can still try ONNX models and see if it satisfies you\n\n\n*You can always [click here](https://github.com/YunaOneeChan/Voice-Changer-Settings) to check if these settings are up-to-date*\n\n---\n**Credits**<br>\nRealtime Voice Changer by [w-okada](https://github.com/w-okada)<br>\nNotebook files updated by [rafacasari](https://github.com/Rafacasari)<br>\nRecommended settings by [YunaOneeChan](https://github.com/YunaOneeChan)\n\n**Need help?** [AI Hub Discord](https://discord.gg/aihub) » ***#help-realtime-vc***\n\n---",
"metadata":{
"id":"Lbbmx_Vjl0zo"
}
},
{
"cell_type":"markdown",
"source":"# Kaggle Tutorial\nRunning this notebook can be a bit complicated.\\\nAfter created your Kaggle account, you'll need to **verify your phone number** to be able to use Internet Connection and GPUs.\\\nFollow the instructions on the image below.\n\n## <font color=blue>*You can use <b>GPU P100</b> instead of GPU T4, some people are telling that <b>P100 is better</b>.*</font>\n![instructions.png](https://i.imgur.com/0NutkD8.png)",
"metadata":{
}
},
{
"cell_type":"markdown",
"source":"# Clone repository and install dependencies\nThis first step will download the latest version of Voice Changer and install the dependencies. **It will take some time to complete.**",
"metadata":{
}
},
{
"cell_type":"code",
"source":"# This will make that we're on the right folder before installing\n%cd /kaggle/working/\n\n!pip install colorama --quiet\nfrom colorama import Fore, Style\nimport os\n\nprint(f\"{Fore.CYAN}> Cloning the repository...{Style.RESET_ALL}\")\n!git clone https://github.com/w-okada/voice-changer.git --quiet\nprint(f\"{Fore.GREEN}> Successfully cloned the repository!{Style.RESET_ALL}\")\n%cd voice-changer/server/\n\nprint(f\"{Fore.CYAN}> Installing libportaudio2...{Style.RESET_ALL}\")\n!apt-get -y install libportaudio2 -qq\n\nprint(f\"{Fore.CYAN}> Installing pre-dependencies...{Style.RESET_ALL}\")\n# Install dependencies that are missing from requirements.txt and pyngrok\n!pip install faiss-gpu fairseq pyngrok --quiet \n!pip install pyworld --no-build-isolation --quiet\nprint(f\"{Fore.CYAN}> Installing dependencies from requirements.txt...{Style.RESET_ALL}\")\n!pip install -r requirements.txt --quiet\n\n# Download the default settings ^-^\nif not os.path.exists(\"/kaggle/working/voice-changer/server/stored_setting.json\"):\n !wget -q https://gist.githubusercontent.com/Rafacasari/d820d945497a01112e1a9ba331cbad4f/raw/8e0a426c22688b05dd9c541648bceab27e422dd6/kaggle_setting.json -O /kaggle/working/voice-changer/server/stored_setting.json\nprint(f\"{Fore.GREEN}> Successfully installed all packages!{Style.RESET_ALL}\")\n\nprint(f\"{Fore.GREEN}> You can safely ignore the dependency conflict errors, it's a error from Kaggle and don't interfer on Voice Changer!{Style.RESET_ALL}\")",
"metadata":{
"id":"86wTFmqsNMnD",
"cellView":"form",
"_kg_hide-output":false,
"execution":{
"iopub.status.busy":"2023-09-14T04:01:17.308284Z",
"iopub.execute_input":"2023-09-14T04:01:17.308682Z",
"iopub.status.idle":"2023-09-14T04:08:08.475375Z",
"shell.execute_reply.started":"2023-09-14T04:01:17.308652Z",
"shell.execute_reply":"2023-09-14T04:08:08.473827Z"
},
"trusted":true
},
"execution_count":0,
"outputs":[
]
},
{
"cell_type":"markdown",
"source":"# Start Server **using ngrok**\nThis cell will start the server, the first time that you run it will download the models, so it can take a while (~1-2 minutes)\n\n---\nYou'll need a ngrok account, but <font color=green>**it's free**</font> and easy to create!\n---\n**1** - Create a **free** account at [ngrok](https://dashboard.ngrok.com/signup)\\\n**2** - If you didn't logged in with Google or Github, you will need to **verify your e-mail**!\\\n**3** - Click [this link](https://dashboard.ngrok.com/get-started/your-authtoken) to get your auth token, and replace **YOUR_TOKEN_HERE** with your token.\\\n**4** - *(optional)* Change to a region near to you",
"metadata":{
}
},
{
"cell_type":"code",
"source":"# ---------------------------------\n# SETTINGS\n# ---------------------------------\n\nToken = '2Tn2hbfLtw2ii6DHEJy7SsM1BjI_21G14MXSwz7qZSDL2Dv3B'\nClearConsole = True # Clear console after initialization. Set to False if you are having some error, then you will be able to report it.\nRegion = \"sa\" # Read the instructions below\n\n# You can change the region for a better latency, use only the abbreviation\n# Choose between this options: \n# us -> United States (Ohio)\n# ap -> Asia/Pacific (Singapore)\n# au -> Australia (Sydney)\n# eu -> Europe (Frankfurt)\n# in -> India (Mumbai)\n# jp -> Japan (Tokyo)\n# sa -> South America (Sao Paulo)\n\n# ---------------------------------\n# DO NOT TOUCH ANYTHING DOWN BELOW!\n# ---------------------------------\n\n%cd /kaggle/working/voice-changer/server\n \nfrom pyngrok import conf, ngrok\nMyConfig = conf.PyngrokConfig()\nMyConfig.auth_token = Token\nMyConfig.region = Region\n#conf.get_default().authtoken = Token\n#conf.get_default().region = Region\nconf.set_default(MyConfig);\n\nimport subprocess, threading, time, socket, urllib.request\nPORT = 8000\n\nfrom pyngrok import ngrok\nngrokConnection = ngrok.connect(PORT)\npublic_url = ngrokConnection.public_url\n\nfrom IPython.display import clear_output\n\ndef wait_for_server():\n while True:\n time.sleep(0.5)\n sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)\n result = sock.connect_ex(('127.0.0.1', PORT))\n if result == 0:\n break\n sock.close()\n if ClearConsole:\n clear_output()\n print(\"--------- SERVER READY! ---------\")\n print(\"Your server is available at:\")\n print(public_url)\n print(\"---------------------------------\")\n\nthreading.Thread(target=wait_for_server, daemon=True).start()\n\n!python3 MMVCServerSIO.py \\\n -p {PORT} \\\n --https False \\\n --content_vec_500 pretrain/checkpoint_best_legacy_500.pt \\\n --content_vec_500_onnx pretrain/content_vec_500.onnx \\\n --content_vec_500_onnx_on true \\\n --hubert_base pretrain/hubert_base.pt \\\n --hubert_base_jp pretrain/rinna_hubert_base_jp.pt \\\n --hubert_soft pretrain/hubert/hubert-soft-0d54a1f4.pt \\\n --nsf_hifigan pretrain/nsf_hifigan/model \\\n --crepe_onnx_full pretrain/crepe_onnx_full.onnx \\\n --crepe_onnx_tiny pretrain/crepe_onnx_tiny.onnx \\\n --rmvpe pretrain/rmvpe.pt \\\n --model_dir model_dir \\\n --samples samples.json\n\nngrok.disconnect(ngrokConnection.public_url)",
"metadata":{
"id":"lLWQuUd7WW9U",
"cellView":"form",
"_kg_hide-input":false,
"scrolled":true,
"trusted":true
},
"execution_count":null,
"outputs":[
]
}
]
}

349
Realtime_Voice_Changer_on_Colab.ipynb
View File

@ -1,6 +1,6 @@
{
"cells": [
{
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
@ -12,264 +12,146 @@
},
{
"cell_type": "markdown",
"metadata": {
"id": "Lbbmx_Vjl0zo"
},
"source": [
"### w-okada's Voice Changer | **Google Colab**\n",
"### [w-okada's Voice Changer](https://github.com/w-okada/voice-changer) | **Colab**\n",
"\n",
"---\n",
"\n",
"##**READ ME - VERY IMPORTANT**\n",
"## **⬇ VERY IMPORTANT ⬇**\n",
"\n",
"This is an attempt to run [Realtime Voice Changer](https://github.com/w-okada/voice-changer) on Google Colab, still not perfect but is totally usable, you can use the following settings for better results:\n",
"You can use the following settings for better results:\n",
"\n",
"If you're using a index: `f0: RMVPE_ONNX | Chunk: 112 or higher | Extra: 8192`\\\n",
"If you're not using a index: `f0: RMVPE_ONNX | Chunk: 96 or higher | Extra: 16384`\\\n",
"**Don't forget to select your Colab GPU in the GPU field (<b>Tesla T4</b>, for free users)*\n",
"If you're using a index: `f0: RMVPE_ONNX | Chunk: 112 or higher | Extra: 8192`<br>\n",
"If you're not using a index: `f0: RMVPE_ONNX | Chunk: 96 or higher | Extra: 16384`<br>\n",
"**Don't forget to select a T4 GPU in the GPU field, <b>NEVER</b> use CPU!\n",
"> Seems that PTH models performance better than ONNX for now, you can still try ONNX models and see if it satisfies you\n",
"\n",
"\n",
"*You can always [click here](https://github.com/YunaOneeChan/Voice-Changer-Settings) to check if these settings are up-to-date*\n",
"<br><br>\n",
"\n",
"---\n",
"\n",
"###Always use Colab GPU (**VERY VERY VERY IMPORTANT!**)\n",
"### <font color=red>⬇ Always use Colab GPU! (**IMPORTANT!**) ⬇</font>\n",
"You need to use a Colab GPU so the Voice Changer can work faster and better\\\n",
"Use the menu above and click on **Runtime** » **Change runtime** » **Hardware acceleration** to select a GPU (**T4 is the free one**)\n",
"\n",
"---\n",
"\n",
"<br>\n",
"\n",
"# **Credits and Support**\n",
"Realtime Voice Changer by [w-okada](https://github.com/w-okada)\\\n",
"Colab files updated by [rafacasari](https://github.com/Rafacasari)\\\n",
"**Credits**<br>\n",
"Realtime Voice Changer by [w-okada](https://github.com/w-okada)<br>\n",
"Notebook files updated by [rafacasari](https://github.com/Rafacasari)<br>\n",
"Recommended settings by [YunaOneeChan](https://github.com/YunaOneeChan)\n",
"\n",
"Need help? [AI Hub Discord](https://discord.gg/aihub) » ***#help-realtime-vc***\n",
"**Need help?** [AI Hub Discord](https://discord.gg/aihub) » ***#help-realtime-vc***\n",
"\n",
"---"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "RhdqDSt-LfGr"
},
"outputs": [],
"source": [
"# @title **[Optional]** Connect to Google Drive\n",
"# @markdown Using Google Drive can improve load times a bit and your models will be stored, so you don't need to re-upload every time that you use.\n",
"import os\n",
"from google.colab import drive\n",
"\n",
"if not os.path.exists('/content/drive'):\n",
" drive.mount('/content/drive')\n",
"\n",
"%cd /content/drive/MyDrive"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "86wTFmqsNMnD",
"cellView": "form"
},
"outputs": [],
"source": [
"# @title **[1]** Clone repository and install dependencies\n",
"# @markdown This first step will download the latest version of Voice Changer and install the dependencies. **It will take around 2 minutes to complete.**\n",
"\n",
"!git clone --depth 1 https://github.com/w-okada/voice-changer.git &> /dev/null\n",
"\n",
"%cd voice-changer/server/\n",
"print(\"\\033[92mSuccessfully cloned the repository\")\n",
"\n",
"!apt-get install libportaudio2 &> /dev/null\n",
"!pip install onnxruntime-gpu uvicorn faiss-gpu fairseq jedi google-colab moviepy decorator==4.4.2 sounddevice numpy==1.23.5 pyngrok --quiet\n",
"!pip install -r requirements.txt --no-build-isolation --quiet\n",
"# Maybe install Tensor packages?\n",
"#!pip install torch-tensorrt\n",
"#!pip install TensorRT\n",
"print(\"\\033[92mSuccessfully installed all packages!\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "lLWQuUd7WW9U",
"cellView": "form"
},
"outputs": [],
"source": [
"# @title **[2]** Start Server **using ngrok** (Recommended | **need a ngrok account**)\n",
"# @markdown This cell will start the server, the first time that you run it will download the models, so it can take a while (~1-2 minutes)\n",
"\n",
"# @markdown ---\n",
"# @markdown You'll need a ngrok account, but **it's free**!\n",
"# @markdown ---\n",
"# @markdown **1** - Create a **free** account at [ngrok](https://dashboard.ngrok.com/signup)\\\n",
"# @markdown **2** - If you didn't logged in with Google or Github, you will need to **verify your e-mail**!\\\n",
"# @markdown **3** - Click [this link](https://dashboard.ngrok.com/get-started/your-authtoken) to get your auth token, copy it and place it here:\n",
"from pyngrok import conf, ngrok\n",
"\n",
"Token = '' # @param {type:\"string\"}\n",
"# @markdown **4** - Still need further tests, but maybe region can help a bit on latency?\\\n",
"# @markdown `Default Region: us - United States (Ohio)`\n",
"Region = \"us - United States (Ohio)\" # @param [\"ap - Asia/Pacific (Singapore)\", \"au - Australia (Sydney)\",\"eu - Europe (Frankfurt)\", \"in - India (Mumbai)\",\"jp - Japan (Tokyo)\",\"sa - South America (Sao Paulo)\", \"us - United States (Ohio)\"]\n",
"\n",
"MyConfig = conf.PyngrokConfig()\n",
"\n",
"MyConfig.auth_token = Token\n",
"MyConfig.region = Region[0:2]\n",
"\n",
"conf.get_default().authtoken = Token\n",
"conf.get_default().region = Region[0:2]\n",
"\n",
"conf.set_default(MyConfig);\n",
"\n",
"# @markdown ---\n",
"# @markdown If you want to automatically clear the output when the server loads, check this option.\n",
"Clear_Output = True # @param {type:\"boolean\"}\n",
"\n",
"import portpicker, subprocess, threading, time, socket, urllib.request\n",
"PORT = portpicker.pick_unused_port()\n",
"\n",
"from IPython.display import clear_output, Javascript\n",
"\n",
"from pyngrok import ngrok\n",
"ngrokConnection = ngrok.connect(PORT)\n",
"public_url = ngrokConnection.public_url\n",
"\n",
"def iframe_thread(port):\n",
" while True:\n",
" time.sleep(0.5)\n",
" sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)\n",
" result = sock.connect_ex(('127.0.0.1', port))\n",
" if result == 0:\n",
" break\n",
" sock.close()\n",
" clear_output()\n",
" print(\"------- SERVER READY! -------\")\n",
" print(\"Your server is available at:\")\n",
" print(public_url)\n",
" print(\"-----------------------------\")\n",
" display(Javascript('window.open(\"{url}\", \\'_blank\\');'.format(url=public_url)))\n",
"\n",
"threading.Thread(target=iframe_thread, daemon=True, args=(PORT,)).start()\n",
"\n",
"!python3 MMVCServerSIO.py \\\n",
" -p {PORT} \\\n",
" --https False \\\n",
" --content_vec_500 pretrain/checkpoint_best_legacy_500.pt \\\n",
" --content_vec_500_onnx pretrain/content_vec_500.onnx \\\n",
" --content_vec_500_onnx_on true \\\n",
" --hubert_base pretrain/hubert_base.pt \\\n",
" --hubert_base_jp pretrain/rinna_hubert_base_jp.pt \\\n",
" --hubert_soft pretrain/hubert/hubert-soft-0d54a1f4.pt \\\n",
" --nsf_hifigan pretrain/nsf_hifigan/model \\\n",
" --crepe_onnx_full pretrain/crepe_onnx_full.onnx \\\n",
" --crepe_onnx_tiny pretrain/crepe_onnx_tiny.onnx \\\n",
" --rmvpe pretrain/rmvpe.pt \\\n",
" --model_dir model_dir \\\n",
" --samples samples.json"
]
},
{
"cell_type": "code",
"source": [
"# @title **[Optional]** Start Server **using localtunnel** (ngrok alternative | no account needed)\n",
"# @markdown This cell will start the server, the first time that you run it will download the models, so it can take a while (~1-2 minutes)\n",
"\n",
"# @markdown ---\n",
"!npm config set update-notifier false\n",
"!npm install -g localtunnel\n",
"print(\"\\033[92mLocalTunnel installed!\")\n",
"# @markdown If you want to automatically clear the output when the server loads, check this option.\n",
"Clear_Output = True # @param {type:\"boolean\"}\n",
"\n",
"import portpicker, subprocess, threading, time, socket, urllib.request\n",
"PORT = portpicker.pick_unused_port()\n",
"\n",
"from IPython.display import clear_output, Javascript\n",
"\n",
"def iframe_thread(port):\n",
" while True:\n",
" time.sleep(0.5)\n",
" sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)\n",
" result = sock.connect_ex(('127.0.0.1', port))\n",
" if result == 0:\n",
" break\n",
" sock.close()\n",
" clear_output()\n",
" print(\"Use the following endpoint to connect to localtunnel:\", urllib.request.urlopen('https://ipv4.icanhazip.com').read().decode('utf8').strip(\"\\n\"))\n",
" p = subprocess.Popen([\"lt\", \"--port\", \"{}\".format(port)], stdout=subprocess.PIPE)\n",
" for line in p.stdout:\n",
" print(line.decode(), end='')\n",
"\n",
"threading.Thread(target=iframe_thread, daemon=True, args=(PORT,)).start()\n",
"\n",
"\n",
"!python3 MMVCServerSIO.py \\\n",
" -p {PORT} \\\n",
" --https False \\\n",
" --content_vec_500 pretrain/checkpoint_best_legacy_500.pt \\\n",
" --content_vec_500_onnx pretrain/content_vec_500.onnx \\\n",
" --content_vec_500_onnx_on true \\\n",
" --hubert_base pretrain/hubert_base.pt \\\n",
" --hubert_base_jp pretrain/rinna_hubert_base_jp.pt \\\n",
" --hubert_soft pretrain/hubert/hubert-soft-0d54a1f4.pt \\\n",
" --nsf_hifigan pretrain/nsf_hifigan/model \\\n",
" --crepe_onnx_full pretrain/crepe_onnx_full.onnx \\\n",
" --crepe_onnx_tiny pretrain/crepe_onnx_tiny.onnx \\\n",
" --rmvpe pretrain/rmvpe.pt \\\n",
" --model_dir model_dir \\\n",
" --samples samples.json \\\n",
" --colab True"
],
"metadata": {
"cellView": "form",
"id": "ZwZaCf4BeZi2"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"# In Development | **Need contributors**"
],
"metadata": {
"id": "iuf9pBHYpTn-"
"id": "Lbbmx_Vjl0zo"
}
},
{
"cell_type": "code",
"source": [
"# @title **[BROKEN]** Start Server using Colab Tunnels (trying to fix this TwT)\n",
"# @markdown **Issue:** Everything starts correctly, but when you try to use the client, you'll see in your browser console a bunch of errors **(Error 500 - Not Allowed.)**\n",
"# @title Clone repository and install dependencies\n",
"# @markdown This first step will download the latest version of Voice Changer and install the dependencies. **It can take some time to complete.**\n",
"%cd /content/\n",
"\n",
"import portpicker, subprocess, threading, time, socket, urllib.request\n",
"PORT = portpicker.pick_unused_port()\n",
"!pip install colorama --quiet\n",
"from colorama import Fore, Style\n",
"import os\n",
"\n",
"def iframe_thread(port):\n",
" while True:\n",
" time.sleep(0.5)\n",
" sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)\n",
" result = sock.connect_ex(('127.0.0.1', port))\n",
" if result == 0:\n",
" break\n",
" sock.close()\n",
" from google.colab.output import serve_kernel_port_as_window\n",
" serve_kernel_port_as_window(PORT)\n",
"print(f\"{Fore.CYAN}> Cloning the repository...{Style.RESET_ALL}\")\n",
"!git clone https://github.com/w-okada/voice-changer.git --quiet\n",
"print(f\"{Fore.GREEN}> Successfully cloned the repository!{Style.RESET_ALL}\")\n",
"%cd voice-changer/server/\n",
"\n",
"threading.Thread(target=iframe_thread, daemon=True, args=(PORT,)).start()\n",
"print(f\"{Fore.CYAN}> Installing libportaudio2...{Style.RESET_ALL}\")\n",
"!apt-get -y install libportaudio2 -qq\n",
"\n",
"print(f\"{Fore.CYAN}> Installing pre-dependencies...{Style.RESET_ALL}\")\n",
"# Install dependencies that are missing from requirements.txt and pyngrok\n",
"!pip install faiss-gpu fairseq pyngrok --quiet\n",
"!pip install pyworld --no-build-isolation --quiet\n",
"print(f\"{Fore.CYAN}> Installing dependencies from requirements.txt...{Style.RESET_ALL}\")\n",
"!pip install -r requirements.txt --quiet\n",
"\n",
"print(f\"{Fore.GREEN}> Successfully installed all packages!{Style.RESET_ALL}\")"
],
"metadata": {
"id": "86wTFmqsNMnD",
"cellView": "form",
"_kg_hide-output": false,
"execution": {
"iopub.status.busy": "2023-09-14T04:01:17.308284Z",
"iopub.execute_input": "2023-09-14T04:01:17.308682Z",
"iopub.status.idle": "2023-09-14T04:08:08.475375Z",
"shell.execute_reply.started": "2023-09-14T04:01:17.308652Z",
"shell.execute_reply": "2023-09-14T04:08:08.473827Z"
},
"trusted": true
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# @title Start Server **using ngrok**\n",
"# @markdown This cell will start the server, the first time that you run it will download the models, so it can take a while (~1-2 minutes)\n",
"\n",
"# @markdown ---\n",
"# @markdown You'll need a ngrok account, but <font color=green>**it's free**</font> and easy to create!\n",
"# @markdown ---\n",
"# @markdown **1** - Create a <font color=green>**free**</font> account at [ngrok](https://dashboard.ngrok.com/signup) or **login with Google/Github account**\\\n",
"# @markdown **2** - If you didn't logged in with Google/Github, you will need to **verify your e-mail**!\\\n",
"# @markdown **3** - Click [this link](https://dashboard.ngrok.com/get-started/your-authtoken) to get your auth token, and place it here:\n",
"Token = '' # @param {type:\"string\"}\n",
"# @markdown **4** - *(optional)* Change to a region near to you or keep at United States if increase latency\\\n",
"# @markdown `Default Region: us - United States (Ohio)`\n",
"Region = \"us - United States (Ohio)\" # @param [\"ap - Asia/Pacific (Singapore)\", \"au - Australia (Sydney)\",\"eu - Europe (Frankfurt)\", \"in - India (Mumbai)\",\"jp - Japan (Tokyo)\",\"sa - South America (Sao Paulo)\", \"us - United States (Ohio)\"]\n",
"\n",
"#@markdown **5** - *(optional)* Other options:\n",
"ClearConsole = True # @param {type:\"boolean\"}\n",
"\n",
"# ---------------------------------\n",
"# DO NOT TOUCH ANYTHING DOWN BELOW!\n",
"# ---------------------------------\n",
"\n",
"%cd /content/voice-changer/server\n",
"\n",
"from pyngrok import conf, ngrok\n",
"MyConfig = conf.PyngrokConfig()\n",
"MyConfig.auth_token = Token\n",
"MyConfig.region = Region[0:2]\n",
"#conf.get_default().authtoken = Token\n",
"#conf.get_default().region = Region\n",
"conf.set_default(MyConfig);\n",
"\n",
"import subprocess, threading, time, socket, urllib.request\n",
"PORT = 8000\n",
"\n",
"from pyngrok import ngrok\n",
"ngrokConnection = ngrok.connect(PORT)\n",
"public_url = ngrokConnection.public_url\n",
"\n",
"from IPython.display import clear_output\n",
"\n",
"def wait_for_server():\n",
" while True:\n",
" time.sleep(0.5)\n",
" sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)\n",
" result = sock.connect_ex(('127.0.0.1', PORT))\n",
" if result == 0:\n",
" break\n",
" sock.close()\n",
" if ClearConsole:\n",
" clear_output()\n",
" print(\"--------- SERVER READY! ---------\")\n",
" print(\"Your server is available at:\")\n",
" print(public_url)\n",
" print(\"---------------------------------\")\n",
"\n",
"threading.Thread(target=wait_for_server, daemon=True).start()\n",
"\n",
"!python3 MMVCServerSIO.py \\\n",
" -p {PORT} \\\n",
@ -285,11 +167,16 @@
" --crepe_onnx_tiny pretrain/crepe_onnx_tiny.onnx \\\n",
" --rmvpe pretrain/rmvpe.pt \\\n",
" --model_dir model_dir \\\n",
" --samples samples.json"
" --samples samples.json\n",
"\n",
"ngrok.disconnect(ngrokConnection.public_url)"
],
"metadata": {
"id": "P2BN-iWvDrMM",
"cellView": "form"
"id": "lLWQuUd7WW9U",
"cellView": "form",
"_kg_hide-input": false,
"scrolled": true,
"trusted": true
},
"execution_count": null,
"outputs": []

2
server/requirements.txt
View File

@ -13,10 +13,8 @@ python-socketio==5.8.0
fastapi==0.95.1
python-multipart==0.0.6
onnxruntime-gpu==1.13.1
pyworld==0.3.3
scipy==1.10.1
matplotlib==3.7.1
fairseq==0.12.2
websockets==11.0.2
faiss-cpu==1.7.3
torchcrepe==0.0.18

24
signatures/version1/cla.json
View File

@ -31,6 +31,30 @@
"created_at": "2023-08-10T11:43:18Z",
"repoId": 527419347,
"pullRequestNo": 683
},
{
"name": "InsanEagle",
"id": 67074517,
"comment_id": 1716001761,
"created_at": "2023-09-12T15:58:11Z",
"repoId": 527419347,
"pullRequestNo": 832
},
{
"name": "jonluca",
"id": 13029040,
"comment_id": 1720154884,
"created_at": "2023-09-14T21:08:39Z",
"repoId": 527419347,
"pullRequestNo": 847
},
{
"name": "aeongdesu",
"id": 50764666,
"comment_id": 1722217182,
"created_at": "2023-09-16T12:12:57Z",
"repoId": 527419347,
"pullRequestNo": 856
}
]
}