pyVideoTrans

English

简体中文

English

简体中文

Appearance

For AI novices, deploying an AI software from source code can be difficult. With a package, you can simply download, unzip, and double-click to use it, greatly reducing the barrier to entry. However, sometimes you may not find a ready-made package, or the package may not be updated in time. In this case, you can try creating your own package and sharing it with others.

Since AI project models are usually large, coupled with GPU support, even when compressed into 7z format, the file size may far exceed 5GB, making it difficult to upload to cloud storage or store locally. Therefore, I will no longer create packages. If you are interested, you can create your own package according to this tutorial and share it with others.

This tutorial uses F5-TTS as an example and creates a package on Windows 10 using Python 3.10. The main steps are as follows:

  1. Download the Python 3.10 embed version (not the exe installer, but a zip archive).
  2. Install pip and set the dependency lookup path for the project.
  3. Download the F5-TTS source code.
  4. Install the F5-TTS dependencies.
  5. Create a one-click startup script and set the model directory to the project directory.
  6. Configure a proxy and download the models.
  7. Perform a cloning task to complete the download of Whisper and other models.
  8. Compress into a package.
  9. Create packages for other AI projects

Preparations: ​

First, create an empty folder. To avoid errors, it is recommended to create an English folder on a non-system drive, such as D:\f5win. This article uses D:\f5win as an example. Then, create another empty folder named runtime inside this folder to store the Python 3.10 embed version files downloaded later.

Before you begin, be sure to click "View" in the folder navigation bar and check "File name extensions", otherwise you may make mistakes in subsequent operations, especially if you are not familiar with extensions.

Show file extensions

1. Download the Python 3.10 embed version ​

Important note: We are downloading the embed version here, not the exe installer. This version does not depend on your local Python environment. Even if you have Python installed on your machine, you still need to download this version.

  • Download address: https://www.python.org/downloads/release/python-31011/

  • After opening the webpage, scroll to the bottom and click Windows embeddable package (64-bit) to download. You will get a zip archive after downloading.

    Download Python embed version

    Be sure to download this version, don't get it wrong!

  • After the download is complete, unzip the zip archive and copy all the files inside to the runtime folder you just created. As shown below:

    Copy Python embed files to runtime folder

2. Install pip and modify the package lookup path ​

The embed version of Python does not include the pip module, so you need to install it manually.

  • Install pip:

    • Open this address: https://bootstrap.pypa.io/get-pip.py

    • Right-click and save as, save the file to the runtime directory. After saving, the runtime folder should have a file named get-pip.py.

      Download get-pip.pyget-pip.py fileget-pip.py under runtime directory

    • Enter cmd in the address bar of the runtime folder and press Enter to open the terminal window (black window).

      Open cmd and confirm the path is in runtime

    • In the terminal window, enter the command .\python get-pip.py and press Enter. Be sure to note whether the current folder address displayed on the command line is within the runtime folder, otherwise an error will occur.

      Wait for the installation to complete...

      pip installing

      pip module installed successfully!

      pip module installed successfully

  • Modify the python310._pth file:

    • Find the file named python310._pth in the runtime folder, right-click and open it with Notepad.

      Default content of python310._pth file

    • On the line below the dot symbol . on the second line, add the following three lines:

      ./Lib/site-packages
../src
../src/f5_tts

    • Save the file. The modified file content should be as follows. Please check carefully to ensure it is correct:

      The modified python310._pth file content should be as follows

3. Download the F5-TTS Source Code ​

  • Open the F5-TTS project's GitHub repository: https://github.com/SWivid/F5-TTS

  • Download the zip archive of the source code.

    Download F5-TTS source code

  • Unzip the downloaded zip package and copy all the files inside the F5-TTS-main folder to the D:\f5win folder. Note: Copy the files inside, not the entire F5-TTS-main folder.

    Copy files inside F5-TTS-main

    After unzipping, the content of the D:\f5win folder should be as shown below:

    Correct directory structure of D:5win after copying

Return to the previous CMD window

Still the same terminal window, execute the cd ../ command to ensure that the address before the command line has been reduced by the runtime characters, and becomes as follows. The following operations must be performed under the D:/f5win directory.

4. Install Dependencies ​

  • Return to the cmd terminal window and double-check that the path currently displayed on the command line is D:\f5win (without runtime).

  • Execute the following command to install the dependencies (note the spaces and dot symbols):

    .\runtime\python -m pip install -e .

    Installing dependencies

    Wait for the installation to complete...

All dependencies installed

  • If you want the package to support NVIDIA graphics cards (optional): Continue executing the following command to install the CUDA version of PyTorch and torchaudio (note the spaces and dot symbols, the command cannot be broken into multiple lines):
    .\runtime\python -m pip install torch==2.4.0+cu124 torchaudio==2.4.0+cu124 --extra-index-url https://download.pytorch.org/whl/cu124

5. Create a One-Click Startup Script ​

By default, models are saved to the user directory on the C drive. To facilitate integration, we need to download the models into the package.

  • In the D:\f5win folder, right-click -- New -- Text Document, create a run.txt file, open it with Notepad, and enter the following code:

```bat
@echo off

chcp 65001 > nul

set "HF_HOME=%~dp0models"
set "MODELSCOPE_CACHE=%~dp0models"

echo HF_HOME: %HF_HOME%
echo MODELSCOPE_CACHE: %MODELSCOPE_CACHE%

"%~dp0runtime\python" -m f5_tts.infer.infer_gradio  --inbrowser

pause
```

The above script means: save the model to the models folder in the current directory, then start the web interface, and automatically open it in the browser.

  • After saving the file, rename run.txt to run.bat. A warning will pop up, select "Yes". If the warning does not pop up, it means you have modified it incorrectly. Please check whether you have displayed the file extensions as instructed in the preparation section at the top of this article.

    Warning pop-up when renaming to run.bat

6. Configure Network Proxy ​

Due to network restrictions, you cannot directly access Hugging Face (huggingface.co) where the F5-TTS model is located. Therefore, you need to configure a proxy and set it as a system proxy.

For example, if the tool is v2ray, you can set it like this:

Set as system proxy in v2ray

After the configuration is complete, double-click the run.bat file you just created.

  • If the file is opened directly with Notepad after double-clicking, it means that you failed to modify the extension. Please return to the preparation section at the top of this article and select the file extension as instructed.

  • If a black window opens after double-clicking, the models will start downloading to the D:\f5win\models folder.

    Downloading model

  • If an error similar to the one below occurs, it means that you have not configured the proxy correctly, or have not correctly set it as a system proxy, resulting in a failure to connect to Hugging Face to download the model.

    Error downloading model: Failed to connect to huggingface.co

    Sometimes the download fails halfway through. The biggest reason is that your proxy node is unstable. Please replace it with a more stable proxy or node.

  • After the model download is complete, the browser window will open automatically. Model download completed, browser opens automatically

7. Perform a Cloning Task to Download the Whisper Model ​

When performing voice cloning, if the text corresponding to the reference audio is not provided, F5-TTS will automatically download the Whisper model from Hugging Face. To pack the package completely, we need to download it in advance.

  • In the automatically opened Web window, select a clean reference audio of 5-10 seconds, enter the text you want to synthesize (e.g. "Hello friend"), and click "Synthesize".

    Web interface

  • This will start downloading the Whisper model.

    Downloading Whisper model

  • When the synthesis is successful and there are no errors, you can start packing the project into a package.

8. Compress into a Package ​

  • Before compressing, you can rename run.bat to Click me to start.bat to make it easier for novice users to understand.
  • Compress the entire D:\f5win folder into a zip file, or compress it into a smaller 7z file.
  • Share the compressed package with others, they can unzip it and double-click run.bat (or Click me to start.bat) to use it.

9. How to Create Packages for Other AI Projects ​

Most Python-based open source projects on GitHub can be packaged using a similar method. The main differences are in the following three points:

  1. Python Version: Python 3.10 is the most common version and is suitable for most projects. If the project has special requirements (such as 3.11 or 3.12), you can find the corresponding version of Windows embeddable package (64-bit) on this page https://www.python.org/downloads/windows/. Be sure to note that you cannot download the exe installer.

  2. Content of the python310._pth file:

    • ./Lib/site-packages is still required.
    • Add other paths according to the actual situation of the project.
    • If there is a code directory named cfg in the project, add a line ../cfg.
    • If the project has a src directory, and there are other folders under src, continue to add ../src/folder_name.

  3. Startup command for the run.bat script:

    • You only need to modify this line of command:
      "%~dp0runtime\python" -m f5_tts.infer.infer_gradio  --inbrowser
    • The "%~dp0runtime\python" part remains unchanged, and the part after it is changed to the command to start the corresponding project (excluding python).
    • If in doubt, you can give the content of run.bat and the startup command of the corresponding project to AI, and let it give a new startup script based on run.bat. Remember to tell AI to use the Python interpreter in run.bat.