Kokoro TTS V1.0 with Subtitle & SRT Dubbing

Alternative ways to use Kokoro-TTS kokoro-onnx, Kokoro-FastAPI, kokoro

Installation

Prerequisites

• At least Python 3.10
• Git
• (Optional) Virtual Environment for dependency isolation

Steps to Install and Run

1. Clone the Repository sh https://github.com/NeuralFalconYT/Kokoro-TTS-Subtitle.git cd Kokoro-TTS-Subtitle

2. (Optional) Create and Activate a Virtual Environment

3. Windows: sh python -m venv myenv myenv\Scripts\activate

4. Mac/Linux: sh python3 -m venv myenv source myenv/bin/activate

5. Install PyTorch

6. Forcefully install Torch with CUDA. If you did not, then requirements.txt will install the CPU version [It's happening with my system.]

7. Check CUDA Version (for GPU setup): bash nvcc --version Find your CUDA version example 11.8

8. Visit PyTorch Get Started and install the version compatible with your CUDA setup.:

   • For CUDA 11.8: pip install torch --index-url https://download.pytorch.org/whl/cu118
   • For CUDA 12.1: pip install torch --index-url https://download.pytorch.org/whl/cu121
   • For CUDA 12.4: pip install torch --index-url https://download.pytorch.org/whl/cu124

9. Install Dependencies

10. Windows/Mac/Linux: sh pip install -r requirements.txt

1. Install eSpeak NG

2. For Windows:

3. Download the eSpeak NG 1.50 release from the eSpeak NG GitHub Releases. [Or, You can try eSpeak NG latest Version]
4. Locate and download the file named espeak-ng-X64.msi.

5. Run the installer and follow the installation steps. Ensure that you install eSpeak NG in the default directory: C:\Program Files\eSpeak NG > Note: This default path is required for the application to locate eSpeak NG properly.

6. For Linux:

7. Open your terminal.
8. Install eSpeak NG using the following command: bash sudo apt-get -qq -y install espeak-ng > /dev/null 2>&1 > Note: This command suppresses unnecessary output for a cleaner installation process.

1. Run the Application

If you used a virtual environment, make sure you enabled it. - Windows/Mac/Linux: sh python beta.py Or,

python one_clicker.py Then, double-click on run_app.bat (Windows) to execute the script.

1. Use Kokoko TTS Gradio app as an API in your other project:
   Check out scripts/api.py Code

Uninstallation Guide for Kokoro v1.0

If You Used a Virtual Environment:

1. Simply delete the kokoro_v1 folder from your project directory.

If You Did Not Use a Virtual Environment:

1. Inside the kokoro_v1 directory, run the following command to uninstall dependencies: bash pip uninstall -r requirements.txt
2. Uninstall PyTorch: bash pip uninstall torch

To clear the HuggingFace cache models:

• Navigate to C:\Users\<username>\.cache\huggingface\hub
• Delete the contents of the hub folder. That's it! You've successfully removed everything.

🛠️ Fix for Japanese Audio Generation Error

If you encounter an error while generating Japanese audio, try the following steps:

1. Uninstall existing unidic:

bash pip uninstall unidic -y

1. Reinstall unidic:

bash pip install unidic

1. Download the dictionary data:

bash python -m unidic download Note: This solution is likely to work, the same issue has been observed on both Colab and Hugging Face.

License

Kokoro model is licensed under the [Apache License 2.0]

Credits

Kokoro HuggingFace