Persian Tts Female Vits

🚀 Persian TTS Female VITS

A Persian text-to-speech model with a single-speaker female voice, trained on a specific Persian dataset.

🚀 Quick Start

To get started with the persian-tts-female-vits model, you need to install the necessary dependencies and then you can generate audio from text.

📦 Installation

Install the required dependencies using the following commands:

!pip install TTS
!sudo apt-get -y install espeak-ng

💻 Usage Examples

🔍 Basic Usage

Generate audio from text using the command-line interface (CLI):

!tts --text "زندگی فقط یک بار است؛ از آن به خوبی استفاده کن" \
     --model_path ".pth" \
     --config_path "config.json" \
     --out_path "speech1.wav"

⚙️ Advanced Usage

Generate audio from text using the Python API:

from TTS.config import load_config
from TTS.utils.manage import ModelManager
from TTS.utils.synthesizer import Synthesizer

config="config.json" 
model="best_model_30824.pth"

model_path =model # Absolute path to the model checkpoint.pth
config_path =config # Absolute path to the model config.json

text=".زندگی فقط یک بار است؛ از آن به خوبی استفاده کن"

synthesizer = Synthesizer(
    model_path, config_path
)
wavs = synthesizer.tts(text)
synthesizer.save_wav(wavs, 'sp.wav')

🎧 Displaying the Audio

After generating the audio, you can display it using the following code:

import IPython
IPython.display.Audio('sp.wav')

✨ Features

• Language Support: This model supports Persian (فارسی) text-to-speech conversion.
• Single-Speaker Voice: It uses a single-speaker female voice for a consistent audio output.
• Trained Dataset: The model is trained on the persian-tts-dataset-male dataset.
• Accessible Resources: You can access the GitHub Repo for the source code and a Demo to test the model.

📚 Documentation

• Hours Used: 10 hours were used in the development or training process.
• Cloud Provider: The model was developed using Kaggle as the cloud provider.

📄 License

This model is released under the OpenRAIL license.

📦 Model Information