Persian Tts Female Glow Tts

🚀 Persian TTS Female Glow_TTS

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

🚀 Quick Start

Installation

Install the necessary dependencies:

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

Generate Audio from Text

Using CLI

!tts --text "زندگی فقط یک بار است؛ از آن به خوبی استفاده کن" \
     --model_path "/coqui_training/run-July-31-2022_10+54AM-0000000/checkpoint_24000.pth" \
     --config_path "/coqui_training/run-July-31-2022_10+54AM-0000000/config.json" \
     --out_path "speech1.wav"

Python API

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

basepath="/train_output/run-December-24-2022_09+28AM-0000000"
config=basepath+"/config.json" 
model=basepath+"/best_model.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')

Display Audio

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

✨ Features

• Language Support: Supports Persian (فارسی) text-to-speech conversion.
• Voice Type: Utilizes a single-speaker female voice.
• Training Dataset: Trained on the persian-tts-dataset-famale.
• Code Repository: Check out the GitHub Repo.

📦 Installation

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

💻 Usage Examples

Basic Usage

# Install dependencies
!pip install TTS
!sudo apt-get -y install espeak-ng

# Generate audio using CLI
!tts --text "زندگی فقط یک بار است؛ از آن به خوبی استفاده کن" \
     --model_path "/coqui_training/run-July-31-2022_10+54AM-0000000/checkpoint_24000.pth" \
     --config_path "/coqui_training/run-July-31-2022_10+54AM-0000000/config.json" \
     --out_path "speech1.wav"

Advanced Usage

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

basepath="/train_output/run-December-24-2022_09+28AM-0000000"
config=basepath+"/config.json" 
model=basepath+"/best_model.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')

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

📚 Documentation

How to Get Started with the Model

Use the training code on this GitHub repository.

📄 License

No license information provided in the original document.

📋 Model Information