ISTNetworks/saudi-msa-piper

Saudi Arabic (MSA) TTS Model - Piper

This repository contains a high-quality Piper TTS model trained on Saudi Arabic (Modern Standard Arabic) dataset for 455 epochs.

Model Details

• Language: Arabic (Saudi dialect)
• Framework: Piper TTS
• Sample Rate: 22050 Hz
• Training Epochs: 455
• Dataset Size: 11,592 audio samples
• Speakers: 5 speakers (SPK1-SPK5)
• Model Quality: Professional grade

Model Files

• checkpoints/epoch=455-step=1189248.ckpt - PyTorch Lightning checkpoint (807 MB)
• config.json - Model configuration file
• training_data.csv - Training dataset metadata
• scripts/export_jit.py - ONNX export script

Quick Start

Export to ONNX

python3 scripts/export_jit.py

This will create an ONNX model file that can be used with Piper for inference.

Usage with Piper

# Install Piper TTS
pip install piper-tts

# After exporting to ONNX
echo 'مرحبا بك في نظام التحويل النصي إلى كلام' | \
  piper --model saudi_msa_epoch455.onnx --output_file output.wav

Python Usage

from piper import PiperVoice

voice = PiperVoice.load("saudi_msa_epoch455.onnx")

# Synthesize speech
with open("output.wav", "wb") as f:
    voice.synthesize_stream_raw("مرحبا بك", f)

Training Details

Dataset Statistics

Training Configuration

voice_name: saudi_msa
sample_rate: 22050
espeak_voice: ar
batch_size: 8
epochs: 455
optimizer: Adam

Training Environment

• Python 3.11
• PyTorch 2.x with CUDA
• Lightning 2.x
• Total training time: ~85+ hours

Model Performance

This model has been trained for 455 epochs, providing:

• ✅ Excellent audio quality with minimal background noise
• ✅ Clear pronunciation of Arabic words
• ✅ Natural prosody and intonation
• ✅ Professional-grade output suitable for production use

The model performs exceptionally well on:

• Customer service dialogues
• Banking and financial terminology
• General conversational Arabic
• Saudi dialect expressions

Export Instructions

To export the checkpoint to ONNX format:

cd scripts
python3 export_jit.py

The script will:

1. Load the checkpoint from checkpoints/epoch=455-step=1189248.ckpt
2. Export to ONNX format with optimizations
3. Create saudi_msa_epoch455.onnx file

Make sure to copy the config.json file alongside the ONNX model:

cp config.json saudi_msa_epoch455.onnx.json

Files Structure

.
├── README.md
├── config.json                          # Model configuration
├── training_data.csv                    # Dataset metadata
├── checkpoints/
│   └── epoch=455-step=1189248.ckpt     # Latest checkpoint (807 MB)
└── scripts/
    ├── export_jit.py                    # ONNX export script
    ├── train_piper.sh                   # Training script
    └── create_training_file.py          # Data preparation script

License

This model is trained using the Piper TTS framework which is licensed under GPL-3.0.

Citation

If you use this model, please cite:

@misc{saudi_msa_piper_2026,
  title={Saudi Arabic TTS Model for Piper - Epoch 455},
  author={Piper MSA Project},
  year={2026},
  publisher={Hugging Face},
  howpublished={\url{https://huggingface.co/YOUR_USERNAME/saudi-msa-piper}}
}

Acknowledgments

• Piper TTS: https://github.com/rhasspy/piper
• eSpeak-ng for Arabic phonemization
• Original dataset contributors

Sample Usage

# Example: Generate customer service greeting
text = "حياك الله عميلنا العزيز، كيف اقدر اساعدك اليوم؟"
echo text | piper --model saudi_msa_epoch455.onnx --output_file greeting.wav

Model Comparison

For questions or issues, please open an issue on the repository.