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

Speaker	Samples
SPK1	3,000
SPK2	714
SPK3	1,656
SPK4	2,057
SPK5	4,193
Total	11,592

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:

Load the checkpoint from checkpoints/epoch=455-step=1189248.ckpt
Export to ONNX format with optimizations
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

Epoch	Quality	Noise Level	Clarity
65	Good	Moderate	Fair
176	Very Good	Low	Good
438	Excellent	Very Low	Excellent
455	Professional	Minimal	Excellent

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