AhmedEladl/Magpie-TTS-Emirates-Arabic

Magpie TTS - Emirati Arabic (Fine-Tuned)

This model is a fine-tuned version of the NVIDIA Magpie TTS Multilingual (357M) model, specifically adapted for Emirati/UAE Arabic text-to-speech generation.

Audio Comparison: Base vs. Fine-Tuned

Below are raw, unedited audio samples demonstrating the dialect adaptation.

Audio Comparison: Base vs. Fine-Tuned

Below are raw, unedited audio samples demonstrating the dialect adaptation.

Text Prompt	Base Model magpie_tts_multilingual_357m	Fine-Tuned Model
ترا الدرب صوب دبي اليوم وايد زحمة، فإذا مستعيلين أحسن نظهر من الحين عشان نوصل قبل الموعد وما نتأخر.
عندي اجتماع باچر الصبح، ولازم أجهز العرض اليوم عشان ما أتوهق وأخلص كل شي في آخر لحظة.
بسير المول العصر، تبغي شي من هناك؟
المكان هني زحمة وايد اليوم.

---

⚙️ Model Details

• Architecture: Magpie TTS (Encoder-Decoder Transformer with Audio Codec)
• Base Model: nvidia/magpie_tts_multilingual_357m
• Language: Arabic (United Arab Emirates) ar-AE
• Framework: NVIDIA NeMo (v2.8.0rc0)
• Codec: nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps

📊 Training Dataset

The model was fine-tuned using the AhmedEladl/emirates-dialect-speech dataset.

🚀 Training Configuration

• Hardware: NVIDIA L4 GPU
• Epochs: 10
• Batch Size: 2 (with gradient accumulation steps = 2)
• Learning Rate: 5e-6 (AdamW)
• Precision: 32-bit float
• Context Duration Constraints: 2.0s to 12.0s

---

📦 Dependencies & Installation

To run inference with this model, ensure you have the correct versions of the NeMo toolkit and audio handling libraries installed.

pip install torch>=2.1.0
pip install soundfile>=0.12.1
pip install librosa>=0.10.1
pip install huggingface_hub>=0.23.0
pip install nemo_toolkit[all]==2.8.0rc0

Inference Code Example

import soundfile as sf
from huggingface_hub import hf_hub_download
from nemo.collections.tts.modules.magpietts_inference.utils import ModelLoadConfig, load_magpie_model

# 1. Download Model & Codec from Hugging Face Hub
print("Downloading models...")
model_path = hf_hub_download(repo_id="AhmedEladl/Magpie-TTS-UAE-Arabic", filename="Magpie-TTS.nemo")
codec_path = hf_hub_download(repo_id="nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps", filename="nemo-nano-codec-22khz-1.89kbps-21.5fps.nemo")

# 2. Load the fine-tuned model and codec
config = ModelLoadConfig(nemo_file=model_path, codecmodel_path=codec_path)
model, _ = load_magpie_model(config)
model.eval().cuda()

# 3. Generate Audio
prompt = "مرحبا الساع، شحالك؟ عساك طيب؟"
print("Generating audio...")
res = model.do_tts(transcript=prompt, language="ar-AE", apply_TN=False)

# 4. Save the output
audio = res[0].cpu().numpy()
if len(audio.shape) == 2:
    audio = audio[0]
    
sf.write("output.wav", audio, 22050)
print("✅ Audio saved successfully to output.wav")

---

📜 Citation

If you use this model in your research or projects, please cite it as follows:

@misc{magpie_tts_uae_arabic,
  author       = {Ahmed Eladl},
  title        = {Magpie TTS - Emirates Arabic (Fine-Tuned)},
  year         = {2026},
  publisher    = {Hugging Face},
  url          = {https://huggingface.co/AhmedEladl/Magpie-TTS-Emirates-Arabic}
}

---

📧 Contact

For any questions, issues, or inquiries regarding this model, please reach out:

• Email: aeladl.dev@gmail.com