---
language:
- ar
license: apache-2.0
tags:
- text-to-speech
- arabic
- spark-tts
- tts
base_model: SparkAudio/Spark-TTS-0.5B
datasets:
- MBZUAI/ClArTTS
---

# Spark-TTS Arabic (Fine-tuned on ClArTTS)

Complete Spark-TTS model with LLM fine-tuned on ClArTTS dataset (12 hours of Classical Arabic speech).

## Usage
```python
from transformers import AutoProcessor, AutoModel
import soundfile as sf
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
processor = AutoProcessor.from_pretrained("azeddinShr/Spark-TTS-Arabic-Complete", trust_remote_code=True)
model = AutoModel.from_pretrained("azeddinShr/Spark-TTS-Arabic-Complete", trust_remote_code=True).eval().to(device)
processor.model = model

# Generate
text = "مَرْحَبًا بِكُمْ"
ref_text = "النَّصُّ الْمَرْجِعِيُّ"
inputs = processor(text=text.lower(), prompt_speech_path="reference.wav", prompt_text=ref_text, return_tensors="pt").to(device)
global_tokens = inputs.pop("global_token_ids_prompt", None)

with torch.no_grad():
    output_ids = model.generate(**inputs, max_new_tokens=8000, do_sample=True, temperature=0.8, top_k=50, top_p=0.95)

output = processor.decode(generated_ids=output_ids, global_token_ids_prompt=global_tokens, input_ids_len=inputs["input_ids"].shape[-1])
audio = output["audio"].cpu().numpy() if isinstance(output["audio"], torch.Tensor) else output["audio"]
sf.write("output.wav", audio, output["sampling_rate"])
```

## Training Details

- **Base Model**: SparkAudio/Spark-TTS-0.5B
- **Fine-tuned Component**: LLM (Qwen2)
- **Dataset**: ClArTTS (12 hours Classical Arabic)
- **Training**: 20 epochs on 30% of dataset

## Model Components

- BiCodec (audio encoder/decoder) - unchanged from base
- wav2vec2 (speech encoder) - unchanged from base  
- LLM (Qwen2) - **fine-tuned on Arabic**