Arabic Spark-TTS Fine-tuned on ClArTTS

Fine-tuned LLM component of Spark-TTS on ClArTTS Arabic dataset (12 hours of Classical Arabic speech).

Model Description

This is the fine-tuned LLM (Qwen2) component of Spark-TTS, trained on the ClArTTS dataset.

Usage

Replace the LLM checkpoint in the original Spark-TTS model with this fine-tuned version.

Base model: SparkAudio/Spark-TTS-0.5B

Downloads last month
11
Safetensors
Model size
0.5B params
Tensor type
F32
·
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support