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