A collection of fine-tuned models for text-to-speech synthesis. The dataset is hosted on Kaggle. The specific architecture combines Matcha_TTS and HiFi GAN components.
Use Cases
- Fine-tune a TTS model for a specific voice or language (inferred from domain, verify after download)
- Generate high-fidelity speech audio from text prompts (inferred from domain, verify after download)
- Benchmark speech synthesis model performance (inferred from domain, verify after download)
Limitations
- Metadata is minimal; actual content requires verification after download.
- Column-level documentation is absent; field semantics must be inferred after download.