Deterministic Prompting for Speaker-Stable Low-Resource Greek TTS
A data curation recipe that transforms audiobook recordings into TTS-ready data via WhisperX alignment and filtering is proposed, and Parler-TTS (880M), a prompt-based multilingual model whose pre-training encodes phonetic priors transferable to Greek is fine-tune.
Georgios Syllas, Efthymios Georgiou, Kosmas Kritsis et al.
· 0 citations