Scaling Rich Style-Prompted Text-to-Speech Datasets
Paper
•
2503.04713
•
Published
•
1
ParaSpeechCaps: Rich Style Prompted TTS
The ParaSpeechCaps dataset and models trained on it
-
ajd12342/paraspeechcaps
Viewer • Updated • 1.07M • 877 • 9Note ParaSpeechCaps (Paralinguistic Speech Captions), a large-scale dataset that annotates speech utterances with rich style captions.
ajd12342/parler-tts-mini-v1-paraspeechcaps
Text-to-Speech • Updated • 499 • 4Note Parler-TTS-Mini-v1, a style-prompted TTS model, finetuned on ParaSpeechCaps.
ajd12342/parler-tts-mini-v1-paraspeechcaps-only-base
Text-to-Speech • Updated • 61 • 1Note Parler-TTS-Mini-v1, a style-prompted TTS model, finetuned on ParaSpeechCaps-Base.
-
1
ParaSpeechCaps
⚡Gradio Demo for ParaSpeechCaps