Photograph of a blind man with "talking books", [s.d.]. The man can be seen at left, seated, holding two "talking book" records in his hands. He wears a suit, business shirt, and tie. The man can be s
This dataset consists of 10.17 hours of annotated male voices in Shanghai dialect that is applicable for Text-to-Speech Synthesis, where 8,499 utterances collected from a 21-year-old man were containe
--- title: "Dataset for AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds" configs: - config_name: mls-tts-bark data_files: - split: dev path: mls/tts/bark/d