This is a single-speaker synthetic speech dataset for Brazilian Portuguese. It carries the Dii voice, a female voice. The audio was synthesized with text-to-speech and adapted to the Dii speaker identity, to train a Dii voice model for Brazilian Portuguese. The dataset contains 1150 recordings, with a metadata.csv transcript file and one WAV file per line.
OpenVoiceOS/pipertts_pt-BR_dii… See the full description on the dataset page:
https://huggingface.co/datasets/TigreGotico/tts-train-synthetic-dii_pt-BR.
