ExpressiveSpeech

Expressive Speech dataset,

1. Default, we build our own by combining multiple classifier models and use LLM to generate synthetic description, https://github.com/Scicom-AI-Enterprise-Organization/Multilingual-TTS/issues/2
2. gigaspeech, from https://speechcraft2024.github.io/speechcraft2024/
3. libritts_r, from https://speechcraft2024.github.io/speechcraft2024/

Data source for Default

You can follow https://github.com/Scicom-AI-Enterprise-Organization/Multilingual-TTS/blob/main/synthetic-description/download.sh

Source code

Steps to reproduce at https://github.com/Scicom-AI-Enterprise-Organization/Multilingual-TTS/tree/main/synthetic-description

Acknowledgement

Special thanks to https://www.scitix.ai/ for H100 Node!