This repository contains dataset for training a Kazakh text-to-speech (TTS) model. The project utilizes the KazakhTTS and KazakhTTS2 corpora and builds upon the ESPnet framework. Pretrained models and vocoders are available.
Paper: KazakhTTS2: Extending the Open-Source Kazakh TTS Corpus With More Data, Speakers, and Topics
GitHub Repository:
https://github.com/IS2AI/Kazakh_TTS
Citation:… See the full description on the dataset page:
https://huggingface.co/datasets/issai/KazakhTTS.