search

TensorSpeech / TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
https://tensorspeech.github.io/TensorFlowTTS/
Apache License 2.0
3.84k stars 815 forks source link

Ukrainian TTS #772

Closed egorsmkv closed 2 years ago

egorsmkv commented 2 years ago

Hello.

If I will publish a high-quality dataset (around 8 hours of speech) for Ukrainian, then you can make a processor for it?

hlp-ai commented 2 years ago

Processor is highly related to speech corpus. So, in order to preserve generality, the project would implement the processors for those common datasets. A simple way is to make your dataset compatible with those common datasets, and you can directly make use of the existing processors.

egorsmkv commented 2 years ago

I have seen code for processors and in my opinion it's easy to write own one.

Your advice about common format is right, fully support it.

stale[bot] commented 2 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.

egorsmkv commented 2 years ago

The dataset is here - https://github.com/egorsmkv/ukrainian-tts-datasets/tree/main/lada