search

jaywalnut310 / glow-tts

A Generative Flow for Text-to-Speech via Monotonic Alignment Search
MIT License
651 stars 150 forks source link

Sharing the results of the Korean model learned in my voice #31

Open rishubil opened 3 years ago

rishubil commented 3 years ago

I used Glow-TTS and Multi-band MelGAN to create Korean TTS using my voice as a dataset. And the sample audio of the result can be found at the bottom of the Colab page.

Demo Colab

The dataset I used was only about 3 hours long, but I got really good results. I'm not very familiar with machine learning, but the results I could make using your code were really impressive. I was very pleased with the quality of the final result and the fast synthesis speed. It is especially good because it can be used even in a CPU environment.

Thanks to all of you for sharing such a great work 😄

ErenBalatkan commented 3 years ago

I would like to thank you for sharing this aswell. In machine learning it is generally really difficult to estimate how much data you need to get a good model, so you sharing this information is really helpful