Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Do you plan to publish your Turkish voice model? #3

Open
trappedinspacetime opened this issue Mar 14, 2023 · 2 comments
Open

Do you plan to publish your Turkish voice model? #3

trappedinspacetime opened this issue Mar 14, 2023 · 2 comments

Comments

@trappedinspacetime
Copy link

Hi,
First of all, I congratulate you on your work. You provided a complete tutorial of a Turkish text-to-speech model.
I am trying to code a simple offline virtual assistant. Unfortunately there is no free or open source trained Turkish text-to-speech model.
My decent laptop is not capable of running the code you published in this repo.
Do you plan to publish your Turkish voice model?
Regards.

@Rumeysakeskin
Copy link
Owner

Hi @trappedinspacetime,
Unfortunately, I will not be able to share the model because the sounds in the dataset are licensed.
You can run your codes on google Colab. As you said there is no free TTS dataset in Turkish. You can use audiobooks and their transcripts. I shared example links, click to see them. But this may take time, you will need to clip the audio files into less than 20-second audio files and prepare them to the appropriate format by corresponding subtitles. I shared the prepared data format in the repo. I hope this will help you!

@trappedinspacetime
Copy link
Author

@Rumeysakeskin ,
Thank you for the info. You are really helpful. If I encounter any problem, I'll ask fror your help.
All the best.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants