How to create and train the model for new language? Tajik language

alphacep / vosk-api

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

Apache License 2.0

7.36k stars 1.04k forks source link

Closed komyor09 closed 3 months ago

komyor09 commented 4 months ago

Hi,

I am Komyor. I want to start create new model for Tajik language.

How to create it ? How to build and compile it? How to share it?

Asap like to start works for new language.

Regards, Komyor.

nshmyrev commented 4 months ago

I told you already, you need to collect 1000+ hours of Tajik voices from youtube as a first step

komyor09 commented 3 months ago

Я уже говорил вам, что вам нужно собрать 1000+ часов таджикских голосов на YouTube в качестве первого шага.

After that what I should do? Please tell all steps.

nshmyrev commented 3 months ago

You first collect and share the data then I tell you the steps

komyor09 commented 3 months ago

You first collect and share the data then I tell you the steps

Okay thanks