Traing Korean Model (Real-time speech-to-text (STT) model)

[DukeZacharia]

Hello, I hope you are well. I am a student engaged in a real-time STT project for my academic paper. Although I am from Kenya, I wish to develop a Korean STT model using Vosk as the backbone. Could you guide me on how to proceed, or do you have any papers I could refer to regarding the training of a lightweight model for the Raspberry Pi? Thank you in advance. I look forward to your response.

[nshmyrev]

It is not different from training any other language, you need to get sufficient data. The example is here:

https://github.com/alphacep/vosk-api/blob/master/python/example/colab/vosk-training.ipynb

[DukeZacharia]

Thank you i will take a look