alphacep / vosk-api

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Apache License 2.0
7.35k stars 1.04k forks source link

how to fine tuning Uzbek language dataset for Vosk model ? #1558

Closed RifatMamayusupov closed 2 months ago

RifatMamayusupov commented 2 months ago

I have dataset created in Kaldi format, so I want to build powerful ASR for uzbek language . I searched several ways to fine tuning and train , but I cannot find enough information. I want to learn to fine tuning my own dataset to Vosk toolkit using Kaldi.

and there is other issue , too which is lexicon dictionary. How to build lexicon dictionary. and if anyone has guide to train dataset , please share it .

Thanks your respose.

nshmyrev commented 2 months ago

Same as https://github.com/alphacep/vosk-api/issues/185