dataset to model / audio to text model

Job ID: 36509328

Budget: $10 – $15 USD

create a audio to text model with https://github.com/vistec-AI/commonvoice-th/tree/main
for swedish with a guide step by step, swedish data set from https://commonvoice.mozilla.org/en/datasets
I need it for vosk-api, it req nvidia gpu todo it