audio dataset render to model for vosk-api
Budget: $10 – $15 USD
I am looking for a freelancer who can help me with rendering my audio dataset to a model for Vosk-API. The audio files are in MP3 format and I require the model to support swedish, which will be specified later. The ideal candidate should have experience in audio processing and machine learning, as well as being familiar with Vosk-API.
the dataset can be found at https://commonvoice.mozilla.org/en/datasets for swedish
example to render found at https://github.com/vistec-AI/commonvoice-th/tree/main
or https://gitlab.utu.fi/almipap/commonvoice-fi
goal
1. create model for vosk-api that working for swedish with common voice
2. document step by step how you did it, so it can be repudes
I provied the docker image build file for it.
left todo how to prepare the data and how to run it.
the dataset can be found at https://commonvoice.mozilla.org/en/datasets for swedish
example to render found at https://github.com/vistec-AI/commonvoice-th/tree/main
or https://gitlab.utu.fi/almipap/commonvoice-fi
goal
1. create model for vosk-api that working for swedish with common voice
2. document step by step how you did it, so it can be repudes
I provied the docker image build file for it.
left todo how to prepare the data and how to run it.