Train vosk on my personal voice dataset
Open
- Dominant language
- Jupyter Notebook
- Stars
- 15.1k
- Forks
- 1.8k
- PR merge metrics
- No merged PRs in 30d
Description
I want to train vosk model vosk-model-en-us-0.22 from https://alphacephei.com/vosk/models with an addition data of my voice with transcript of 1 hour so that the model gets overfit with my voice and don't get problem recognizing my voice properly. So how can I train it if someone can give me roadmap how to train that as I am beginner in open source.
How to record my voice in which type i.e. mp3, wav etc.
How to feed recording dataset and transcript to model.
What code I use for training it and testing it.
How to make it better. And any other related query
I tried reading https://alphacephei.com/vosk/lm but could not help myself with it.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.