I am trying to improve deepspeech model accuracy for indian english dataset.
how my data should look like, is there any requirements.
what I did:
first I tried recording 6 people’s voice on 8-10 average word sentence. about 30 sentence each, note that same sentence repeated by every person. I got reasonably good accuracy,
then i tried again with 6 people with 40 sentence each. but this time some of the sentence only had one word which is kind of keyword i want to predict correctly. accuracy did not improve like the first time.
so what are some requirement we should keep in mind while recording voice.
1.should there be only sentences not words
2.does some noise around effect accuracy
3. fine tuning on already finetuned model effects accuracy.
4.If I repeated those sentence again with varied decible in wav. (data augumetetion) will it effect accuracy
5. what you suggest for data agumentetion.
1.will adding some noise help
2. will varying speed and pitch helps.
sorry for the big essay but i did not know how to frame this question.