Can i train the model with longer audio files?


(kmrambo) #1

I want to train the model based on my own data. I have 2 questions:

1.) Is it possible to train the model on longer audio files i.e >2 minutes
2.) If it is possible to train, is it advisable to train a fresh model or to re-train the frozen model already published? - I basically want to adapt the model for Indian English.


#2

Hi @kmrambo,

See this post Longer audio files with Deep Speech

Regards,

G