I’m willing to train my own simple model for testing numbers 0-9. but I want to be able to recognize through audio.wav files and export the text from them. is that possible if yes then how
Sorry, but your question is unclear.
Please explain properly what you want to achieve and how you are blocked right now.
im sorry for the unclear message.
i want to creat my own speech to text envirement using mozilla open source scripts on gethub “https://github.com/mozilla/DeepSpeech”. what i want to know before starting is if i could recognize audio.wav files using this script, i dont want to use microphone
Read the doc, then, the library is agnostic to this. You can read wav file and feed it …
2 Likes
Why don’t you check the new playbook whether it has all the info you need?
1 Like
thankyou for your help