tensorflow-speech-recognition
tensorflow-speech-recognition copied to clipboard
How to record my own speech?
I have tried to record but unsuccessfully. There is module Record.py but it doesn't save speech.
What should I add to code in order to recognize my own speech?
All you need is to generate a wav file. You can do it with your smart phone. Just record your sentence with voice-recorder of your phone as a wav file, then put it into test directory.
test directory as in? couldnt get you, if you could please tell me where.