search

pannous / tensorflow-speech-recognition

🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks
Other
2.17k stars 639 forks source link

Create Spectrograms #49

Open burakipekk opened 7 years ago

burakipekk commented 7 years ago

How did you create "Sample spectrogram, Karen uttering 'zero' with 160 words per minute."? How did you create that gray scale spectrogram?

feiwenbo commented 6 years ago

I also want to ask this question.

pannous commented 6 years ago

take a look at './record.py' instead of painting the spectrograms to the screen you can save it as a file

feiwenbo commented 6 years ago

thank you very much!

burakipekk commented 6 years ago

Spectograms are taken after recording process with this code or is this code using only for spectogram? Also this voice files are created via one file or every file is created is one by one? I mean a person said 'one' in one second one time and the other files 160 times in one second, 200 times in one second etc. are derived from first record through a program.