louiskirsch / speechT

An opensource speech-to-text software written in tensorflow
Apache License 2.0
157 stars 36 forks source link

Not saving .npz files in the preprocessed folder #7

Closed arpit601 closed 7 years ago

arpit601 commented 7 years ago

After preprocessing, files are not getting stored in the desired folder even though the right directory path has been generated .

Like for developmental data, the directory path is data/preprocessed-power/dev but it shows empty directory even after running the preprocessing step.

arpit601 commented 7 years ago

Does it use power spectrogram as deault preprocessing parameter or mfcc ?

louiskirsch commented 7 years ago

Probably your audioread backend does not support flac Install e.g. ffmpeg and portaudio19-dev sudo apt install portaudio19-dev ffmpeg

We should print an error message if that is the case though.

louiskirsch commented 7 years ago

@arpit601 power by default

louiskirsch commented 7 years ago

@arpit601 Before installing the necessary packages, can you check whether you get a proper error message with #9

Thanks!

louiskirsch commented 7 years ago

solved in #9