domerin0 / rnn-speech

Character level speech recognizer using ctc loss with deep rnns in TensorFlow.
MIT License
77 stars 31 forks source link

Reading data problem #7

Closed robotnc closed 8 years ago

robotnc commented 8 years ago

HI I run your code and meet data loading problem, and found that this code might be problem.

file:util/dataprocessor.py, line:78 if len(wav_audio_files) == 0: will_convert = True audio_files = wav_audio_files else: will_convert = False audio_files = flac_audio_files

I think the wav and flac lines should be changed. If no wav file, the audio_file = flac_audio_files.