search

Janghyun1230 / Speaker_Verification

Tensorflow implementation of "Generalized End-to-End Loss for Speaker Verification"
MIT License
349 stars 104 forks source link

Error while executing data_preprocess.py #10

Closed tonytonyissaissa closed 5 years ago

tonytonyissaissa commented 5 years ago

Hi @Janghyun1230, I got this error (processing till speaker 14 was ok): 15th speaker processing... _Traceback (most recent call last): File "data_preprocess.py", line 139, in save_spectrogram_tisv() File "data_preprocess.py", line 112, in save_spectrogram_tisv utter, sr = librosa.core.load(utter_path, config.sr) # load utterance audio File "/usr/local/lib/python3.5/dist-packages/librosa/core/audio.py", line 112, in load with audioread.audio_open(os.path.realpath(path)) as input_file: File "/usr/local/lib/python3.5/dist-packages/audioread/init.py", line 116, in audioopen raise NoBackendError() audioread.NoBackendError

any clues ?

Thanks in advance,

Janghyun1230 commented 5 years ago

@tonytonyissaissa Hi, I'm not sure but I recommend you to check the path of dataset.

MuruganR96 commented 5 years ago

@tonytonyissaissa sir how do you resolve this issue? can you help me? i am also getting same issue. Thanks.

tonytonyissaissa commented 5 years ago

Hi @MuruganR96, The problem was that the dataset contains some corrupted .wav. I think you should search for zero-byte files and anything like .raw and delete them: find -name ".wav" -size 0c -delete find -name "*raw" -delete

MuruganR96 commented 5 years ago

Thank you sir. :relaxed: