bill317996 / audio-to-midi Goto Github PK

how can i set high pass, low pass and gain filters on WAV file in this code?

D:\0__A\Audio-to-midi-master>python audio2midi.py
Audio to midi : Update in 20190503

input_folder: ./input/
output_folder: ./output/
melody_type: Vocal

Songname: vocals
Traceback (most recent call last):
File "audio2midi.py", line 305, in
main(fp, mp, op)
File "audio2midi.py", line 249, in main
W, Time_arr, Freq_arr = feature_ext(file_path)
File "audio2midi.py", line 182, in feature_ext
Z, Time_arr, Freq_arr, tfrL0, tfrLF, tfrLQ = cfp.feature_extraction(y, sr,
op=512, StartFreq=32.7, StopFreq=2093.0, NumPerOct=48)
File "D:\0__A\Audio-to-midi-master\cfp.py", line 208, in feature_extraction
tfrL0, tfrLF, tfrLQ, f, q, t, CenFreq = CFP_filterbank(x, fr, fs, Hop, h, S
artFreq, 1/StopFreq, g, NumPerOct)
File "D:\0__A\Audio-to-midi-master\cfp.py", line 141, in CFP_filterbank
[tfr, f, t, N] = STFT(x, fr, fs, Hop, h)
File "D:\0__A\Audio-to-midi-master\cfp.py", line 55, in STFT
f = fs*np.linspace(0, 0.5, np.round(N/2), endpoint=True)
File "<array_function internals>", line 5, in linspace
File "D:\ProgramData\Anaconda3\lib\site-packages\numpy\core\function_base.py"
line 113, in linspace
num = operator.index(num)
TypeError: 'numpy.float64' object cannot be interpreted as an integer

While exceuting, i get following error:
`Audio to midi : Update in 20190503

input_folder: ./input/
output_folder: ./output/
melody_type: Vocal

Songname: train01
Traceback (most recent call last):
File "audio2midi.py", line 305, in
main(fp, mp, op)
File "audio2midi.py", line 249, in main
W, Time_arr, Freq_arr = feature_ext(file_path)
File "audio2midi.py", line 182, in feature_ext
Z, Time_arr, Freq_arr, tfrL0, tfrLF, tfrLQ = cfp.feature_extraction(y, sr, Hop=512, StartFreq=32.7, StopFreq=2093.0, NumPerOct=48)
File "/mnt/f/Users/JonasR/Downloads/Audio-to-midi-master/cfp.py", line 208, in feature_extraction
tfrL0, tfrLF, tfrLQ, f, q, t, CenFreq = CFP_filterbank(x, fr, fs, Hop, h, StartFreq, 1/StopFreq, g, NumPerOct)
File "/mnt/f/Users/JonasR/Downloads/Audio-to-midi-master/cfp.py", line 141, in CFP_filterbank
[tfr, f, t, N] = STFT(x, fr, fs, Hop, h)
File "/mnt/f/Users/JonasR/Downloads/Audio-to-midi-master/cfp.py", line 55, in STFT
f = fs*np.linspace(0, 0.5, np.round(N/2), endpoint=True)
File "<array_function internals>", line 5, in linspace
File "/usr/local/lib/python3.8/dist-packages/numpy/core/function_base.py", line 113, in linspace
num = operator.index(num)
TypeError: 'numpy.float64' object cannot be interpreted as an integer`

Code needs to call model_vocal not model_Vocal

Traceback (most recent call last):
  File "audio2midi.py", line 305, in <module>
    main(fp, mp, op)
  File "audio2midi.py", line 243, in main
    Net.load_state_dict(torch.load(model_path, map_location=lambda storage, loc: storage))
  File "/home/trigdev/anaconda3/lib/python3.7/site-packages/torch/serialization.py", line 584, in load
    with _open_file_like(f, 'rb') as opened_file:
  File "/home/trigdev/anaconda3/lib/python3.7/site-packages/torch/serialization.py", line 234, in _open_file_like
    return _open_file(name_or_buffer, mode)
  File "/home/trigdev/anaconda3/lib/python3.7/site-packages/torch/serialization.py", line 215, in __init__
    super(_open_file, self).__init__(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: './model/model_Vocal'