Open drscotthawley opened 1 month ago
Trying to add model path as positional argument, e.g.
from basic_pitch.inference import predict_and_save
from basic_pitch import ICASSP_2022_MODEL_PATH
predict_and_save(
audio_file,
'/content',
True,
True,
True,
True,
ICASSP_2022_MODEL_PATH
)
results in this error:
Predicting MIDI for /...
/usr/local/lib/python3.10/dist-packages/basic_pitch/inference.py:229: UserWarning: PySoundFile failed. Trying audioread instead.
audio_original, _ = librosa.load(str(audio_path), sr=AUDIO_SAMPLE_RATE, mono=True)
/usr/local/lib/python3.10/dist-packages/librosa/core/audio.py:184: FutureWarning: librosa.core.audio.__audioread_load
Deprecated as of librosa version 0.10.0.
It will be removed in librosa version 1.0.
y, sr_native = __audioread_load(path, offset, duration, dtype)
---------------------------------------------------------------------------
LibsndfileError Traceback (most recent call last)
[/usr/local/lib/python3.10/dist-packages/librosa/core/audio.py](https://localhost:8080/#) in load(path, sr, mono, offset, duration, dtype, res_type)
175 try:
--> 176 y, sr_native = __soundfile_load(path, offset, duration, dtype)
177
13 frames
[/usr/local/lib/python3.10/dist-packages/librosa/core/audio.py](https://localhost:8080/#) in __soundfile_load(path, offset, duration, dtype)
208 # Otherwise, create the soundfile object
--> 209 context = sf.SoundFile(path)
210
[/usr/local/lib/python3.10/dist-packages/soundfile.py](https://localhost:8080/#) in __init__(self, file, mode, samplerate, channels, subtype, endian, format, closefd)
657 format, subtype, endian)
--> 658 self._file = self._open(file, mode_int, closefd)
659 if set(mode).issuperset('r+') and self.seekable():
[/usr/local/lib/python3.10/dist-packages/soundfile.py](https://localhost:8080/#) in _open(self, file, mode_int, closefd)
1215 err = _snd.sf_error(file_ptr)
-> 1216 raise LibsndfileError(err, prefix="Error opening {0!r}: ".format(self.name))
1217 if mode_int == _snd.SFM_WRITE:
LibsndfileError: Error opening '/': Format not recognised.
During handling of the above exception, another exception occurred:
IsADirectoryError Traceback (most recent call last)
[<ipython-input-50-2a564e710ae5>](https://localhost:8080/#) in <cell line: 1>()
----> 1 predict_and_save(
2 audio_file,
3 '/content',
4 True,
5 True,
[/usr/local/lib/python3.10/dist-packages/basic_pitch/inference.py](https://localhost:8080/#) in predict_and_save(audio_path_list, output_directory, save_midi, sonify_midi, save_model_outputs, save_notes, model_or_model_path, onset_threshold, frame_threshold, minimum_note_length, minimum_frequency, maximum_frequency, multiple_pitch_bends, melodia_trick, debug_file, sonification_samplerate, midi_tempo)
585 raise e
586 except Exception as e:
--> 587 raise e
[/usr/local/lib/python3.10/dist-packages/basic_pitch/inference.py](https://localhost:8080/#) in predict_and_save(audio_path_list, output_directory, save_midi, sonify_midi, save_model_outputs, save_notes, model_or_model_path, onset_threshold, frame_threshold, minimum_note_length, minimum_frequency, maximum_frequency, multiple_pitch_bends, melodia_trick, debug_file, sonification_samplerate, midi_tempo)
532 print("")
533 try:
--> 534 model_output, midi_data, note_events = predict(
535 pathlib.Path(audio_path),
536 model_or_model_path,
[/usr/local/lib/python3.10/dist-packages/basic_pitch/inference.py](https://localhost:8080/#) in predict(audio_path, model_or_model_path, onset_threshold, frame_threshold, minimum_note_length, minimum_frequency, maximum_frequency, multiple_pitch_bends, melodia_trick, debug_file, midi_tempo)
449 print(f"Predicting MIDI for {audio_path}...")
450
--> 451 model_output = run_inference(audio_path, model_or_model_path, debug_file)
452 min_note_len = int(np.round(minimum_note_length / 1000 * (AUDIO_SAMPLE_RATE / FFT_HOP)))
453 midi_data, note_events = infer.model_output_to_notes(
[/usr/local/lib/python3.10/dist-packages/basic_pitch/inference.py](https://localhost:8080/#) in run_inference(audio_path, model_or_model_path, debug_file)
290
291 output: Dict[str, Any] = {"note": [], "onset": [], "contour": []}
--> 292 for audio_windowed, _, audio_original_length in get_audio_input(audio_path, overlap_len, hop_size):
293 for k, v in model.predict(audio_windowed).items():
294 output[k].append(v)
[/usr/local/lib/python3.10/dist-packages/basic_pitch/inference.py](https://localhost:8080/#) in get_audio_input(audio_path, overlap_len, hop_size)
227 assert overlap_len % 2 == 0, f"overlap_length must be even, got {overlap_len}"
228
--> 229 audio_original, _ = librosa.load(str(audio_path), sr=AUDIO_SAMPLE_RATE, mono=True)
230
231 original_length = audio_original.shape[0]
[/usr/local/lib/python3.10/dist-packages/librosa/core/audio.py](https://localhost:8080/#) in load(path, sr, mono, offset, duration, dtype, res_type)
182 "PySoundFile failed. Trying audioread instead.", stacklevel=2
183 )
--> 184 y, sr_native = __audioread_load(path, offset, duration, dtype)
185 else:
186 raise exc
<decorator-gen-157> in __audioread_load(path, offset, duration, dtype)
[/usr/local/lib/python3.10/dist-packages/librosa/util/decorators.py](https://localhost:8080/#) in __wrapper(func, *args, **kwargs)
57 stacklevel=3, # Would be 2, but the decorator adds a level
58 )
---> 59 return func(*args, **kwargs)
60
61 return decorator(__wrapper)
[/usr/local/lib/python3.10/dist-packages/librosa/core/audio.py](https://localhost:8080/#) in __audioread_load(path, offset, duration, dtype)
238 else:
239 # If the input was not an audioread object, try to open it
--> 240 reader = audioread.audio_open(path)
241
242 with reader as input_file:
[/usr/local/lib/python3.10/dist-packages/audioread/__init__.py](https://localhost:8080/#) in audio_open(path, backends)
125 for BackendClass in backends:
126 try:
--> 127 return BackendClass(path)
128 except DecodeError:
129 pass
[/usr/local/lib/python3.10/dist-packages/audioread/rawread.py](https://localhost:8080/#) in __init__(self, filename)
57 """
58 def __init__(self, filename):
---> 59 self._fh = open(filename, 'rb')
60
61 try:
IsADirectoryError: [Errno 21] Is a directory: '/'
Ok, so correct syntax is to supply a list where it says to supply a list. ;-) But still positional requirement of model path remains:
predict_and_save(
[audio_file],
'/content',
True,
True,
True,
True,
ICASSP_2022_MODEL_PATH
)
README example should read as follows:
predict_and_save(
<input-audio-path-list>,
<output-directory>,
<save-midi>,
<sonify-midi>,
<save-model-outputs>,
<save-notes>,
<model-path>
)
Describe the bug Try to use
predict_and_save
as listed on the README and you getTo Reproduce Steps to reproduce the behavior:
predict_and_save(