Create audio_methods.py

audio_methods.py

@@ -0,0 +1,101 @@
+# WHERE DID I USE SCALING FACTORS TO CONVERT WAV TO MAP?
+
+_SAMPLING_RATE = 16000 # Parameter to pass continuous signal to a discrete one
+_INSTRUMENT_NAME = "Acoustic Grand Piano" # MIDI instrument used
+_SCALING_FACTORS = pd.Series(
+    {"pitch": 64.024558, "step": 0.101410, "duration": 0.199386}
+) # Factors used to normalize song maps
+
+def midi_to_notes(midi_file: str) -> pd.DataFrame:
+  pm = pretty_midi.PrettyMIDI(midi_file)
+  instrument = pm.instruments[0]
+  notes = collections.defaultdict(list)
+
+  # Sort the notes by start time
+  sorted_notes = sorted(instrument.notes, key=lambda note: note.start)
+  prev_start = sorted_notes[0].start
+
+  for note in sorted_notes:
+    start = note.start
+    end = note.end
+    notes['pitch'].append(note.pitch)
+    notes['start'].append(start)
+    notes['end'].append(end)
+    notes['step'].append(start - prev_start)
+    notes['duration'].append(end - start)
+    prev_start = start
+
+  return pd.DataFrame({name: np.array(value) for name, value in notes.items()})
+
+def notes_to_midi(
+  notes: pd.DataFrame,
+  out_file: str,
+  velocity: int = 100,  # note loudness
+) -> pretty_midi.PrettyMIDI:
+
+  pm = pretty_midi.PrettyMIDI()
+  instrument = pretty_midi.Instrument(
+      program=pretty_midi.instrument_name_to_program(
+          _INSTRUMENT_NAME))
+
+  prev_start = 0
+  for i, note in notes.iterrows():
+    start = float(prev_start + note['step'])
+    end = float(start + note['duration'])
+    note = pretty_midi.Note(
+        velocity=velocity,
+        pitch=int(note['pitch']),
+        start=start,
+        end=end,
+    )
+    instrument.notes.append(note)
+    prev_start = start
+
+  pm.instruments.append(instrument)
+  pm.write(out_file)
+  return pm
+
+
+def display_audio(pm: pretty_midi.PrettyMIDI, seconds=120):
+  waveform = pm.fluidsynth(fs=_SAMPLING_RATE)
+  # Take a sample of the generated waveform to mitigate kernel resets
+  waveform_short = waveform[:seconds*_SAMPLING_RATE]
+  return display.Audio(waveform_short, rate=_SAMPLING_RATE)
+
+
+# Define function to convert song map to wav
+
+def map_to_wav(song_map, out_file, instrument_name, velocity=100):
+  contracted_map = tf.squeeze(song_map)
+  song_map_T = contracted_map.numpy().T
+  notes = pd.DataFrame(song_map_T, columns=["pitch", "step", "duration"]).mul(_SCALING_FACTORS, axis=1)
+  notes["pitch"] = notes["pitch"].astype('int32').clip(1, 127)
+
+  pm = pretty_midi.PrettyMIDI()
+  instrument = pretty_midi.Instrument(
+      program=pretty_midi.instrument_name_to_program(
+          instrument_name))
+
+  prev_start = 0
+  for i, note in notes.iterrows():
+    start = float(prev_start + note['step'])
+    end = float(start + note['duration'])
+    note = pretty_midi.Note(
+        velocity=velocity,
+        pitch=int(note['pitch']),
+        start=start,
+        end=end,
+    )
+    instrument.notes.append(note)
+    prev_start = start
+
+  pm.instruments.append(instrument)
+  pm.write(out_file)
+  return pm
+
+def generate_and_display(out_file, instrument_name, model, z_sample=None, velocity=100, seconds=120):
+  song_map = model.generate(z_sample)
+  display.display(imshow(tf.squeeze(song_map)[:,:50]))
+  wav = map_to_wav(song_map, out_file, instrument_name, velocity)
+
+  return display_audio(wav, seconds)