0xfe

points = 256
y = np.zeros(points, dtype="complex64")
y[20] = np.complex(1,0)
ifft_y = fft.irfft(y) * points
plt.figure(figsize=(10, 3))
plt.plot(ifft_y)
plt.show()

0xfe

points = 256
y = np.zeros(points, dtype="complex64")
y[20] = np.complex(1,0) # stick a 1 into the 20th position
plt.figure(figsize=(10, 3))
plt.bar(np.arange(100), np.absolute(y)[:100]) # Show the first 100 points
plt.show()

0xfe

# Generate an integer-period sine wave to
# eliminate spectral leak.
hz = 20
x = np.linspace(0, 2 * np.pi * hz, 128 * hz)
y = np.sin(x)
plt.figure(figsize=(10, 3))
plt.plot(x, y)
plt.show()

# We're only interested in the real components

0xfe

import numpy as np
import matplotlib.pyplot as plt

# Generate Sine wave
hz = 20
x = np.arange(0, 1, 0.001) # 1 second
y = np.sin(2 * np.pi * hz * x)
plt.figure(figsize=(10, 3))
plt.plot(x, y)
plt.show()

0xfe

files = os.listdir("samples")
np.random.shuffle(files)

notes = ['A', 'As', 'B', 'C', 'Cs', 'D', 'Ds', 'E', 'F', 'Fs', 'G', 'Gs']
note_map = {}
for i, note_name in enumerate(notes):
  note_map[note_name] = i

count_by_key = np.zeros((8 * 12))
errors_by_key = np.zeros((8 * 12))

0xfe

self.model.fit(training_xs, training_ys, epochs=150, batch_size=32,
               callbacks=[tf.keras.callbacks.EarlyStopping(monitor='val_mse', patience=25)],
               validation_data=(testing_xs, testing_ys))

0xfe

for octave in range(2, 8):
    random.shuffle(GM_PATCHES)
    for patch in range(0, 15):
        program = GM_PATCHES[patch]
        for key in Note.names:
            sample = Sample("samples/note-%s%s-P%s" % (key, octave, program),
                            program=program, key=key, octave=octave)
            sample.make_wav()
            for pitch_shift_hz in np.concatenate((np.array([0]), np.random.randint(10, 80, 5))):
                sample.transform_wav(

0xfe

self.model = tf.keras.models.Sequential([
        # Add features/channels dim for Conv2D layer
        layers.Reshape((self.s_rows, self.s_cols, 1), input_shape=(self.s_rows, self.s_cols)),
        tf.keras.layers.Dropout(0.2),
        tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
        tf.keras.layers.MaxPooling2D(pool_size=(2,2)),
        tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
        tf.keras.layers.MaxPooling2D(pool_size=(2,2)),
        tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
        tf.keras.layers.MaxPooling2D(pool_size=(2,2)),

0xfe

DefaultConfig = Config(
    rows=513,
    cols = 90,
    s_nperseg = 256,
    s_nfft = 1024,
    s_noverlap = 200,
    resample = 16000)

def spectrogram(file, config=DefaultConfig):
  fs, data = wavfile.read(file)

0xfe

class Note:
    values = {
        "c": 0,
        "d": 2,
        "e": 4,
        "f": 5,
        "g": 7,
        "a": 9,
        "b": 11
    }