def experiment_ford_helper(ckpt_dir, data_dir, plot_type="spectrogram",
sound_mode="save",
f0_denom=1.,
n_harmonic_distribution=60,
n_noise_magnitudes=65,
losses=None,
feature_domain="freq",
model=None):
'''
Code general for all Ford experiments.
'''
logging.info("Loading data...")
data_provider = TFRecordProvider(data_dir)
input_tensor = data_provider.get_single_batch(batch_number=1)
#input_tensor["f0"] = tf.convert_to_tensor(np.flip(np.arange(32., 33., 100./np.size(input_tensor["f0"]))), dtype=tf.float32)[tf.newaxis,:,tf.newaxis]
#input_tensor["f0"] = tf.convert_to_tensor(np.arange(1., 200., 100./np.size(input_tensor["f0"])), dtype=tf.float32)[tf.newaxis,:,tf.newaxis]
#N = np.size(input_tensor["f0"])
#x = 2*np.pi/N*np.arange(1,N)
#y = 100 + 50*np.sin(x)
#input_tensor["f0"] = tf.convert_to_tensor(y, dtype=tf.float32)[tf.newaxis,:,tf.newaxis]
#input_tensor["f0"] += 20.
#input_tensor.pop("osc", None)
logging.info("Building model...")
if model is None:
model = ModelBuilder(model_type="f0_rnn_fc_hpn_decoder",
audio_rate=data_provider.audio_rate,
input_rate=data_provider.input_rate,
window_secs=data_provider.example_secs,
f0_denom=f0_denom,
checkpoint_dir=ckpt_dir,
n_harmonic_distribution=n_harmonic_distribution,
n_noise_magnitudes=n_noise_magnitudes,
losses=losses,
feature_domain=feature_domain).build()
logging.info("Normalizing inputs...")
features = model.encode(input_tensor)
logging.info("Synthesizing from f0 signal...")
start = time.time()
output_tensor = model.decode(features, training=False)
time_elapsed = time.time() - start
logging.info("Synthesis took %.3f seconds." % time_elapsed)
logging.info("Plotting signals...")
audio_in = features["audio"].numpy()[0,:]
audio_out = output_tensor.numpy()[0,:]
f0 = input_tensor["f0"].numpy()[0,:]
f0_scaled = features["f0_scaled"].numpy()[0,:]
if plot_type == "signal":
_, ax = plt.subplots(4, 1, figsize=(10, 8))
ax[0].plot(audio_in)
ax[1].plot(audio_out)
ax[2].plot(f0)
ax[3].plot(f0_scaled)
elif plot_type == "spectrogram":
'''mag_in = spectral_ops.compute_mag(audio_in, size=8192).numpy().T
plt.imshow(mag_in, origin="lower")
plt.show()
pdb.set_trace()'''
n_fft = 4096
n_mels = int(n_fft/8)
audio_dict = {"recording": audio_in, "synthesized": audio_out}
for key in audio_dict.keys():
plt.figure()
plot_audio_f0(audio_dict[key], data_provider.audio_rate, f0, data_provider.input_rate, title=key, n_fft=n_fft, n_mels=n_mels)
plt.show()
if sound_mode == "play":
logging.info("Playing original audio...")
sd.play(audio_in, data_provider.audio_rate)
sd.wait()
logging.info("Playing synthesized audio...")
sd.play(audio_out, data_provider.audio_rate)
sd.wait()
elif sound_mode == "save":
audio_in_path = "./audio_in.wav"
audio_out_path = "./audio_out.wav"
logging.info("Saving recorded audio to '%s'..." % audio_in_path)
sf.write(audio_in_path, audio_in, data_provider.audio_rate)
logging.info("Saving synthesized audio to '%s'..." % audio_out_path)
sf.write(audio_out_path, audio_out, data_provider.audio_rate)
