TTS/utils/visual.py

36 lines
1.1 KiB
Python

import numpy as np
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
def plot_alignment(alignment, info=None):
fig, ax = plt.subplots(figsize=(16, 10))
im = ax.imshow(alignment.T, aspect='auto', origin='lower',
interpolation='none')
fig.colorbar(im, ax=ax)
xlabel = 'Decoder timestep'
if info is not None:
xlabel += '\n\n' + info
plt.xlabel(xlabel)
plt.ylabel('Encoder timestep')
plt.tight_layout()
fig.canvas.draw()
data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
plt.close()
return data
def plot_spectrogram(linear_output, audio):
spectrogram = audio._denormalize(linear_output)
fig = plt.figure(figsize=(16, 10))
plt.imshow(spectrogram.T, aspect="auto", origin="lower")
plt.colorbar()
plt.tight_layout()
fig.canvas.draw()
data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
plt.close()
return data