import os import glob import logging import json import numpy as np import torch import torchaudio MATPLOTLIB_FLAG = False def plot_alignment_to_numpy(alignment, info=None): global MATPLOTLIB_FLAG if not MATPLOTLIB_FLAG: import matplotlib matplotlib.use("Agg") MATPLOTLIB_FLAG = True mpl_logger = logging.getLogger('matplotlib') mpl_logger.setLevel(logging.WARNING) import matplotlib.pylab as plt import numpy as np fig, ax = plt.subplots(figsize=(6, 4)) im = ax.imshow(alignment.transpose(), 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