visualization.py

import hparams
import json


with open(preset) as f:
  hparams.hparams.parse_json(f.read())

import synthesis
import train
from deepvoice3_pytorch import frontend
synthesis._frontend = getattr(frontend, "en")
train._frontend =  getattr(frontend, "en")

fs = hparams.hparams.sample_rate
hop_length = hparams.hparams.hop_size

def tts(model, text, p=0, speaker_id=None, fast=True, figures=True):
  from synthesis import tts as _tts
  waveform, alignment, spectrogram, mel = _tts(model, text, p, speaker_id, fast)
  if figures:
      visualize(alignment, spectrogram)
  IPython.display.display(Audio(waveform, rate=fs))

def visualize(alignment, spectrogram):
  label_fontsize = 16
  figure(figsize=(16,16))

  subplot(2,1,1)
  imshow(alignment.T, aspect="auto", origin="lower", interpolation=None)
  xlabel("Decoder timestamp", fontsize=label_fontsize)
  ylabel("Encoder timestamp", fontsize=label_fontsize)
  colorbar()

  subplot(2,1,2)
  librosa.display.specshow(spectrogram.T, sr=fs,
                           hop_length=hop_length, x_axis="time", y_axis="linear")
  xlabel("Time", fontsize=label_fontsize)
  ylabel("Hz", fontsize=label_fontsize)
  tight_layout()
  colorbar()



from train import build_model
from train import restore_parts, load_checkpoint

model = build_model()
model = load_checkpoint(checkpoint_path, model, None, True)

texts = [
    "Scientists at the CERN laboratory say they have discovered a new particle.",
    "There's a way to measure the acute emotional intelligence that has never gone out of style.",
    "President Trump met with other leaders at the Group of 20 conference.",
    "The Senate's bill to repeal and replace the Affordable Care Act is now imperiled.",
    "Generative adversarial network or variational auto-encoder.",
    "The buses aren't the problem, they actually provide a solution.",
    "peter piper picked a peck of pickled peppers how many peppers did peter piper pick.",
    "Some have accepted this as a miracle without any physical explanation.",
]

for idx, text in enumerate(texts):
  print(idx, text)
  tts(model, text, figures=False)