wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-11 12:00:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

visual updates for phoenemes

Browse Source
This commit is contained in:
Eren Golge
2019-02-25 17:20:36 +01:00
parent a60c9ee47d
commit caae1af4f6
4 changed files with 17 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
utils/visual.py
+14 -9
View File
@@ -3,6 +3,7 @@ import librosa
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
from utils.text import phoneme_to_sequence, sequence_to_phoneme
def plot_alignment(alignment, info=None):
@@ -29,19 +30,22 @@ def plot_spectrogram(linear_output, audio):
return fig
def visualize(alignment, spectrogram, stop_tokens, text, hop_length, CONFIG, spectrogram2=None):
if spectrogram2 is not None:
def visualize(alignment, spectrogram_postnet, stop_tokens, text, hop_length, CONFIG, spectrogram=None):
if spectrogram is not None:
num_plot = 4
else:
num_plot = 3
label_fontsize = 16
plt.figure(figsize=(16, 32))
plt.figure(figsize=(16, 48))
plt.subplot(num_plot, 1, 1)
plt.imshow(alignment.T, aspect="auto", origin="lower", interpolation=None)
plt.xlabel("Decoder timestamp", fontsize=label_fontsize)
plt.ylabel("Encoder timestamp", fontsize=label_fontsize)
if CONFIG.use_phonemes:
seq = phoneme_to_sequence(text, [CONFIG.text_cleaner], CONFIG.phoneme_language)
text = sequence_to_phoneme(seq)
plt.yticks(range(len(text)), list(text))
plt.colorbar()
@@ -50,17 +54,18 @@ def visualize(alignment, spectrogram, stop_tokens, text, hop_length, CONFIG, spe
plt.plot(range(len(stop_tokens)), list(stop_tokens))
plt.subplot(num_plot, 1, 3)
librosa.display.specshow(spectrogram.T, sr=CONFIG.audio['sample_rate'],
librosa.display.specshow(spectrogram_postnet.T, sr=CONFIG.audio['sample_rate'],
hop_length=hop_length, x_axis="time", y_axis="linear")
plt.xlabel("Time", fontsize=label_fontsize)
plt.ylabel("Hz", fontsize=label_fontsize)
plt.tight_layout()
plt.colorbar()
if spectrogram2 is not None:
if spectrogram is not None:
plt.subplot(num_plot, 1, 4)
librosa.display.specshow(spectrogram2.T, sr=CONFIG.audio['sample_rate'],
librosa.display.specshow(spectrogram.T, sr=CONFIG.audio['sample_rate'],
hop_length=hop_length, x_axis="time", y_axis="linear")
plt.xlabel("Time", fontsize=label_fontsize)
plt.ylabel("Hz", fontsize=label_fontsize)
plt.tight_layout()
plt.colorbar()
plt.tight_layout()
plt.colorbar()