Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add stop token visualizaiotn for the notebook

This commit is contained in:
Eren Golge 2018-05-03 05:56:33 -07:00
parent f8d5bbd5d2
commit d02dd47958
2 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
notebooks/utils.py
View File

@ -34,20 +34,25 @@ def create_speech(m, s, CONFIG, use_cuda, ap):
return wav, alignment, spec, stop_tokens
def visualize(alignment, spectrogram, CONFIG):
def visualize(alignment, spectrogram, stop_tokens, CONFIG):
label_fontsize = 16
plt.figure(figsize=(16, 16))
plt.figure(figsize=(16, 24))
plt.subplot(2, 1, 1)
plt.subplot(3, 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)
plt.colorbar()
plt.subplot(3, 1, 2)
plt.plot(range(len(stop_tokens)), list(stop_tokens))
plt.subplot(2, 1, 2)
plt.subplot(3, 1, 3)
librosa.display.specshow(spectrogram.T, sr=CONFIG.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()

2
utils/visual.py
View File

@ -32,4 +32,4 @@ def plot_spectrogram(linear_output, audio):
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
return data