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

Update sythesis function for stop tokens

pull/10/head
Eren Golge 2018-05-13 06:34:46 -07:00
parent 060200991e
commit f27281d529
1 changed files with 12 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
notebooks/utils.py
View File

@ -23,7 +23,7 @@ def create_speech(m, s, CONFIG, use_cuda, ap):
torch.from_numpy(seq), volatile=True).unsqueeze(0)
# mel_var = torch.autograd.Variable(torch.from_numpy(mel).type(torch.FloatTensor), volatile=True)
mel_out, linear_out, alignments = m.forward(chars_var)
mel_out, linear_out, alignments, stop_tokens = m.forward(chars_var)
linear_out = linear_out[0].data.cpu().numpy()
alignment = alignments[0].cpu().data.numpy()
spec = ap._denormalize(linear_out)
@ -31,23 +31,29 @@ def create_speech(m, s, CONFIG, use_cuda, ap):
wav = wav[:ap.find_endpoint(wav)]
out = io.BytesIO()
ap.save_wav(wav, out)
return wav, alignment, spec
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()
stop_tokens = stop_tokens.squeeze().detach().to('cpu').numpy()
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()