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

enable phoneme based synthesizing

This commit is contained in:
Eren Golge 2019-01-16 15:53:07 +01:00
parent 72341ae22a
commit 915783e10e
1 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
utils/synthesis.py
View File

@ -11,14 +11,19 @@ from matplotlib import pylab as plt
def synthesis(m, s, CONFIG, use_cuda, ap): def synthesis(m, s, CONFIG, use_cuda, ap):
""" Given the text, synthesising the audio """ """ Given the text, synthesising the audio """
text_cleaner = [CONFIG.text_cleaner] text_cleaner = [CONFIG.text_cleaner]
# print(phoneme_to_sequence(s, text_cleaner)) # print(phoneme_to_sequence(s, text_cleaner))s
# print(sequence_to_phoneme(phoneme_to_sequence(s, text_cleaner))) # print(sequence_to_phoneme(phoneme_to_sequence(s, text_cleaner)))
if CONFIG.use_phonemes:
seq = np.asarray( seq = np.asarray(
phoneme_to_sequence(s, text_cleaner), dtype=np.int32) phoneme_to_sequence(s, text_cleaner, CONFIG.phoneme_language),
dtype=np.int32)
else:
seq = np.asarray(text_to_sequence(s, text_cleaner), dtype=np.int32)
chars_var = torch.from_numpy(seq).unsqueeze(0) chars_var = torch.from_numpy(seq).unsqueeze(0)
if use_cuda: if use_cuda:
chars_var = chars_var.cuda() chars_var = chars_var.cuda()
mel_spec, linear_spec, alignments, stop_tokens = m.forward(chars_var.long()) mel_spec, linear_spec, alignments, stop_tokens = m.forward(
chars_var.long())
linear_spec = linear_spec[0].data.cpu().numpy() linear_spec = linear_spec[0].data.cpu().numpy()
mel_spec = mel_spec[0].data.cpu().numpy() mel_spec = mel_spec[0].data.cpu().numpy()
alignment = alignments[0].cpu().data.numpy() alignment = alignments[0].cpu().data.numpy()