You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm trying to run Mozilla TTS. I used DDC_TTS_and_MultiBand_MelGAN_TF_Example and it worked exactly like in the example but... it only shows audiofile on my jupyter notebook. I would like to save this file or at least play this on my terminal. I tried to do that like this:
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
>>> Incybro
[July 19, 2020, 11:27am]
Hi,
I'm trying to run Mozilla TTS. I used
DDC_TTS_and_MultiBand_MelGAN_TF_Example and it worked exactly like in
the example but... it only shows audiofile on my jupyter notebook. I
would like to save this file or at least play this on my terminal. I
tried to do that like this:
def tts(model, text, CONFIG, p):
t_1 = time.time()
waveform, alignment, mel_spec, mel_postnet_spec, stop_tokens, inputs = synthesis(model, text, CONFIG, use_cuda, ap, speaker_id, style_wav=None,
truncated=False, enable_eos_bos_chars=CONFIG.enable_eos_bos_chars,
backend='tf')
waveform = vocoder_model.inference(torch.FloatTensor(mel_postnet_spec.T).unsqueeze(0))
waveform = waveform.numpy()[0, 0]
rtf = (time.time() - t_1) / (len(waveform) / ap.sample_rate)
tps = (time.time() - t_1) / len(waveform)
print(waveform.shape)
print(' > Run-time: {}'.format(time.time() - t_1))
print(' > Real-time factor: {}'.format(rtf))
print(' > Time per step: {}'.format(tps))
IPython.display.display(IPython.display.Audio(waveform, rate=CONFIG.audio['sample_rate']))
scipy.io.wavfile.write('test.wav',CONFIG.audio['sample_rate'],waveform)
return alignment, mel_postnet_spec, stop_tokens, waveform
sentence = 'Holly molly, it works!'
align, spec, stop_tokens, wav = tts(model, sentence, TTS_CONFIG, ap)
But it saved a file with 1 minute long and what I hear is a slow motion
voice. How should I do that?
[This is an archived TTS discussion thread from discourse.mozilla.org/t/mozilla-tts-how-to-save-wav]
Beta Was this translation helpful? Give feedback.
All reactions