def init_vocoder(self):
model_fpath = self.ui.current_vocoder_fpath
# Case of Griffin-lim
if model_fpath is None:
return
else:
self.ui.log("Loading the vocoder %s... " % model_fpath)
self.ui.set_loading(1)
start = timer()
if Path(model_fpath).parent.stem == "melgan":
vocoder_melgan.load_vocoder_melgan(model_fpath)
elif Path(model_fpath).parent.stem == "wavernn":
vocoder.load_model(model_fpath)
else:
return
self.ui.log("Done (%dms)." % int(1000 * (timer() - start)), "append")
self.ui.set_loading(0)
hparams = create_hparams()
stft = TacotronSTFT(hparams.filter_length, hparams.hop_length, hparams.win_length,
hparams.n_mel_channels, hparams.sampling_rate, hparams.mel_fmin,
hparams.mel_fmax)
model_path = "models/mellotron_libritts.pt"
mellotron = load_model(hparams).cuda().eval()
mellotron.load_state_dict(torch.load(model_path)['state_dict'])
waveglow_path = 'models/waveglow_256channels_v4.pt'
waveglow = torch.load(waveglow_path)['model'].cuda().eval()
denoiser = Denoiser(waveglow).cuda().eval()
melgan_path = 'models/multi_speaker.pt'
load_vocoder_melgan(melgan_path)
## Setup dataloaders
arpabet_dict = cmudict.CMUDict('data/cmu_dictionary')
audio_paths = 'data/examples_filelist.txt'
dataloader = TextMelLoader(audio_paths, hparams)
datacollate = TextMelCollate(1)
## Load data
file_idx = 0
audio_path, text, sid = dataloader.audiopaths_and_text[file_idx]
# get audio path, encoded text, pitch contour and mel for gst
text_encoded = torch.LongTensor(text_to_sequence(text, hparams.text_cleaners, arpabet_dict))[None, :].cuda()
pitch_contour = dataloader[file_idx][3][None].cuda()
mel = load_mel(audio_path)