def main1():
path = os.path.join("data", "LJSpeech-1.1")
#preprocess_ljspeech(path)
text_path = os.path.join("data", "train.txt")
texts = process_text(text_path)
if not os.path.exists(hp.alignment_path):
os.mkdir(hp.alignment_path)
tacotron2 = get_Tacotron2()
num = 0
for ind, text in enumerate(texts[num:]):
if (ind > 10):
exit(0)
character = text[0:len(text) - 1]
mel_gt_name = os.path.join(hp.mel_ground_truth,
"ljspeech-mel-%05d.npy" % (ind + num + 1))
mel_gt_target = np.load(mel_gt_name)
_, _, D = load_data(character, mel_gt_target, tacotron2)
np.save(os.path.join(hp.alignment_path,
str(ind + num) + ".npy"),
D,
allow_pickle=False)
def main():
# path = os.path.join("data", "LJSpeech-1.1")
# preprocess_ljspeech(path)
text_path = os.path.join("data", "train.txt")
texts = process_text(text_path)
if not os.path.exists(hp.cemb_path):
os.mkdir(hp.cemb_path)
if not os.path.exists(hp.alignment_path):
os.mkdir(hp.alignment_path)
if not os.path.exists(hp.mel_tacotron2):
os.mkdir(hp.mel_tacotron2)
tacotron2 = get_Tacotron2()
# wave_glow = get_WaveGlow()
num = 0
for ind, text in enumerate(texts[num:]):
print(ind)
# mel_name = os.path.join(hp.mel_ground_truth,
# "ljspeech-mel-%05d.npy" % (ind+1))
# mel_target = np.load(mel_name)
character = text[0:len(text) - 1]
mel_tacotron2, cemb, D = load_data_from_tacotron2(character, tacotron2)
np.save(os.path.join(hp.mel_tacotron2,
str(ind + num) + ".npy"),
mel_tacotron2,
allow_pickle=False)
np.save(os.path.join(hp.cemb_path,
str(ind + num) + ".npy"),
cemb,
allow_pickle=False)
np.save(os.path.join(hp.alignment_path,
str(ind + num) + ".npy"),
D,
allow_pickle=False)
#num = 112000
num = "final"
alpha = 1.0
model = get_FastSpeech(num)
words = "Let’s go out to the airport. The plane landed ten minutes ago."
words = "Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition"
words = "Printing differs from most if not from all the arts"
mel, mel_postnet, mel_torch, mel_postnet_torch = synthesis(model,
words,
alpha=alpha)
if not os.path.exists("results"):
os.mkdir("results")
Audio.tools.inv_mel_spec(
mel_postnet,
os.path.join("results", words + "_" + num + "_griffin_lim.wav"))
wave_glow = utils.get_WaveGlow()
waveglow.inference.inference(
mel_postnet_torch, wave_glow,
os.path.join("results", words + "_" + num + "_waveglow.wav"))
tacotron2 = utils.get_Tacotron2()
mel_tac2, _, _ = utils.load_data_from_tacotron2(words, tacotron2)
waveglow.inference.inference(
torch.stack([torch.from_numpy(mel_tac2).cuda()]), wave_glow,
os.path.join("results", words + "_" + num + "_tacotron2.wav"))
utils.plot_data([mel.numpy(), mel_postnet.numpy(), mel_tac2])
# return [mel, mel_postnet_1, mel_postnet_2], predicted, cemb
return mel, predicted, cemb
def inference(self, character, alpha=1.0):
x = self.embeddings(character)
self.pre_gru.flatten_parameters()
x, _ = self.pre_gru(x)
x = self.pre_linear(x)
x = self.LR(x, alpha=alpha)
self.post_gru.flatten_parameters()
x, _ = self.post_gru(x)
mel = self.post_linear(x)
# mel_postnet_1, mel_postnet_2 = self.postnet.inference(mel)
# return mel, mel_postnet_1, mel_postnet_2
return mel
if __name__ == "__main__":
# Test
num_1 = utils.get_param_num(LightSpeech())
print(num_1)
model = utils.get_Tacotron2()
num_2 = utils.get_param_num(model)
print(num_2 / num_1)