malarinv
/
tacotron2
mirror of https://github.com/malarinv/tacotron2
1
0
Fork 0
Code Issues Releases Wiki Activity

data_utils.py: rewrite

clean_slate
rafaelvalle 2018-11-25 22:32:47 -08:00
parent fc0cf6a89a
commit 1683a57ae5
1 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
data_utils.py
View File

@ -14,9 +14,8 @@ class TextMelLoader(torch.utils.data.Dataset):
2) normalizes text and converts them to sequences of one-hot vectors 2) normalizes text and converts them to sequences of one-hot vectors
3) computes mel-spectrograms from audio files. 3) computes mel-spectrograms from audio files.
""" """
def __init__(self, audiopaths_and_text, hparams, shuffle=True): def __init__(self, audiopaths_and_text, hparams):
self.audiopaths_and_text = load_filepaths_and_text( self.audiopaths_and_text = load_filepaths_and_text(audiopaths_and_text)
audiopaths_and_text, hparams.sort_by_length)
self.text_cleaners = hparams.text_cleaners self.text_cleaners = hparams.text_cleaners
self.max_wav_value = hparams.max_wav_value self.max_wav_value = hparams.max_wav_value
self.sampling_rate = hparams.sampling_rate self.sampling_rate = hparams.sampling_rate
@ -26,8 +25,7 @@ class TextMelLoader(torch.utils.data.Dataset):
hparams.n_mel_channels, hparams.sampling_rate, hparams.mel_fmin, hparams.n_mel_channels, hparams.sampling_rate, hparams.mel_fmin,
hparams.mel_fmax) hparams.mel_fmax)
random.seed(1234) random.seed(1234)
if shuffle: random.shuffle(self.audiopaths_and_text)
random.shuffle(self.audiopaths_and_text)
def get_mel_text_pair(self, audiopath_and_text): def get_mel_text_pair(self, audiopath_and_text):
# separate filename and text # separate filename and text
@ -38,7 +36,10 @@ class TextMelLoader(torch.utils.data.Dataset):
def get_mel(self, filename): def get_mel(self, filename):
if not self.load_mel_from_disk: if not self.load_mel_from_disk:
audio = load_wav_to_torch(filename, self.sampling_rate) audio, sampling_rate = load_wav_to_torch(filename)
if sampling_rate != self.stft.sampling_rate:
raise ValueError("{} {} SR doesn't match target {} SR".format(
sampling_rate, self.stft.sampling_rate))
audio_norm = audio / self.max_wav_value audio_norm = audio / self.max_wav_value
audio_norm = audio_norm.unsqueeze(0) audio_norm = audio_norm.unsqueeze(0)
audio_norm = torch.autograd.Variable(audio_norm, requires_grad=False) audio_norm = torch.autograd.Variable(audio_norm, requires_grad=False)
@ -87,9 +88,9 @@ class TextMelCollate():
text = batch[ids_sorted_decreasing[i]][0] text = batch[ids_sorted_decreasing[i]][0]
text_padded[i, :text.size(0)] = text text_padded[i, :text.size(0)] = text
# Right zero-pad mel-spec with extra single zero vector to mark the end # Right zero-pad mel-spec
num_mels = batch[0][1].size(0) num_mels = batch[0][1].size(0)
max_target_len = max([x[1].size(1) for x in batch]) + 1 max_target_len = max([x[1].size(1) for x in batch])
if max_target_len % self.n_frames_per_step != 0: if max_target_len % self.n_frames_per_step != 0:
max_target_len += self.n_frames_per_step - max_target_len % self.n_frames_per_step max_target_len += self.n_frames_per_step - max_target_len % self.n_frames_per_step
assert max_target_len % self.n_frames_per_step == 0 assert max_target_len % self.n_frames_per_step == 0
@ -103,7 +104,7 @@ class TextMelCollate():
for i in range(len(ids_sorted_decreasing)): for i in range(len(ids_sorted_decreasing)):
mel = batch[ids_sorted_decreasing[i]][1] mel = batch[ids_sorted_decreasing[i]][1]
mel_padded[i, :, :mel.size(1)] = mel mel_padded[i, :, :mel.size(1)] = mel
gate_padded[i, mel.size(1):] = 1 gate_padded[i, mel.size(1)-1:] = 1
output_lengths[i] = mel.size(1) output_lengths[i] = mel.size(1)
return text_padded, input_lengths, mel_padded, gate_padded, \ return text_padded, input_lengths, mel_padded, gate_padded, \