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

Data loader bug fix 2

This commit is contained in:
Eren Golge 2018-03-26 11:07:15 -07:00
parent b62e09b84d
commit 4a800eadf8
4 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
datasets/LJSpeech.py
View File

@ -125,6 +125,7 @@ class LJSpeechDataset(Dataset):
mel = torch.FloatTensor(mel) mel = torch.FloatTensor(mel)
mel_lengths = torch.LongTensor(mel_lengths) mel_lengths = torch.LongTensor(mel_lengths)
stop_targets = torch.FloatTensor(stop_targets) stop_targets = torch.FloatTensor(stop_targets)
return text, text_lenghts, linear, mel, mel_lengths, stop_targets, item_idxs[0] return text, text_lenghts, linear, mel, mel_lengths, stop_targets, item_idxs[0]
raise TypeError(("batch must contain tensors, numbers, dicts or lists;\ raise TypeError(("batch must contain tensors, numbers, dicts or lists;\

3
layers/tacotron.py
View File

@ -256,9 +256,12 @@ class Decoder(nn.Module):
greedy = not self.training greedy = not self.training
if memory is not None: if memory is not None:
print(memory.shape)
# Grouping multiple frames if necessary # Grouping multiple frames if necessary
if memory.size(-1) == self.memory_dim: if memory.size(-1) == self.memory_dim:
memory = memory.view(B, memory.size(1) // self.r, -1) memory = memory.view(B, memory.size(1) // self.r, -1)
print(memory.shape)
assert memory.size(-1) == self.memory_dim * self.r,\ assert memory.size(-1) == self.memory_dim * self.r,\
" !! Dimension mismatch {} vs {} * {}".format(memory.size(-1), " !! Dimension mismatch {} vs {} * {}".format(memory.size(-1),
self.memory_dim, self.r) self.memory_dim, self.r)

8
utils/data.py
View File

@ -17,13 +17,13 @@ def prepare_data(inputs):
def _pad_tensor(x, length): def _pad_tensor(x, length):
_pad = 0 _pad = 0
assert x.ndim == 2 assert x.ndim == 2
return np.pad(x, [[0, 0], [0, length - x.shape[1]]], mode='constant', constant_values=_pad) x = np.pad(x, [[0, 0], [0, length - x.shape[1]]], mode='constant', constant_values=_pad)
return x
def prepare_tensor(inputs, out_steps): def prepare_tensor(inputs, out_steps):
max_len = max((x.shape[1] for x in inputs)) + 1 # zero-frame max_len = max((x.shape[1] for x in inputs)) + 1 # zero-frame
remainder = max_len % out_steps remainder = max_len % out_steps
return np.stack([_pad_tensor(x, max_len + remainder) for x in inputs]) return np.stack([_pad_tensor(x, max_len + (out_steps - remainder)) for x in inputs])
def _pad_stop_target(x, length): def _pad_stop_target(x, length):
@ -35,7 +35,7 @@ def _pad_stop_target(x, length):
def prepare_stop_target(inputs, out_steps): def prepare_stop_target(inputs, out_steps):
max_len = max((x.shape[0] for x in inputs)) + 1 # zero-frame max_len = max((x.shape[0] for x in inputs)) + 1 # zero-frame
remainder = max_len % out_steps remainder = max_len % out_steps
return np.stack([_pad_stop_target(x, max_len + remainder) for x in inputs]) return np.stack([_pad_stop_target(x, max_len + (out_steps - remainder)) for x in inputs])
def pad_per_step(inputs, pad_len): def pad_per_step(inputs, pad_len):