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

bug fix for tacotron and tests update

This commit is contained in:
Eren Golge 2019-03-06 13:43:29 +01:00
parent b031a65677
commit a9ce1d4f19
4 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
models/tacotron.py
View File

@ -28,7 +28,7 @@ class Tacotron(nn.Module):
nn.Linear(self.postnet.cbhg.gru_features * 2, linear_dim),
nn.Sigmoid())
def forward(self, characters, text_lengths, mel_specs=None):
def forward(self, characters, text_lengths, mel_specs):
B = characters.size(0)
mask = sequence_mask(text_lengths).to(characters.device)
inputs = self.embedding(characters)

2
models/tacotron2.py
View File

@ -28,7 +28,7 @@ class Tacotron2(nn.Module):
def forward(self, text, text_lengths, mel_specs=None):
# compute mask for padding
mask = sequence_mask(text_lengths).to(characters.device)
mask = sequence_mask(text_lengths).to(text.device)
embedded_inputs = self.embedding(text).transpose(1, 2)
encoder_outputs = self.encoder(embedded_inputs, text_lengths)
mel_outputs, stop_tokens, alignments = self.decoder(

2
tests/layers_tests.py
View File

@ -42,7 +42,7 @@ class DecoderTests(unittest.TestCase):
dummy_input = T.rand(4, 8, 256)
dummy_memory = T.rand(4, 2, 80)
output, alignment, stop_tokens = layer(dummy_input, dummy_memory)
output, alignment, stop_tokens = layer(dummy_input, dummy_memory, mask=None)
assert output.shape[0] == 4
assert output.shape[1] == 1, "size not {}".format(output.shape[1])

7
tests/tacotron_tests.py
View File

@ -21,6 +21,7 @@ c = load_config(os.path.join(file_path, 'test_config.json'))
class TacotronTrainTest(unittest.TestCase):
def test_train_step(self):
input = torch.randint(0, 24, (8, 128)).long().to(device)
input_lengths = torch.randint(100, 129, (8, )).long().to(device)
mel_spec = torch.rand(8, 30, c.audio['num_mels']).to(device)
linear_spec = torch.rand(8, 30, c.audio['num_freq']).to(device)
mel_lengths = torch.randint(20, 30, (8, )).long().to(device)
@ -35,8 +36,8 @@ class TacotronTrainTest(unittest.TestCase):
criterion = L1LossMasked().to(device)
criterion_st = nn.BCELoss().to(device)
model = Tacotron(32, c.embedding_size, c.audio['num_freq'], c.audio['num_mels'],
c.r, c.memory_size).to(device)
model = Tacotron(32, c.audio['num_freq'], c.audio['num_mels'],
c.r, memory_size=c.memory_size).to(device)
model.train()
model_ref = copy.deepcopy(model)
count = 0
@ -47,7 +48,7 @@ class TacotronTrainTest(unittest.TestCase):
optimizer = optim.Adam(model.parameters(), lr=c.lr)
for i in range(5):
mel_out, linear_out, align, stop_tokens = model.forward(
input, mel_spec)
input, input_lengths, mel_spec)
assert stop_tokens.data.max() <= 1.0
assert stop_tokens.data.min() >= 0.0
optimizer.zero_grad()