def test_in_out(self):
layer = Encoder(128)
dummy_input = T.rand(4, 8, 128)
print(layer)
output = layer(dummy_input)
print(output.shape)
assert output.shape[0] == 4
assert output.shape[1] == 8
assert output.shape[2] == 256 # 128 * 2 BiRNN
def __init__(self,
num_chars,
num_speakers,
r=5,
postnet_output_dim=1025,
decoder_output_dim=80,
attn_type='original',
attn_win=False,
attn_norm="sigmoid",
prenet_type="original",
prenet_dropout=True,
forward_attn=False,
trans_agent=False,
forward_attn_mask=False,
location_attn=True,
attn_K=5,
separate_stopnet=True,
bidirectional_decoder=False,
double_decoder_consistency=False,
ddc_r=None,
encoder_in_features=256,
decoder_in_features=256,
speaker_embedding_dim=None,
gst=False,
gst_embedding_dim=256,
gst_num_heads=4,
gst_style_tokens=10,
memory_size=5):
super(Tacotron,
self).__init__(num_chars, num_speakers, r, postnet_output_dim,
decoder_output_dim, attn_type, attn_win,
attn_norm, prenet_type, prenet_dropout,
forward_attn, trans_agent, forward_attn_mask,
location_attn, attn_K, separate_stopnet,
bidirectional_decoder, double_decoder_consistency,
ddc_r, encoder_in_features, decoder_in_features,
speaker_embedding_dim, gst, gst_embedding_dim,
gst_num_heads, gst_style_tokens)
# speaker embedding layers
if self.num_speakers > 1:
if not self.embeddings_per_sample:
speaker_embedding_dim = 256
self.speaker_embedding = nn.Embedding(self.num_speakers,
speaker_embedding_dim)
self.speaker_embedding.weight.data.normal_(0, 0.3)
# speaker and gst embeddings is concat in decoder input
if self.num_speakers > 1:
self.decoder_in_features += speaker_embedding_dim # add speaker embedding dim
# embedding layer
self.embedding = nn.Embedding(num_chars, 256, padding_idx=0)
self.embedding.weight.data.normal_(0, 0.3)
# base model layers
self.encoder = Encoder(self.encoder_in_features)
self.decoder = Decoder(self.decoder_in_features, decoder_output_dim, r,
memory_size, attn_type, attn_win, attn_norm,
prenet_type, prenet_dropout, forward_attn,
trans_agent, forward_attn_mask, location_attn,
attn_K, separate_stopnet)
self.postnet = PostCBHG(decoder_output_dim)
self.last_linear = nn.Linear(self.postnet.cbhg.gru_features * 2,
postnet_output_dim)
# global style token layers
if self.gst:
self.gst_layer = GST(num_mel=80,
num_heads=gst_num_heads,
num_style_tokens=gst_style_tokens,
embedding_dim=gst_embedding_dim)
# backward pass decoder
if self.bidirectional_decoder:
self._init_backward_decoder()
# setup DDC
if self.double_decoder_consistency:
self.coarse_decoder = Decoder(
self.decoder_in_features, decoder_output_dim, ddc_r,
memory_size, attn_type, attn_win, attn_norm, prenet_type,
prenet_dropout, forward_attn, trans_agent, forward_attn_mask,
location_attn, attn_K, separate_stopnet)
def __init__(self,
num_chars,
num_speakers,
r=5,
postnet_output_dim=1025,
decoder_output_dim=80,
attn_type='original',
attn_win=False,
attn_norm="sigmoid",
prenet_type="original",
prenet_dropout=True,
forward_attn=False,
trans_agent=False,
forward_attn_mask=False,
location_attn=True,
attn_K=5,
separate_stopnet=True,
bidirectional_decoder=False,
double_decoder_consistency=False,
ddc_r=None,
gst=False,
memory_size=5):
super(Tacotron,
self).__init__(num_chars, num_speakers, r, postnet_output_dim,
decoder_output_dim, attn_type, attn_win,
attn_norm, prenet_type, prenet_dropout,
forward_attn, trans_agent, forward_attn_mask,
location_attn, attn_K, separate_stopnet,
bidirectional_decoder, double_decoder_consistency,
ddc_r, gst)
decoder_in_features = 512 if num_speakers > 1 else 256
encoder_in_features = 512 if num_speakers > 1 else 256
speaker_embedding_dim = 256
proj_speaker_dim = 80 if num_speakers > 1 else 0
# base model layers
self.embedding = nn.Embedding(num_chars, 256, padding_idx=0)
self.embedding.weight.data.normal_(0, 0.3)
self.encoder = Encoder(encoder_in_features)
self.decoder = Decoder(decoder_in_features, decoder_output_dim, r,
memory_size, attn_type, attn_win, attn_norm,
prenet_type, prenet_dropout, forward_attn,
trans_agent, forward_attn_mask, location_attn,
attn_K, separate_stopnet, proj_speaker_dim)
self.postnet = PostCBHG(decoder_output_dim)
self.last_linear = nn.Linear(self.postnet.cbhg.gru_features * 2,
postnet_output_dim)
# speaker embedding layers
if num_speakers > 1:
self.speaker_embedding = nn.Embedding(num_speakers, speaker_embedding_dim)
self.speaker_embedding.weight.data.normal_(0, 0.3)
self.speaker_project_mel = nn.Sequential(
nn.Linear(speaker_embedding_dim, proj_speaker_dim), nn.Tanh())
self.speaker_embeddings = None
self.speaker_embeddings_projected = None
# global style token layers
if self.gst:
gst_embedding_dim = 256
self.gst_layer = GST(num_mel=80,
num_heads=4,
num_style_tokens=10,
embedding_dim=gst_embedding_dim)
# backward pass decoder
if self.bidirectional_decoder:
self._init_backward_decoder()
# setup DDC
if self.double_decoder_consistency:
self.coarse_decoder = Decoder(
decoder_in_features, decoder_output_dim, ddc_r, memory_size,
attn_type, attn_win, attn_norm, prenet_type, prenet_dropout,
forward_attn, trans_agent, forward_attn_mask, location_attn,
attn_K, separate_stopnet, proj_speaker_dim)