class Tacotron(nn.Module):
def __init__(self,
num_chars,
linear_dim=1025,
mel_dim=80,
r=5,
padding_idx=None,
memory_size=5,
attn_win=False,
attn_norm="sigmoid"):
super(Tacotron, self).__init__()
self.r = r
self.mel_dim = mel_dim
self.linear_dim = linear_dim
self.embedding = nn.Embedding(num_chars, 256, padding_idx=padding_idx)
self.embedding.weight.data.normal_(0, 0.3)
self.encoder = Encoder(256)
self.decoder = Decoder(256, mel_dim, r, memory_size, attn_win,
attn_norm)
self.postnet = PostCBHG(mel_dim)
self.last_linear = nn.Sequential(
nn.Linear(self.postnet.cbhg.gru_features * 2, linear_dim),
nn.Sigmoid())
def forward(self, characters, text_lengths, mel_specs):
B = characters.size(0)
mask = sequence_mask(text_lengths).to(characters.device)
inputs = self.embedding(characters)
encoder_outputs = self.encoder(inputs)
mel_outputs, alignments, stop_tokens = self.decoder(
encoder_outputs, mel_specs, mask)
mel_outputs = mel_outputs.view(B, -1, self.mel_dim)
linear_outputs = self.postnet(mel_outputs)
linear_outputs = self.last_linear(linear_outputs)
return mel_outputs, linear_outputs, alignments, stop_tokens
def inference(self, characters):
B = characters.size(0)
inputs = self.embedding(characters)
encoder_outputs = self.encoder(inputs)
mel_outputs, alignments, stop_tokens = self.decoder.inference(
encoder_outputs)
mel_outputs = mel_outputs.view(B, -1, self.mel_dim)
linear_outputs = self.postnet(mel_outputs)
linear_outputs = self.last_linear(linear_outputs)
return mel_outputs, linear_outputs, alignments, stop_tokens
class Tacotron(nn.Module):
def __init__(self,
num_chars,
num_speakers,
r=5,
linear_dim=1025,
mel_dim=80,
memory_size=5,
attn_win=False,
gst=False,
attn_norm="sigmoid",
prenet_type="original",
prenet_dropout=True,
forward_attn=False,
trans_agent=False,
forward_attn_mask=False,
location_attn=True,
separate_stopnet=True):
super(Tacotron, self).__init__()
self.r = r
self.mel_dim = mel_dim
self.linear_dim = linear_dim
self.gst = gst
self.num_speakers = num_speakers
self.embedding = nn.Embedding(num_chars, 256)
self.embedding.weight.data.normal_(0, 0.3)
decoder_dim = 512 if num_speakers > 1 else 256
encoder_dim = 512 if num_speakers > 1 else 256
proj_speaker_dim = 80 if num_speakers > 1 else 0
# boilerplate model
self.encoder = Encoder(encoder_dim)
self.decoder = Decoder(decoder_dim, mel_dim, r, memory_size, attn_win,
attn_norm, prenet_type, prenet_dropout,
forward_attn, trans_agent, forward_attn_mask,
location_attn, separate_stopnet,
proj_speaker_dim)
self.postnet = PostCBHG(mel_dim)
self.last_linear = nn.Linear(self.postnet.cbhg.gru_features * 2,
linear_dim)
# speaker embedding layers
if num_speakers > 1:
self.speaker_embedding = nn.Embedding(num_speakers, 256)
self.speaker_embedding.weight.data.normal_(0, 0.3)
self.speaker_project_mel = nn.Sequential(
nn.Linear(256, 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)
def _init_states(self):
self.speaker_embeddings = None
self.speaker_embeddings_projected = None
def compute_speaker_embedding(self, speaker_ids):
if hasattr(self, "speaker_embedding") and speaker_ids is None:
raise RuntimeError(
" [!] Model has speaker embedding layer but speaker_id is not provided"
)
if hasattr(self, "speaker_embedding") and speaker_ids is not None:
self.speaker_embeddings = self._compute_speaker_embedding(
speaker_ids)
self.speaker_embeddings_projected = self.speaker_project_mel(
self.speaker_embeddings).squeeze(1)
def compute_gst(self, inputs, mel_specs):
gst_outputs = self.gst_layer(mel_specs)
inputs = self._add_speaker_embedding(inputs, gst_outputs)
return inputs
def forward(self, characters, text_lengths, mel_specs, speaker_ids=None):
B = characters.size(0)
mask = sequence_mask(text_lengths).to(characters.device)
inputs = self.embedding(characters)
self._init_states()
self.compute_speaker_embedding(speaker_ids)
if self.num_speakers > 1:
inputs = self._concat_speaker_embedding(inputs,
self.speaker_embeddings)
encoder_outputs = self.encoder(inputs)
if self.gst:
encoder_outputs = self.compute_gst(encoder_outputs, mel_specs)
if self.num_speakers > 1:
encoder_outputs = self._concat_speaker_embedding(
encoder_outputs, self.speaker_embeddings)
mel_outputs, alignments, stop_tokens = self.decoder(
encoder_outputs, mel_specs, mask,
self.speaker_embeddings_projected)
mel_outputs = mel_outputs.view(B, -1, self.mel_dim)
linear_outputs = self.postnet(mel_outputs)
linear_outputs = self.last_linear(linear_outputs)
return mel_outputs, linear_outputs, alignments, stop_tokens
def inference(self, characters, speaker_ids=None, style_mel=None):
B = characters.size(0)
inputs = self.embedding(characters)
self._init_states()
self.compute_speaker_embedding(speaker_ids)
if self.num_speakers > 1:
inputs = self._concat_speaker_embedding(inputs,
self.speaker_embeddings)
encoder_outputs = self.encoder(inputs)
if self.gst and style_mel is not None:
encoder_outputs = self.compute_gst(encoder_outputs, style_mel)
if self.num_speakers > 1:
encoder_outputs = self._concat_speaker_embedding(
encoder_outputs, self.speaker_embeddings)
mel_outputs, alignments, stop_tokens = self.decoder.inference(
encoder_outputs, self.speaker_embeddings_projected)
mel_outputs = mel_outputs.view(B, -1, self.mel_dim)
linear_outputs = self.postnet(mel_outputs)
linear_outputs = self.last_linear(linear_outputs)
return mel_outputs, linear_outputs, alignments, stop_tokens
def _compute_speaker_embedding(self, speaker_ids):
speaker_embeddings = self.speaker_embedding(speaker_ids)
return speaker_embeddings.unsqueeze_(1)
@staticmethod
def _add_speaker_embedding(outputs, speaker_embeddings):
speaker_embeddings_ = speaker_embeddings.expand(
outputs.size(0), outputs.size(1), -1)
outputs = outputs + speaker_embeddings_
return outputs
@staticmethod
def _concat_speaker_embedding(outputs, speaker_embeddings):
speaker_embeddings_ = speaker_embeddings.expand(
outputs.size(0), outputs.size(1), -1)
outputs = torch.cat([outputs, speaker_embeddings_], dim=-1)
return outputs
class Tacotron(nn.Module):
def __init__(self,
num_chars,
num_speakers,
r=5,
linear_dim=1025,
mel_dim=80,
memory_size=5,
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,
separate_stopnet=True):
super(Tacotron, self).__init__()
self.r = r
self.mel_dim = mel_dim
self.linear_dim = linear_dim
self.embedding = nn.Embedding(num_chars, 256)
self.embedding.weight.data.normal_(0, 0.3)
if num_speakers > 1:
self.speaker_embedding = nn.Embedding(num_speakers, 256)
self.speaker_embedding.weight.data.normal_(0, 0.3)
self.encoder = Encoder(256)
self.decoder = Decoder(256, mel_dim, r, memory_size, attn_win,
attn_norm, prenet_type, prenet_dropout,
forward_attn, trans_agent, forward_attn_mask,
location_attn, separate_stopnet)
self.postnet = PostCBHG(mel_dim)
self.last_linear = nn.Linear(self.postnet.cbhg.gru_features * 2,
linear_dim)
def forward(self, characters, text_lengths, mel_specs, speaker_ids=None):
B = characters.size(0)
mask = sequence_mask(text_lengths).to(characters.device)
inputs = self.embedding(characters)
encoder_outputs = self.encoder(inputs)
encoder_outputs = self._add_speaker_embedding(encoder_outputs,
speaker_ids)
mel_outputs, alignments, stop_tokens = self.decoder(
encoder_outputs, mel_specs, mask)
mel_outputs = mel_outputs.view(B, -1, self.mel_dim)
linear_outputs = self.postnet(mel_outputs)
linear_outputs = self.last_linear(linear_outputs)
return mel_outputs, linear_outputs, alignments, stop_tokens
def inference(self, characters, speaker_ids=None):
B = characters.size(0)
inputs = self.embedding(characters)
encoder_outputs = self.encoder(inputs)
encoder_outputs = self._add_speaker_embedding(encoder_outputs,
speaker_ids)
mel_outputs, alignments, stop_tokens = self.decoder.inference(
encoder_outputs)
mel_outputs = mel_outputs.view(B, -1, self.mel_dim)
linear_outputs = self.postnet(mel_outputs)
linear_outputs = self.last_linear(linear_outputs)
return mel_outputs, linear_outputs, alignments, stop_tokens
def _add_speaker_embedding(self, encoder_outputs, speaker_ids):
if hasattr(self, "speaker_embedding") and speaker_ids is None:
raise RuntimeError(
" [!] Model has speaker embedding layer but speaker_id is not provided"
)
if hasattr(self, "speaker_embedding") and speaker_ids is not None:
speaker_embeddings = self.speaker_embedding(speaker_ids)
speaker_embeddings.unsqueeze_(1)
speaker_embeddings = speaker_embeddings.expand(
encoder_outputs.size(0), encoder_outputs.size(1), -1)
encoder_outputs = encoder_outputs + speaker_embeddings
return encoder_outputs
class Tacotron(nn.Module):
def __init__(self,
num_chars,
num_speakers,
r=5,
postnet_output_dim=1025,
decoder_output_dim=80,
memory_size=5,
attn_type='original',
attn_win=False,
gst=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):
super(Tacotron, self).__init__()
self.r = r
self.decoder_output_dim = decoder_output_dim
self.postnet_output_dim = postnet_output_dim
self.gst = gst
self.num_speakers = num_speakers
self.bidirectional_decoder = bidirectional_decoder
decoder_dim = 512 if num_speakers > 1 else 256
encoder_dim = 512 if num_speakers > 1 else 256
proj_speaker_dim = 80 if num_speakers > 1 else 0
# embedding layer
self.embedding = nn.Embedding(num_chars, 256)
self.embedding.weight.data.normal_(0, 0.3)
# boilerplate model
self.encoder = Encoder(encoder_dim)
self.decoder = Decoder(decoder_dim, 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)
if self.bidirectional_decoder:
self.decoder_backward = copy.deepcopy(self.decoder)
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, 256)
self.speaker_embedding.weight.data.normal_(0, 0.3)
self.speaker_project_mel = nn.Sequential(
nn.Linear(256, 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)
def _init_states(self):
self.speaker_embeddings = None
self.speaker_embeddings_projected = None
def compute_speaker_embedding(self, speaker_ids):
if hasattr(self, "speaker_embedding") and speaker_ids is None:
raise RuntimeError(
" [!] Model has speaker embedding layer but speaker_id is not provided"
)
if hasattr(self, "speaker_embedding") and speaker_ids is not None:
self.speaker_embeddings = self._compute_speaker_embedding(
speaker_ids)
self.speaker_embeddings_projected = self.speaker_project_mel(
self.speaker_embeddings).squeeze(1)
def compute_gst(self, inputs, mel_specs):
gst_outputs = self.gst_layer(mel_specs)
inputs = self._add_speaker_embedding(inputs, gst_outputs)
return inputs
def forward(self, characters, text_lengths, mel_specs, speaker_ids=None):
"""
Shapes:
- characters: B x T_in
- text_lengths: B
- mel_specs: B x T_out x D
- speaker_ids: B x 1
"""
self._init_states()
mask = sequence_mask(text_lengths).to(characters.device)
# B x T_in x embed_dim
inputs = self.embedding(characters)
# B x speaker_embed_dim
self.compute_speaker_embedding(speaker_ids)
if self.num_speakers > 1:
# B x T_in x embed_dim + speaker_embed_dim
inputs = self._concat_speaker_embedding(inputs,
self.speaker_embeddings)
# B x T_in x encoder_dim
encoder_outputs = self.encoder(inputs)
if self.gst:
# B x gst_dim
encoder_outputs = self.compute_gst(encoder_outputs, mel_specs)
if self.num_speakers > 1:
encoder_outputs = self._concat_speaker_embedding(
encoder_outputs, self.speaker_embeddings)
# decoder_outputs: B x decoder_dim x T_out
# alignments: B x T_in x encoder_dim
# stop_tokens: B x T_in
decoder_outputs, alignments, stop_tokens = self.decoder(
encoder_outputs, mel_specs, mask,
self.speaker_embeddings_projected)
# B x T_out x decoder_dim
postnet_outputs = self.postnet(decoder_outputs)
# B x T_out x posnet_dim
postnet_outputs = self.last_linear(postnet_outputs)
# B x T_out x decoder_dim
decoder_outputs = decoder_outputs.transpose(1, 2).contiguous()
if self.bidirectional_decoder:
decoder_outputs_backward, alignments_backward = self._backward_inference(
mel_specs, encoder_outputs, mask)
return decoder_outputs, postnet_outputs, alignments, stop_tokens, decoder_outputs_backward, alignments_backward
return decoder_outputs, postnet_outputs, alignments, stop_tokens
def inference(self, characters, speaker_ids=None, style_mel=None):
inputs = self.embedding(characters)
self._init_states()
self.compute_speaker_embedding(speaker_ids)
if self.num_speakers > 1:
inputs = self._concat_speaker_embedding(inputs,
self.speaker_embeddings)
encoder_outputs = self.encoder(inputs)
if self.gst and style_mel is not None:
encoder_outputs = self.compute_gst(encoder_outputs, style_mel)
if self.num_speakers > 1:
encoder_outputs = self._concat_speaker_embedding(
encoder_outputs, self.speaker_embeddings)
decoder_outputs, alignments, stop_tokens = self.decoder.inference(
encoder_outputs, self.speaker_embeddings_projected)
postnet_outputs = self.postnet(decoder_outputs)
postnet_outputs = self.last_linear(postnet_outputs)
decoder_outputs = decoder_outputs.transpose(1, 2)
return decoder_outputs, postnet_outputs, alignments, stop_tokens
def _backward_inference(self, mel_specs, encoder_outputs, mask):
decoder_outputs_b, alignments_b, _ = self.decoder_backward(
encoder_outputs, torch.flip(mel_specs, dims=(1, )), mask,
self.speaker_embeddings_projected)
decoder_outputs_b = decoder_outputs_b.transpose(1, 2).contiguous()
return decoder_outputs_b, alignments_b
def _compute_speaker_embedding(self, speaker_ids):
speaker_embeddings = self.speaker_embedding(speaker_ids)
return speaker_embeddings.unsqueeze_(1)
@staticmethod
def _add_speaker_embedding(outputs, speaker_embeddings):
speaker_embeddings_ = speaker_embeddings.expand(
outputs.size(0), outputs.size(1), -1)
outputs = outputs + speaker_embeddings_
return outputs
@staticmethod
def _concat_speaker_embedding(outputs, speaker_embeddings):
speaker_embeddings_ = speaker_embeddings.expand(
outputs.size(0), outputs.size(1), -1)
outputs = torch.cat([outputs, speaker_embeddings_], dim=-1)
return outputs
class Tacotron(TacotronAbstract):
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)
def forward(self, characters, text_lengths, mel_specs, mel_lengths=None, speaker_ids=None):
"""
Shapes:
- characters: B x T_in
- text_lengths: B
- mel_specs: B x T_out x D
- speaker_ids: B x 1
"""
self._init_states()
input_mask, output_mask = self.compute_masks(text_lengths, mel_lengths)
# B x T_in x embed_dim
inputs = self.embedding(characters)
# B x speaker_embed_dim
if speaker_ids is not None:
self.compute_speaker_embedding(speaker_ids)
if self.num_speakers > 1:
# B x T_in x embed_dim + speaker_embed_dim
inputs = self._concat_speaker_embedding(inputs,
self.speaker_embeddings)
# B x T_in x encoder_in_features
encoder_outputs = self.encoder(inputs)
# sequence masking
encoder_outputs = encoder_outputs * input_mask.unsqueeze(2).expand_as(encoder_outputs)
# global style token
if self.gst:
# B x gst_dim
encoder_outputs = self.compute_gst(encoder_outputs, mel_specs)
if self.num_speakers > 1:
encoder_outputs = self._concat_speaker_embedding(
encoder_outputs, self.speaker_embeddings)
# decoder_outputs: B x decoder_in_features x T_out
# alignments: B x T_in x encoder_in_features
# stop_tokens: B x T_in
decoder_outputs, alignments, stop_tokens = self.decoder(
encoder_outputs, mel_specs, input_mask,
self.speaker_embeddings_projected)
# sequence masking
if output_mask is not None:
decoder_outputs = decoder_outputs * output_mask.unsqueeze(1).expand_as(decoder_outputs)
# B x T_out x decoder_in_features
postnet_outputs = self.postnet(decoder_outputs)
# sequence masking
if output_mask is not None:
postnet_outputs = postnet_outputs * output_mask.unsqueeze(2).expand_as(postnet_outputs)
# B x T_out x posnet_dim
postnet_outputs = self.last_linear(postnet_outputs)
# B x T_out x decoder_in_features
decoder_outputs = decoder_outputs.transpose(1, 2).contiguous()
if self.bidirectional_decoder:
decoder_outputs_backward, alignments_backward = self._backward_pass(mel_specs, encoder_outputs, input_mask)
return decoder_outputs, postnet_outputs, alignments, stop_tokens, decoder_outputs_backward, alignments_backward
if self.double_decoder_consistency:
decoder_outputs_backward, alignments_backward = self._coarse_decoder_pass(mel_specs, encoder_outputs, alignments, input_mask)
return decoder_outputs, postnet_outputs, alignments, stop_tokens, decoder_outputs_backward, alignments_backward
return decoder_outputs, postnet_outputs, alignments, stop_tokens
@torch.no_grad()
def inference(self, characters, speaker_ids=None, style_mel=None):
inputs = self.embedding(characters)
self._init_states()
if speaker_ids is not None:
self.compute_speaker_embedding(speaker_ids)
if self.num_speakers > 1:
inputs = self._concat_speaker_embedding(inputs,
self.speaker_embeddings)
encoder_outputs = self.encoder(inputs)
if self.gst and style_mel is not None:
encoder_outputs = self.compute_gst(encoder_outputs, style_mel)
if self.num_speakers > 1:
encoder_outputs = self._concat_speaker_embedding(
encoder_outputs, self.speaker_embeddings)
decoder_outputs, alignments, stop_tokens = self.decoder.inference(
encoder_outputs, self.speaker_embeddings_projected)
postnet_outputs = self.postnet(decoder_outputs)
postnet_outputs = self.last_linear(postnet_outputs)
decoder_outputs = decoder_outputs.transpose(1, 2)
return decoder_outputs, postnet_outputs, alignments, stop_tokens
