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

init coarse decoder with argument list

This commit is contained in:
erogol 2020-06-22 14:54:23 +02:00
parent 18d4ed3dc4
commit 70c83671e6
2 changed files with 14 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
models/tacotron.py
View File

@ -46,11 +46,11 @@ class Tacotron(TacotronAbstract):
self.embedding = nn.Embedding(num_chars, 256, padding_idx=0) self.embedding = nn.Embedding(num_chars, 256, padding_idx=0)
self.embedding.weight.data.normal_(0, 0.3) self.embedding.weight.data.normal_(0, 0.3)
self.encoder = Encoder(encoder_in_features) self.encoder = Encoder(encoder_in_features)
self.decoder = Decoder(decoder_in_features, decoder_output_dim, r, memory_size, attn_type, attn_win, self.decoder = Decoder(decoder_in_features, decoder_output_dim, r,
attn_norm, prenet_type, prenet_dropout, memory_size, attn_type, attn_win, attn_norm,
forward_attn, trans_agent, forward_attn_mask, prenet_type, prenet_dropout, forward_attn,
location_attn, attn_K, separate_stopnet, trans_agent, forward_attn_mask, location_attn,
proj_speaker_dim) attn_K, separate_stopnet, proj_speaker_dim)
self.postnet = PostCBHG(decoder_output_dim) self.postnet = PostCBHG(decoder_output_dim)
self.last_linear = nn.Linear(self.postnet.cbhg.gru_features * 2, self.last_linear = nn.Linear(self.postnet.cbhg.gru_features * 2,
postnet_output_dim) postnet_output_dim)
@ -74,7 +74,11 @@ class Tacotron(TacotronAbstract):
self._init_backward_decoder() self._init_backward_decoder()
# setup DDC # setup DDC
if self.double_decoder_consistency: if self.double_decoder_consistency:
self._init_coarse_decoder() 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): def forward(self, characters, text_lengths, mel_specs, mel_lengths=None, speaker_ids=None):

5
models/tacotron2.py
View File

@ -68,7 +68,10 @@ class Tacotron2(TacotronAbstract):
self._init_backward_decoder() self._init_backward_decoder()
# setup DDC # setup DDC
if self.double_decoder_consistency: if self.double_decoder_consistency:
self._init_coarse_decoder() self.coarse_decoder = Decoder(decoder_in_features, self.decoder_output_dim, ddc_r, 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)
@staticmethod @staticmethod
def shape_outputs(mel_outputs, mel_outputs_postnet, alignments): def shape_outputs(mel_outputs, mel_outputs_postnet, alignments):