(self, nmels, hidden_size=512, dropout=0.2)

(ilen, rilen, olen, rolen, sigma)

(self, emotion_global, emotion_local, text, maxlen=1000, threshold=.5, ref_wav=True)

(self, x, length)

(self, attns, prefix)

(self, x, length)

(nbuckets, length, batch_size, drop_last, distributed=False, world_size=None, rank=Non

(self, text, global_ref_audio, local_ref_audio, outputname, wav_input=False)

(self, g_emo, text, outputname)

(length, shape, dtype, device)

(self, i)

(self, i)

(self, text_embed_dim, emo_embed_dim, nmels, maxlength, symbols, ngst, d_model=512, hidden_si

(self, text_embed_dim, emo_embed_dim, nmels, maxlength, ngst, nlst, model_dim, model_hidden_s

(self, datadir)

(self, datadir)

(self, nbuckets, length, batch_size, drop_last)

(self, nbuckets, length, batch_size, drop_last, num_replicas, rank, seed=787)

(self, text_embed_dim, emo_embed_dim, nmels, maxlength, symbols, ngst, nlst, d_model=512, hid

(self, ndim, hidden_size=256, dropout=0.2)

(self, nmels, bottleneck_size=32, hidden_size=256)

(self, maxlength, ndim, scaled=True)

(self, d_model, nhead, dim_feedforward=2048, dropout=0.1)

(self, d_model, nhead, dim_feedforward=2048, dropout=0.1)

(self, d_model, nhead, dim_feedforward=2048, dropout=0.1)

(self, decoder_layers, guided_sigma=0.7, guided_layers=None, norm=None)

(self, decoder_layer, num_layers, d_model, nhead, guided_sigma=0.5, guided_layers=None,

(self, d_model, nhead, dim_feedforward=2048, dropout=0.1)

(self, encoder_layers, guided_sigma=0.3, guided_layers=None, norm=None)

(self, d_model, nhead, dim_feedforward=2048, dropout=0.1)

(self, encoder_layers, guided_sigma=0.3, guided_layers=None, norm=None)

(self, datadir, datatype, vocoder_ckpt_path, maxlength, nmels, emo_embed_dim, text_embed_dim,

(self)

(self, pretrain=True)

(self)

(self)

(self)

(self)

(self)

(input_length, kernel_size, stride)

(self)

(self, emotion_global, text, mels, length_emo_global, length_text, length_mels)

(self, emotion_global, emotion_local, text, mels, length_emo_global, length_emo_local, length_text, length_mel

(self, x, mask=None)

(self, x, dropout)

(self, x)

(self, x)

(self, tgt, memory, tgt_mask=None, memory_mask=None, tgt_key_padding_mask=None, memory_key_pad

(self, tgt, text, emotion, tgt_mask=None, text_mask=None, emo_mask=None, tgt_key_padding_mask=

(self, tgt, memory, tgt_mask=None, memory_mask=None, tgt_key_padding_mask=None, memory_key_pad

(self, tgt, text, tgt_mask=None, memory_mask=None, tgt_key_padding_mask=None,

(self, tgt, text, global_emotion, local_emotion, tgt_mask=None, tgt_key_padding_mask=None, tex

(self, src, src_mask=None, src_key_padding_mask=None)

(self, src, mask=None, src_key_padding_mask=None)

(self, src, global_emotion, local_emotion, src_mask=None, src_key_padding_mask=None, emotion_k

(self, src, global_emotion, local_emotion, mask=None, src_key_padding_mask=None, emotion_key_p

(self, x, length=None)

(self, x, length=None)

(self, emotion_global, text, maxlen=1000, threshold=.5, ref_wav=True)

(current_step)

(self)

(self)

(self, batch)

(self, batch)

(self, epoch)

(self)

(self)

(self, batch, batch_idx)

(self)

(self, batch, batch_idx)