malarinv/tacotron2
1
0
Fork 0
mirror of https://github.com/malarinv/tacotron2 synced 2026-03-09 02:02:33 +00:00
Code Issues Releases Wiki Activity

Compare commits

base: malarinv:mask-utils-0.4
Branches Tags
malarinv:master malarinv:experiments malarinv:clean_slate malarinv:latest_model malarinv:attention_full_mel malarinv:fp16_path malarinv:load_mel_from_disk malarinv:padding-patch-0.4 malarinv:mask-utils-0.4 malarinv:single-gpu-and-0.4
..
compare: malarinv:padding-patch-0.4
Branches Tags
malarinv:master malarinv:experiments malarinv:clean_slate malarinv:latest_model malarinv:attention_full_mel malarinv:fp16_path malarinv:load_mel_from_disk malarinv:padding-patch-0.4 malarinv:mask-utils-0.4 malarinv:single-gpu-and-0.4

3 Commits
mask-utils ... padding-pa

Author SHA1 Message Date
Raul Puri
b20765a3dc 0.4 scalar tensor padding update 2018-05-04 12:12:08 -07:00
Raul Puri
2a394f4aaa integer maxlen for padding 2018-05-04 11:11:14 -07:00
Rafael Valle
2c545ac800 Merge pull request #4 from NVIDIA/mask-utils-0.4 
mask utils update for 0.4 cuda
 2018-05-04 11:02:30 -07:00
1 changed files with 1 additions and 1 deletions
Expand all files Collapse all files

2
model.py
View File

@@ -470,8 +470,8 @@ class Tacotron2(nn.Module):
text_padded, input_lengths, mel_padded, gate_padded, \ text_padded, input_lengths, mel_padded, gate_padded, \
output_lengths = batch output_lengths = batch
text_padded = to_gpu(text_padded).long() text_padded = to_gpu(text_padded).long()
max_len = int(torch.max(input_lengths.data).numpy())
input_lengths = to_gpu(input_lengths).long() input_lengths = to_gpu(input_lengths).long()
max_len = torch.max(input_lengths.data)
mel_padded = to_gpu(mel_padded).float() mel_padded = to_gpu(mel_padded).float()
gate_padded = to_gpu(gate_padded).float() gate_padded = to_gpu(gate_padded).float()
output_lengths = to_gpu(output_lengths).long() output_lengths = to_gpu(output_lengths).long()