Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
espnet
/
kan-bayashi_vctk_tts_train_gst_fastspeech2_raw_phn_tacotron_g2p_en_no_space_train.loss.ave
like
0
Text-to-Speech
ESPnet
vctk
English
audio
arxiv:
1804.00015
License:
cc-by-4.0
Model card
Files
Files and versions
Community
Use this model
main
kan-bayashi_vctk_tts_train_gst_fastspeech2_raw_phn_tacotron_g2p_en_no_space_train.loss.ave
/
exp
/
tts_train_gst_fastspeech2_raw_phn_tacotron_g2p_en_no_space
/
images
1 contributor
History:
1 commit
Siddhant
import from zenodo
90eb595
about 3 years ago
backward_time.png
78.1 kB
import from zenodo
about 3 years ago
decoder_alpha.png
32.4 kB
import from zenodo
about 3 years ago
duration_loss.png
28.1 kB
import from zenodo
about 3 years ago
encoder_alpha.png
37.9 kB
import from zenodo
about 3 years ago
energy_loss.png
30.3 kB
import from zenodo
about 3 years ago
forward_time.png
78.7 kB
import from zenodo
about 3 years ago
iter_time.png
41 kB
import from zenodo
about 3 years ago
l1_loss.png
30.2 kB
import from zenodo
about 3 years ago
loss.png
26 kB
import from zenodo
about 3 years ago
lr_0.png
35.2 kB
import from zenodo
about 3 years ago
optim_step_time.png
72.5 kB
import from zenodo
about 3 years ago
pitch_loss.png
33.6 kB
import from zenodo
about 3 years ago
train_time.png
39.3 kB
import from zenodo
about 3 years ago