Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
espnet
/
kan-bayashi_libritts_gst_xvector_conformer_fastspeech2
like
0
Text-to-Speech
ESPnet
libritts
English
audio
arxiv:
1804.00015
License:
cc-by-4.0
Model card
Files
Files and versions
Community
Use this model
main
kan-bayashi_libritts_gst_xvector_conformer_fastspeech2
/
exp
/
tts_train_gst+xvector_conformer_fastspeech2_transformer_teacher_raw_phn_tacotron_g2p_en_no_space
/
images
1 contributor
History:
1 commit
Siddhant
import from zenodo
222bd6f
about 3 years ago
backward_time.png
75.1 kB
import from zenodo
about 3 years ago
duration_loss.png
36.1 kB
import from zenodo
about 3 years ago
energy_loss.png
35.3 kB
import from zenodo
about 3 years ago
forward_time.png
89.4 kB
import from zenodo
about 3 years ago
iter_time.png
52.9 kB
import from zenodo
about 3 years ago
l1_loss.png
29.2 kB
import from zenodo
about 3 years ago
loss.png
26.9 kB
import from zenodo
about 3 years ago
lr_0.png
32 kB
import from zenodo
about 3 years ago
optim_step_time.png
94.5 kB
import from zenodo
about 3 years ago
pitch_loss.png
29.5 kB
import from zenodo
about 3 years ago
train_time.png
47.2 kB
import from zenodo
about 3 years ago