Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
mio
/
amadeus
like
85
Text-to-Speech
ESPnet
amadeus
jp
audio
arxiv:
1804.00015
License:
cc-by-4.0
Model card
Files
Files and versions
Community
7
Use this model
main
amadeus
/
exp
/
tts_amadeus_vits_finetune_from_jsut_32_sentence
/
images
1 contributor
History:
1 commit
mio
Update model
c7886ed
about 2 years ago
discriminator_backward_time.png
Safe
60.9 kB
Update model
about 2 years ago
discriminator_fake_loss.png
Safe
75.2 kB
Update model
about 2 years ago
discriminator_forward_time.png
Safe
35.8 kB
Update model
about 2 years ago
discriminator_loss.png
Safe
31.2 kB
Update model
about 2 years ago
discriminator_optim_step_time.png
Safe
73.4 kB
Update model
about 2 years ago
discriminator_real_loss.png
Safe
31.5 kB
Update model
about 2 years ago
discriminator_train_time.png
Safe
33.5 kB
Update model
about 2 years ago
generator_adv_loss.png
Safe
64.1 kB
Update model
about 2 years ago
generator_backward_time.png
Safe
63.1 kB
Update model
about 2 years ago
generator_dur_loss.png
Safe
37.1 kB
Update model
about 2 years ago
generator_feat_match_loss.png
Safe
60.8 kB
Update model
about 2 years ago
generator_forward_time.png
Safe
54.6 kB
Update model
about 2 years ago
generator_kl_loss.png
Safe
37.4 kB
Update model
about 2 years ago
generator_loss.png
Safe
56.7 kB
Update model
about 2 years ago
generator_mel_loss.png
Safe
62.4 kB
Update model
about 2 years ago
generator_optim_step_time.png
Safe
55.6 kB
Update model
about 2 years ago
generator_train_time.png
Safe
62.3 kB
Update model
about 2 years ago
gpu_max_cached_mem_GB.png
Safe
26.8 kB
Update model
about 2 years ago
iter_time.png
Safe
56.6 kB
Update model
about 2 years ago
optim0_lr0.png
Safe
22.2 kB
Update model
about 2 years ago
optim1_lr0.png
Safe
21.9 kB
Update model
about 2 years ago
train_time.png
Safe
43.6 kB
Update model
about 2 years ago