Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
espnet
/
amuse_soundstream16k
like
0
Follow
ESPnet
166
ESPnet
amuse
multilingual
audio
codec
arxiv:
1804.00015
License:
cc-by-4.0
Model card
Files
Files and versions
Community
Use this model
main
amuse_soundstream16k
/
exp_16k
/
codec_train_soundstream4_fs16000_raw_fs16000
/
images
1 contributor
History:
1 commit
ftshijt
Update model
9f6296d
5 months ago
adv_loss.png
64.3 kB
Update model
5 months ago
codec_commit_loss.png
33.6 kB
Update model
5 months ago
codec_loss.png
31.5 kB
Update model
5 months ago
codec_quantization_loss.png
23.4 kB
Update model
5 months ago
discriminator_backward_time.png
50.6 kB
Update model
5 months ago
discriminator_forward_time.png
40.6 kB
Update model
5 months ago
discriminator_loss.png
68.4 kB
Update model
5 months ago
discriminator_optim_step_time.png
38.2 kB
Update model
5 months ago
discriminator_train_time.png
42.7 kB
Update model
5 months ago
fake_loss.png
59.7 kB
Update model
5 months ago
feat_match_loss.png
54.2 kB
Update model
5 months ago
generator_backward_time.png
53 kB
Update model
5 months ago
generator_forward_time.png
58.9 kB
Update model
5 months ago
generator_optim_step_time.png
38.9 kB
Update model
5 months ago
generator_train_time.png
57.2 kB
Update model
5 months ago
gpu_max_cached_mem_GB.png
28.4 kB
Update model
5 months ago
iter_time.png
53.5 kB
Update model
5 months ago
loss.png
31.5 kB
Update model
5 months ago
mel_loss.png
30.2 kB
Update model
5 months ago
mel_loss_real.png
32.4 kB
Update model
5 months ago
optim0_lr0.png
33.3 kB
Update model
5 months ago
optim1_lr0.png
33.2 kB
Update model
5 months ago
real_loss.png
60.3 kB
Update model
5 months ago
reconstruct_loss.png
67.4 kB
Update model
5 months ago
train_time.png
45.7 kB
Update model
5 months ago