Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
espnet
/
su_openslr36
like
0
Follow
ESPnet
198
Automatic Speech Recognition
ESPnet
su_openslr36
Sundanese
audio
arxiv:
1804.00015
License:
cc-by-4.0
Model card
Files
Files and versions
Community
Use this model
cf1ad95
su_openslr36
/
exp
/
asr_train_asr_raw_bpe1000
/
images
1 contributor
History:
1 commit
Siddhant
import from zenodo
cf1ad95
over 3 years ago
acc.png
Safe
26.3 kB
import from zenodo
over 3 years ago
backward_time.png
Safe
34.4 kB
import from zenodo
over 3 years ago
cer.png
Safe
28.3 kB
import from zenodo
over 3 years ago
cer_ctc.png
Safe
24.9 kB
import from zenodo
over 3 years ago
forward_time.png
Safe
35.6 kB
import from zenodo
over 3 years ago
gpu_max_cached_mem_GB.png
Safe
28.4 kB
import from zenodo
over 3 years ago
iter_time.png
Safe
37.9 kB
import from zenodo
over 3 years ago
loss.png
Safe
23.9 kB
import from zenodo
over 3 years ago
loss_att.png
Safe
25.4 kB
import from zenodo
over 3 years ago
loss_ctc.png
Safe
24.9 kB
import from zenodo
over 3 years ago
optim0_lr0.png
Safe
33.2 kB
import from zenodo
over 3 years ago
optim_step_time.png
Safe
42.4 kB
import from zenodo
over 3 years ago
train_time.png
Safe
27 kB
import from zenodo
over 3 years ago
wer.png
Safe
22.7 kB
import from zenodo
over 3 years ago
