Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
espnet
/
siddhana_fsc_challenge_asr_train_asr_hubert_transformer_adam_specaug_r-truncated-36174d
like
0
Automatic Speech Recognition
ESPnet
fsc_challenge
English
audio
arxiv:
1804.00015
License:
cc-by-4.0
Model card
Files
Files and versions
Community
Use this model
main
siddhana_fsc_challenge_asr_train_asr_hubert_transformer_adam_specaug_r-truncated-36174d
/
exp
/
asr_train_asr_hubert_transformer_adam_specaug_raw_en_word
/
images
1 contributor
History:
1 commit
Siddhant
Upload model from zenodo
c01a05b
almost 3 years ago
acc.png
29.1 kB
Upload model from zenodo
almost 3 years ago
backward_time.png
57.6 kB
Upload model from zenodo
almost 3 years ago
cer.png
21.9 kB
Upload model from zenodo
almost 3 years ago
cer_ctc.png
24.6 kB
Upload model from zenodo
almost 3 years ago
forward_time.png
36.8 kB
Upload model from zenodo
almost 3 years ago
gpu_max_cached_mem_GB.png
23.8 kB
Upload model from zenodo
almost 3 years ago
iter_time.png
57.6 kB
Upload model from zenodo
almost 3 years ago
loss.png
29 kB
Upload model from zenodo
almost 3 years ago
loss_att.png
28.7 kB
Upload model from zenodo
almost 3 years ago
loss_ctc.png
30.4 kB
Upload model from zenodo
almost 3 years ago
optim0_lr0.png
36.8 kB
Upload model from zenodo
almost 3 years ago
optim_step_time.png
57.6 kB
Upload model from zenodo
almost 3 years ago
train_time.png
59.3 kB
Upload model from zenodo
almost 3 years ago
wer.png
24.1 kB
Upload model from zenodo
almost 3 years ago