Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
espnet
/
DCASE23.AudioCaptioning.PreTrained
like
1
Follow
ESPnet
333
Automatic Speech Recognition
ESPnet
clotho_v2
slseanwu/clotho-chatgpt-mixup-50K
audiocaps
English
audio
audio_captioning
License:
cc-by-4.0
Model card
Files
Files and versions
xet
Community
Use this model
main
DCASE23.AudioCaptioning.PreTrained
/
exp
/
asr_pt
/
images
416 kB
1 contributor
History:
1 commit
shikhar7ssu
Upload 19 files
f8585bb
verified
about 1 year ago
acc.png
Safe
30.9 kB
Upload 19 files
about 1 year ago
backward_time.png
Safe
32 kB
Upload 19 files
about 1 year ago
cer.png
Safe
30.8 kB
Upload 19 files
about 1 year ago
clip.png
Safe
14.4 kB
Upload 19 files
about 1 year ago
forward_time.png
Safe
31.4 kB
Upload 19 files
about 1 year ago
gpu_max_cached_mem_GB.png
Safe
20.8 kB
Upload 19 files
about 1 year ago
grad_norm.png
Safe
27.9 kB
Upload 19 files
about 1 year ago
iter_time.png
Safe
28.3 kB
Upload 19 files
about 1 year ago
loss.png
Safe
29.7 kB
Upload 19 files
about 1 year ago
loss_att.png
Safe
30.6 kB
Upload 19 files
about 1 year ago
loss_scale.png
Safe
17.1 kB
Upload 19 files
about 1 year ago
optim0_lr0.png
Safe
33.6 kB
Upload 19 files
about 1 year ago
optim_step_time.png
Safe
30.3 kB
Upload 19 files
about 1 year ago
train_time.png
Safe
30.5 kB
Upload 19 files
about 1 year ago
wer.png
Safe
28 kB
Upload 19 files
about 1 year ago
