Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
espnet
/
kyrgyz_commonvoice_blstm
like
0
Automatic Speech Recognition
ESPnet
commonvoice
Kyrgyz
audio
arxiv:
1804.00015
License:
cc-by-4.0
Model card
Files
Files and versions
Community
Deploy
Use in ESPnet
e191f1d
kyrgyz_commonvoice_blstm
/
exp
/
asr_train_asr_rnn_tr_raw_ky_bpe150_sp
/
images
2 contributors
History:
1 commit
dzeinali
Update model
e191f1d
almost 2 years ago
acc.png
27.4 kB
Update model
almost 2 years ago
backward_time.png
43.5 kB
Update model
almost 2 years ago
cer.png
20.4 kB
Update model
almost 2 years ago
cer_ctc.png
25.8 kB
Update model
almost 2 years ago
forward_time.png
43.1 kB
Update model
almost 2 years ago
gpu_max_cached_mem_GB.png
23.4 kB
Update model
almost 2 years ago
iter_time.png
26.3 kB
Update model
almost 2 years ago
loss.png
30.2 kB
Update model
almost 2 years ago
loss_att.png
30.4 kB
Update model
almost 2 years ago
loss_ctc.png
33.2 kB
Update model
almost 2 years ago
optim0_lr0.png
17.9 kB
Update model
almost 2 years ago
optim_step_time.png
51.8 kB
Update model
almost 2 years ago
train_time.png
34.4 kB
Update model
almost 2 years ago
wer.png
26.4 kB
Update model
almost 2 years ago