Hugging Face
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Darayut
/
sota-base
Like
0
Automatic Speech Recognition
PyTorch
Safetensors
Khmer
English
omnilingual-asr
ctc
wav2vec2
structured-pruning
khmer
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
sota-base
292 MB
Ctrl+K
Ctrl+K
1 contributor
History:
8 commits
Darayut
Card: inference time at 0% vs 80% sparsity
81eab20
verified
6 days ago
assets
Card: inference time at 0% vs 80% sparsity
6 days ago
omniprune
Release pruned (80% sparsity) Khmer + English omniASR CTC model
8 days ago
.gitattributes
Safe
1.58 kB
Card: pruning diagram and speed/error trade-off figure
6 days ago
README.md
Safe
5.49 kB
Card: inference time at 0% vs 80% sparsity
6 days ago
config.json
Safe
1.08 kB
Release pruned (80% sparsity) Khmer + English omniASR CTC model
8 days ago
inference.py
Safe
2.21 kB
inference.py: put the bundled omniprune package on sys.path
8 days ago
model.safetensors
292 MB
xet
Release pruned (80% sparsity) Khmer + English omniASR CTC model
8 days ago
vocab.json
Safe
67.9 kB
Release pruned (80% sparsity) Khmer + English omniASR CTC model
8 days ago
