Hugging Face
Search models, datasets, users...
Ctrl K
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-large
Like
1
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-large
815 MB
Ctrl+K
Ctrl+K
1 contributor
History:
11 commits
Darayut
Split the architecture figure from the pruning figure
29e9e25
verified
6 days ago
assets
Split the architecture figure from the pruning figure
6 days ago
eval
Add v1 evaluation results (student, fine-tuned teacher, stock 1B, inference time)
13 days ago
omniprune
Release pruned (80% sparsity) Khmer + English omniASR CTC model
27 days ago
.gitattributes
1.69 kB
Split the architecture figure from the pruning figure
6 days ago
README.md
6.32 kB
Split the architecture figure from the pruning figure
6 days ago
config.json
1.47 kB
Release pruned (80% sparsity) Khmer + English omniASR CTC model
27 days ago
inference.py
2.21 kB
inference.py: put the bundled omniprune package on sys.path
27 days ago
model.safetensors
814 MB
xet
Release pruned (80% sparsity) Khmer + English omniASR CTC model
27 days ago
vocab.json
67.9 kB
Release pruned (80% sparsity) Khmer + English omniASR CTC model
27 days ago