Hugging Face
Models
Datasets
Spaces
Buckets
new
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
Scicom-intl
/
CallEnhancer
Like
0
Follow
Scicom (MSC) Bhd
36
Audio-to-Audio
speech-restoration
speech-enhancement
bandwidth-extension
telephony
call-center
w2v-bert
lora
dac
License:
cc-by-nc-4.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
CallEnhancer
3.78 GB
Ctrl+K
Ctrl+K
1 contributor
History:
5 commits
huseinzolkepliscicom
Card: a shorter How we measured (534 to 238 words); numbers and figures unchanged
be853d0
verified
4 days ago
assets
CallEnhancer v2: the 188M model at 150k, full band, keeps both parties in one channel (v1 stays at tag v1)
6 days ago
decoder_callcentre
CallEnhancer v2: the 188M model at 150k, full band, keeps both parties in one channel (v1 stays at tag v1)
6 days ago
examples
CallEnhancer v2: the 188M model at 150k, full band, keeps both parties in one channel (v1 stays at tag v1)
6 days ago
fe_callcentre
CallEnhancer v2: the 188M model at 150k, full band, keeps both parties in one channel (v1 stays at tag v1)
6 days ago
.gitattributes
Safe
42.9 kB
CallEnhancer v2: the 188M model at 150k, full band, keeps both parties in one channel (v1 stays at tag v1)
6 days ago
README.md
Safe
8.7 kB
Card: a shorter How we measured (534 to 238 words); numbers and figures unchanged
4 days ago
expand_decoder.py
Safe
8.67 kB
CallEnhancer v2: the 188M model at 150k, full band, keeps both parties in one channel (v1 stays at tag v1)
6 days ago
infer_callcentre.py
Safe
16.8 kB
CallEnhancer v2: the 188M model at 150k, full band, keeps both parties in one channel (v1 stays at tag v1)
6 days ago