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
lunks
/
Confucius4-R2T2-CoreML-ANE
Like
0
Automatic Speech Recognition
Core ML
apple-neural-engine
speech-to-text
asr
stt
streaming
confucius4
r2t2
License:
netease-model-use-license-agreement
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Confucius4-R2T2-CoreML-ANE
/
r2t2_lm_head_lut8.mlmodelc
321 MB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
lunks
v4: two-lane decoder (two pieces per infer call, grouped-query attention)
b8b7f8c
verified
9 days ago
analytics
v4: two-lane decoder (two pieces per infer call, grouped-query attention)
9 days ago
weights
Confucius4-R2T2 converted for Core ML on the Apple Neural Engine (encoder fp16, decoder LUT8 with 128-row prefill and verify head)
9 days ago
coremldata.bin
1.26 kB
xet
v4: two-lane decoder (two pieces per infer call, grouped-query attention)
9 days ago
metadata.json
15.3 kB
v4: two-lane decoder (two pieces per infer call, grouped-query attention)
9 days ago
model.mil
144 kB
v4: two-lane decoder (two pieces per infer call, grouped-query attention)
9 days ago
