Avihu Dekel

Avihu's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in ibm-granite/granite-speech-4.1-2b-nar 11 days ago

Maximum duration in one input?

👀 1

5

#3 opened 14 days ago by

coder543

New activity in ibm-granite/granite-speech-4.1-2b-nar 14 days ago

flash attention 2 is borked but I got it to work anyways

1

#2 opened 14 days ago by

ctranslate2-4you

updated a model 14 days ago

ibm-granite/granite-speech-4.1-2b-nar

Feature Extraction • 2B • Updated 14 days ago • 3.37k • 42

liked 2 models 14 days ago

ibm-granite/granite-vision-4.1-4b

Image-Text-to-Text • 4B • Updated 8 days ago • 23.8k • 73

ibm-granite/granite-speech-4.1-2b-plus

Automatic Speech Recognition • 2B • Updated 15 days ago • 12.1k • 49

upvoted an article 15 days ago

view article

Article

Granite 4.1 LLMs: How They’re Built

• 

ibm-granite

•

15 days ago

• 68

liked 2 models 15 days ago

ibm-granite/granite-speech-4.1-2b

Automatic Speech Recognition • 2B • Updated 15 days ago • 185k • 93

ibm-granite/granite-speech-4.1-2b-nar

Feature Extraction • 2B • Updated 14 days ago • 3.37k • 42

published a model 15 days ago

ibm-granite/granite-speech-4.1-2b-nar

Feature Extraction • 2B • Updated 14 days ago • 3.37k • 42

New activity in ibm-granite/granite-speech-4.1-2b-nar 16 days ago

Update README.md

#1 opened 16 days ago by

kristunlee

upvoted a paper 17 days ago

Video Analysis and Generation via a Semantic Progress Function

Paper • 2604.22554 • Published 21 days ago • 63

updated a model 18 days ago

ibm-granite/granite-vision-4.1-4b

Image-Text-to-Text • 4B • Updated 8 days ago • 23.8k • 73

updated a model 28 days ago

granite-vision-dev/granite-4.1-3b-vision

4B • Updated 21 days ago • 726 • 1

upvoted a paper about 1 month ago

ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding

Paper • 2603.27064 • Published Mar 28 • 28

upvoted an article about 1 month ago

view article

Article

Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents

• 

ibm-granite

•

Mar 31

• 34

updated a model about 1 month ago

ibm-granite/granite-4.0-3b-vision

Image-Text-to-Text • 4B • Updated 14 days ago • 159k • 109

upvoted 2 papers about 2 months ago

Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs

Paper • 2603.16932 • Published Mar 14 • 88

CARES: Context-Aware Resolution Selector for VLMs

Paper • 2510.19496 • Published Oct 22, 2025 • 9

New activity in ibm-granite/granite-speech 2 months ago

add "translate to English" choice

#2 opened 2 months ago by

Avihu

upvoted a paper 2 months ago

NLE: Non-autoregressive LLM-based ASR by Transcript Editing

Paper • 2603.08397 • Published Mar 9 • 22