Kreshnik Hasanaj
Kreshnik
AI & ML interests
None yet
Recent Activity
updated a collection about 10 hours ago
OCR upvoted a paper 7 days ago
Wan-Streamer v0.2: Higher Resolution, Same Latency upvoted a paper 19 days ago
Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation ModelsOrganizations
None yet
OCR
Language
Voice
-
microsoft/VibeVoice-1.5B
Text-to-Speech • 3B • Updated • 40.3k • 2.42k - Configuration errorFeatured446
FastVLM WebGPU
🍎446Real-time video captioning powered by FastVLM
-
openbmb/VoxCPM-0.5B
Text-to-Speech • Updated • 4.59k • 808 - Paused85
MiMo-Audio-Chat
💬85Chat with Xiaomi MiMo-Audio using voice
Model training
Structured Output
music
OCR
3D
Language
Image
Voice
-
microsoft/VibeVoice-1.5B
Text-to-Speech • 3B • Updated • 40.3k • 2.42k - Configuration errorFeatured446
FastVLM WebGPU
🍎446Real-time video captioning powered by FastVLM
-
openbmb/VoxCPM-0.5B
Text-to-Speech • Updated • 4.59k • 808 - Paused85
MiMo-Audio-Chat
💬85Chat with Xiaomi MiMo-Audio using voice
Papers
Model training