Marco
AI & ML interests
Recent Activity
Organizations
-
nvidia/diar_sortformer_4spk-v1
Automatic Speech Recognition • 0.1B • Updated • 81.7k • 163 - Running30
ConvFill Gemma Voice Demo
🎙30Generate spoken output from your voice input
-
nvidia/NVIDIA-NemotronLabs-RE-USE
Audio-to-Audio • 9.61M • Updated • 46.9k • 227 -
nvidia/NVIDIA-NemotronLabs-RE-USE-laughter
Audio-to-Audio • 9.61M • Updated • 2.57k • 17
-
stepfun-ai/GOT-OCR-2.0-hf
Image-Text-to-Text • 0.6B • Updated • 117k • 244 - Running on ZeroAgents83
GOT OCR Transformers
📷83Demo of GOT-OCR 2.0's Transformers implementation
-
allenai/olmOCR-7B-0225-preview
Image-Text-to-Text • 8B • Updated • 40.1k • 705 -
allenai/olmOCR-mix-0225
Viewer • Updated • 259k • 744 • 179
- Running74
SmolVLM 256M Instruct WebGPU
🐨74Generate captions for your images instantly
-
deepseek-ai/Janus-Pro-7B
Any-to-Any • Updated • 18.1k • 3.73k -
Qwen/Qwen2.5-VL-72B-Instruct
Image-Text-to-Text • 73B • Updated • 86.4k • • 668 - PausedAgents228
BEN2
🚀228Remove background from images and videos
- Running573
DeepSeek-R1 WebGPU
🧠573Next-generation reasoning model that runs locally in-browser
- PausedAgents102
Qwen2.5-1M Demo
💻102Ask questions about your uploaded documents
-
mistralai/Mistral-Small-24B-Base-2501
24B • Updated • 16.2k • 282 -
deepseek-ai/deepseek-vl2-small
Image-Text-to-Text • 16B • Updated • 5.27k • 195
- RunningAgentsFeatured276
Qwen3 Omni Demo
⚡276Chat with AI using text, audio, images, and video
- RunningAgents68
Qwen3 Omni Captioner Demo
🐠68Generate captions for your audio recordings
-
Qwen/Qwen3-Omni-30B-A3B-Thinking
Any-to-Any • 32B • Updated • 204k • 342 -
Qwen/Qwen3-Omni-30B-A3B-Instruct
Any-to-Any • 35B • Updated • 353k • 1.06k
- RunningMCP137
Consilium MCP Server
🏢137Multi-AI Expert Consensus Platform
- Runtime errorMCP2
MCP Hackathon Deepfake Watchdog
🛡2Upload your image and/or voice to scan for deepfake misuse o
- Runtime error37
VulnBuster
🛡37AI Security Agent: Multi-MCP Code Vulnerability Scanner
- RunningMCP203
AI Marketing Content Generator
🎨203An AI-powered tool made for content creators and marketers
-
nvidia/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • Updated • 135k • 1.59k - Running on ZeroAgentsFeatured484
Parakeet-TDT-0.6b-V2
484Transcribe audio with timestamps and export CSV/SRT
- Runtime errorAgents33
Blazing Fast Whisper
👁33Blazing Fast Whisper Deployed on HF Inference Endpoints
- Running on CPU UpgradeAgentsFeatured1.54k
Open ASR Leaderboard
🏆1.54kExplore ASR model benchmarks across datasets and languages
- Runtime errorAgents155
RF-DETR
🔥155SOTA real-time object detection model
- PausedAgents50
YOLO ARENA
🏟50compare performance of top object detectors
- Running on ZeroAgentsFeatured96
D-Fine - SOTA Real-Time Object Detector
⚡96Object Detection on Images and Video
- Running on ZeroMCP31
Gaze LLE
👀31Gaze Target Estimation
-
flax-community/t5-recipe-generation
Text Generation • 0.2B • Updated • 535 • 77 -
numind/NuExtract-1.5
Text Generation • 4B • Updated • 1.17k • 252 - RunningAgents12
Signature Detection
👁12Handwritten Signature Detection
-
manycore-research/SpatialLM-Llama-1B
Text Generation • 1B • Updated • 4.71k • 1k
- Running on ZeroMCPFeatured632
LatentSync
👄632Audio Conditioned LipSync with Latent Diffusion Models
- PausedAgents228
BEN2
🚀228Remove background from images and videos
- Running on ZeroAgents84
SmolVLM
📊84Ask questions about images or videos and get answers
- Build errorAgents59
SmolVLM2 HighlightGenerator
🐨59Generate video highlights from uploaded video
-
NexaAI/Qwen2-Audio-7B-GGUF
Audio-Text-to-Text • 8B • Updated • 2.51k • 177 -
kyutai/hibiki-2b-pytorch-bf16
Translation • Updated • 1.35k • 64 -
Zyphra/Zonos-v0.1-hybrid
Text-to-Speech • 2B • Updated • 1.01k • • 1.12k - Running on ZeroAgentsFeatured690
Di♪♪Rhythm
🎶690Blazingly Fast and Embarrassingly Simple Song Generation
-
onnx-community/Kokoro-82M-ONNX
Text-to-Speech • Updated • 81.1k • 183 - Running227
Kokoro Text-to-Speech
🗣227High-quality speech synthesis powered by Kokoro TTS
-
NexaAI/Qwen2-Audio-7B-GGUF
Audio-Text-to-Text • 8B • Updated • 2.51k • 177 -
jonatasgrosman/wav2vec2-large-xlsr-53-english
Automatic Speech Recognition • 0.3B • Updated • 126k • 477
- RunningAgentsFeatured276
Qwen3 Omni Demo
⚡276Chat with AI using text, audio, images, and video
- RunningAgents68
Qwen3 Omni Captioner Demo
🐠68Generate captions for your audio recordings
-
Qwen/Qwen3-Omni-30B-A3B-Thinking
Any-to-Any • 32B • Updated • 204k • 342 -
Qwen/Qwen3-Omni-30B-A3B-Instruct
Any-to-Any • 35B • Updated • 353k • 1.06k
-
nvidia/diar_sortformer_4spk-v1
Automatic Speech Recognition • 0.1B • Updated • 81.7k • 163 - Running30
ConvFill Gemma Voice Demo
🎙30Generate spoken output from your voice input
-
nvidia/NVIDIA-NemotronLabs-RE-USE
Audio-to-Audio • 9.61M • Updated • 46.9k • 227 -
nvidia/NVIDIA-NemotronLabs-RE-USE-laughter
Audio-to-Audio • 9.61M • Updated • 2.57k • 17
- RunningMCP137
Consilium MCP Server
🏢137Multi-AI Expert Consensus Platform
- Runtime errorMCP2
MCP Hackathon Deepfake Watchdog
🛡2Upload your image and/or voice to scan for deepfake misuse o
- Runtime error37
VulnBuster
🛡37AI Security Agent: Multi-MCP Code Vulnerability Scanner
- RunningMCP203
AI Marketing Content Generator
🎨203An AI-powered tool made for content creators and marketers
-
nvidia/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • Updated • 135k • 1.59k - Running on ZeroAgentsFeatured484
Parakeet-TDT-0.6b-V2
484Transcribe audio with timestamps and export CSV/SRT
- Runtime errorAgents33
Blazing Fast Whisper
👁33Blazing Fast Whisper Deployed on HF Inference Endpoints
- Running on CPU UpgradeAgentsFeatured1.54k
Open ASR Leaderboard
🏆1.54kExplore ASR model benchmarks across datasets and languages
- Runtime errorAgents155
RF-DETR
🔥155SOTA real-time object detection model
- PausedAgents50
YOLO ARENA
🏟50compare performance of top object detectors
- Running on ZeroAgentsFeatured96
D-Fine - SOTA Real-Time Object Detector
⚡96Object Detection on Images and Video
- Running on ZeroMCP31
Gaze LLE
👀31Gaze Target Estimation
-
flax-community/t5-recipe-generation
Text Generation • 0.2B • Updated • 535 • 77 -
numind/NuExtract-1.5
Text Generation • 4B • Updated • 1.17k • 252 - RunningAgents12
Signature Detection
👁12Handwritten Signature Detection
-
manycore-research/SpatialLM-Llama-1B
Text Generation • 1B • Updated • 4.71k • 1k
-
stepfun-ai/GOT-OCR-2.0-hf
Image-Text-to-Text • 0.6B • Updated • 117k • 244 - Running on ZeroAgents83
GOT OCR Transformers
📷83Demo of GOT-OCR 2.0's Transformers implementation
-
allenai/olmOCR-7B-0225-preview
Image-Text-to-Text • 8B • Updated • 40.1k • 705 -
allenai/olmOCR-mix-0225
Viewer • Updated • 259k • 744 • 179
- Running on ZeroMCPFeatured632
LatentSync
👄632Audio Conditioned LipSync with Latent Diffusion Models
- PausedAgents228
BEN2
🚀228Remove background from images and videos
- Running on ZeroAgents84
SmolVLM
📊84Ask questions about images or videos and get answers
- Build errorAgents59
SmolVLM2 HighlightGenerator
🐨59Generate video highlights from uploaded video
- Running74
SmolVLM 256M Instruct WebGPU
🐨74Generate captions for your images instantly
-
deepseek-ai/Janus-Pro-7B
Any-to-Any • Updated • 18.1k • 3.73k -
Qwen/Qwen2.5-VL-72B-Instruct
Image-Text-to-Text • 73B • Updated • 86.4k • • 668 - PausedAgents228
BEN2
🚀228Remove background from images and videos
-
NexaAI/Qwen2-Audio-7B-GGUF
Audio-Text-to-Text • 8B • Updated • 2.51k • 177 -
kyutai/hibiki-2b-pytorch-bf16
Translation • Updated • 1.35k • 64 -
Zyphra/Zonos-v0.1-hybrid
Text-to-Speech • 2B • Updated • 1.01k • • 1.12k - Running on ZeroAgentsFeatured690
Di♪♪Rhythm
🎶690Blazingly Fast and Embarrassingly Simple Song Generation
- Running573
DeepSeek-R1 WebGPU
🧠573Next-generation reasoning model that runs locally in-browser
- PausedAgents102
Qwen2.5-1M Demo
💻102Ask questions about your uploaded documents
-
mistralai/Mistral-Small-24B-Base-2501
24B • Updated • 16.2k • 282 -
deepseek-ai/deepseek-vl2-small
Image-Text-to-Text • 16B • Updated • 5.27k • 195
-
onnx-community/Kokoro-82M-ONNX
Text-to-Speech • Updated • 81.1k • 183 - Running227
Kokoro Text-to-Speech
🗣227High-quality speech synthesis powered by Kokoro TTS
-
NexaAI/Qwen2-Audio-7B-GGUF
Audio-Text-to-Text • 8B • Updated • 2.51k • 177 -
jonatasgrosman/wav2vec2-large-xlsr-53-english
Automatic Speech Recognition • 0.3B • Updated • 126k • 477