Andres Marafioti

andito

·

AI & ML interests

Multimodal models, VLM and TTS

Recent Activity

updated a bucket about 18 hours ago

smolagents/demo-s2s-dashboard

liked a Space 2 days ago

joelniklaus/harness-optimization

liked a model 5 days ago

poolside/Laguna-XS-2.1

View all activity

Organizations

liked a Space 2 days ago

Don't Train the Model, Evolve the Harness

Evolving an agent's harness, not its model, on Harvey's LAB

liked 3 models 5 days ago

poolside/Laguna-XS-2.1

Text Generation • 33B • Updated 4 days ago • 63.6k • 227

poolside/Laguna-S-2.1

Text Generation • 118B • Updated 4 days ago • 82.4k • • 984

poolside/Laguna-M.1

Text Generation • 226B • Updated Jul 14 • 6.56k • 142

liked a model 19 days ago

k2-fsa/OmniVoice

Text-to-Speech • 0.6B • Updated Jul 3 • 951k • 1.3k

liked a Space 23 days ago

Hugging Face Voice - Inkling

Talk to Inkling with faster-qwen3tts voice replies

liked 2 models about 1 month ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 4 days ago • 2.73M • • 10.9k

thinkingmachines/Inkling

Image-Text-to-Text • 952B • Updated Jul 23 • 152k • • 1.74k

liked a Space about 1 month ago

MOSS Transcribe Diarize

Transcribe audio/video with speaker diarization

liked a model about 1 month ago

OpenMOSS-Team/MOSS-Transcribe-Diarize

Audio-Text-to-Text • 0.9B • Updated 23 days ago • 281k • 391

liked a Space about 1 month ago

Agent Manager

Private cloud manager for AI coding CLI sessions

liked a Space about 2 months ago

An Open Realtime Voice You Can Actually Run Yourself

Generate real‑time spoken AI conversations

liked a dataset about 2 months ago

allenai/pixmo-cap

Viewer • Updated Nov 27, 2024 • 717k • 1.2k • 48

liked 2 Spaces about 2 months ago

Gemma Avatar

Talk to Gemma 4 face to face, with a 3D lip-synced avatar

HF Realtime Voice

Voice chat over WebSocket against a HF speech-to-speech

liked 4 Spaces 2 months ago

CUGA Apps

2 dozen real-life agents optimized for open models & stack

Minimal Conversation (S2S backend, WebSocket)

Voice chat over WebSocket against a HF speech-to-speech

Encoder-Free VLM

Train Your Own Encoder-Free VLM in $100

Encoder-Free VLM (DenseFusion-1M + ShareGPT4V)

Encoder-free VLM (Qwen3-1.7B) on DenseFusion-1M + ShareGPT4V

liked a Space 3 months ago

PEEK Frame Selector

Query-free frame selection + captioning for video