Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart published a Space about 8 hours ago

hugging-apps/silencio-tts

multimodalart updated a Space about 8 hours ago

hugging-apps/silencio-tts

multimodalart published a Space about 22 hours ago

hugging-apps/licon-live-talk

View all activity

hugging-apps 's Spaces 721

StreamTalk

Speech to streaming 3D co-speech gesture animation

Qwen-Drive-1.0-4B

Driving VQA and motion planning with Qwen-Drive-1.0

Hojo ASR Multi V1

Multilingual speech recognition with Hojo-ASR-Multi-V1

AQ3D 3D Instance Segmentation

Segment indoor 3D scans into object instances

A2R-30B-A3B Speaker-Attributed Reasoning

Ask who said what in a multi-speaker recording

DesignAsCode

Editable HTML/CSS graphic design from a text brief

H3-World

Drive a world model with WASD and camera keys

Stream-DiffVSR

Low-latency streamable 4x video super-resolution

STUDIO 1939 — old-animation LoRA for MiniMax-H3

1930s hand-painted animation style, video+audio

MiniMax-H3 Fused Turbo

Few-step MiniMax-H3 video with synchronized audio

MiniMax-H3 Hybrid

Reference-conditioned video with sound, from MiniMax-H3

ICE-012-Audio TTS

Multilingual TTS and voice cloning with ICE-012-Audio

Cross-Encoder Re-Ranking

Re-rank passages with cross-encoders from arXiv 2603.03010

MiniMax Music 3 Latent Refiner

Restore damaged music in MiniMax Music 3 DAV latent space

CuteTTS

Lightweight autoregressive TTS with voice cloning

OmniFusion Translate

Multimodal speech & image-grounded translation, 25 languages

dots.tts

Zero-shot voice-cloning TTS at 48 kHz from dots.tts

CogEvol 4B

Turn a course brief into slides or an interactive widget

LightNav-0 Navigation Demo

Egocentric video + instruction to robot trajectory

Krea 2 360° Panorama LoRAs

Generate and outpaint seamless 360° panoramas with Krea 2

Krea 2 Turbo SDA Diversity LoRA

Same prompt, many seeds - diversity LoRA for Krea 2 Turbo

CrisperWhisper 2.0 Small

Verbatim & intended ASR with word timestamps

ReSplat

Recurrent feed-forward 3D Gaussian Splatting

OpenThai 2.0 OCR Demo

Thai document/handwriting OCR with OpenThai 2.0 27B VLM