Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart published a Space about 6 hours ago

hugging-apps/musci-asr-qwen-1019

multimodalart updated a Space about 6 hours ago

hugging-apps/musci-asr-qwen-1019

multimodalart published a Space about 8 hours ago

hugging-apps/mvrd-spatial-reasoning

View all activity

hugging-apps 's Spaces 869

Musci-ASR-qwen-1019

Multilingual speech recognition, Qwen3-ASR fine-tune

MVRD Spatial Reasoning

Spatial reasoning QA over video with the MVRD-distilled VLM

MANTA-4B

Calibrated medical answers from text and images

OpenThai2.0 ASR Streaming

Thai & mixed Thai-English streaming speech-to-text

hima-tts-nano-te · Telugu TTS

Telugu text-to-speech, 62M params, 6 voices

Fluid Speech Pro

Multilingual speech-to-text for 25 European languages

MANTA-27B

Calibrated medical answers from text and images

Open Vision Banana

Generative visual perception — segment, depth, normals

LES-eg2-665M-asr-en

English ASR with a 665M word-CTC model on EmbeddingGemma 2

Nara Mini v1 TTS

Burmese & English TTS with four preset voices

Haru-4B

Full-duplex speech-to-speech dialogue with Haru-4B

orukqwen-asr-1.7b

Verbatim English speech-to-text (Qwen3-ASR + GSPO)

WVY-Blender-5m

Text to Blender scenes with a 5M-param from-scratch model

UGG — Unified Generative Geometry Model

One image → video, depth and 4D camera trajectory

SOV-Transcribe-1

Speech-to-text with Salesforce's SOV-Transcribe-1

karpo-decision-31B

Typed decisions from one forward pass — choice, noul, score

TaoMate-R1 Multi-Reference Video

Reference images to video with speech in 3 steps

FlashMotion — Music to 3D Dance

Turn a music track into a rendered 3D dance

Graph Energy Matching

Energy-based molecular graph generation (MOSES)

Video-Mirai Video Generation

Few-step autoregressive text-to-video with Video-Mirai

ci-proto

Zero-shot probabilistic time-series forecasting

MoganOCR-TR

Turkish document page to Markdown OCR

rakedoc-nano-2

Document page → markdown with rakedoc-nano-2 (1.2B)

AnyMo

Wearable-IMU motion captioning & activity recognition