3 1 115

Mehdi Challakh

ragraph-ai

AI & ML interests

LLM, VLM, TTS, RAG, CLIP, CV, T2V

Recent Activity

liked a Space 15 days ago

merve/Grounding_DINO_demo

liked a model 2 months ago

MoritzLaurer/mDeBERTa-v3-base-mnli-xnli

liked a Space 3 months ago

Qwen/Qwen3-TTS

View all activity

Organizations

liked a Space 15 days ago

Grounding DINO Demo

💻

121

Cutting edge open-vocabulary object detection app

liked a model 2 months ago

MoritzLaurer/mDeBERTa-v3-base-mnli-xnli

Zero-Shot Classification • 0.3B • Updated Jan 8, 2024 • 253k • • 303

liked a Space 3 months ago

Qwen3-TTS Demo

🎙

1.87k

Generate speech from text with custom voice, cloning, or presets

liked a Space 6 months ago

PaddleOCR-VL Online Demo

📈

238

Extract text, tables, formulas, and charts from images

liked 2 models 6 months ago

PaddlePaddle/PaddleOCR-VL

Image-Text-to-Text • 1.0B • Updated 22 days ago • 6.78k • 1.59k

joeddav/distilbert-base-uncased-go-emotions-student

Text Classification • 67M • Updated Sep 15, 2025 • 9.51k • • 82

liked 2 Spaces 7 months ago

Kokoro TTS

❤

3.29k

Upgraded to v1.0!

Sesame CSM

🌱

862

Conversational speech generation

liked 2 datasets 7 months ago

Universal-NER/Pile-NER-type

Viewer • Updated Aug 7, 2023 • 45.9k • 323 • 27

numind/NuNER

Viewer • Updated Mar 19, 2024 • 2M • 185 • 40

liked 2 models 7 months ago

ibm-granite/granite-docling-258M

Image-Text-to-Text • Updated Sep 23, 2025 • 63.9k • 1.15k

microsoft/layoutlm-base-uncased

0.1B • Updated Apr 16, 2024 • 152k • 62

liked a Space 7 months ago

granite-docling-258M demo

📝

271

Extract and convert document content from images

liked a dataset 7 months ago

docling-project/DocLayNet-v1.2

Viewer • Updated Feb 10, 2025 • 80.9k • 3.14k • 17

liked 3 models 7 months ago

liked a Space 7 months ago

YOLOv10 Document Layout Analysis

🏆

Analyze scanned documents to detect and label content

liked a model 7 months ago

urchade/gliner_multi-v2.1

Token Classification • Updated Dec 8, 2025 • 20.9k • 157

liked a Space 8 months ago

Segment Anything Web

💻

269

Segment objects in images using click‑based masks