Andrés PRO

ankandrew

12 8 30

https://github.com/ankandrew

ankandrew

AI & ML interests

CV & NLP

Recent Activity

updated a Space 4 days ago

ankandrew/Audio8-TTS-Realistic-0.6b

published a model 5 days ago

mediainbox/redimnet2-b6-onnx

liked a model 5 days ago

vllm-sr/d3-ultra

View all activity

Organizations

ankandrew 's Spaces 17

FastALPR - Automatic License Plate Recognition - Demo

🔍

A high-performance, customizable and simple (ALPR)

MiMo VL 7B RL

🔥

MiMo-VL-7B-RL

Open Image Models - License Plate Detection

🦀

Pre-trained image models using ONNX for fast, out-of-the-box

Audio8 TTS Realistic Playground

🚀

Realistic speech and voice cloning with Audio8 0.6B

Speaker Emotion Explorer

🎙

Analyze audio to reveal speakers and their emotions

PP-OCRv6 Receipt Grouping

🧾

Compare PP-OCRv6 tiers on receipt line grouping

NMFP Two Audio Comparator

🎧

Compare two audio recordings for similarity and alignment

MOSS Transcribe Diarize

🐨

OpenMOSS-Team MOSS-Transcribe-Diarize Demo

Higgs Audio v3 TTS

🔊

Generate speech from text with optional voice cloning

Rembg

👀

Remove backgrounds from photos and see model comparisons

Gemma 4 E4B It

🚀

Chat with a multimodal AI for text, images, audio, video

CLAP

🦀

CLAP (Contrastive Language-Audio Pretraining)

Qwen2.5VL

🔥

Qwen2.5VL 3B/7B variants

Nisqa V2.0

🦀

NISQA v2.0 Demo

SmolVLM2 HighlightGenerator

🐨

Generate highlights from a video automatically

Face Image Quality Ediffiqa

🐠

Face image quality assessment with ediffiqa using OpenCV

Whisper

📚

Whisper v3 ZeroGPU demo.