🤝 Open to Collab

ahk-d

ahk-d

·

AI & ML interests

- Speech Language Models - On Device A.I. - Medical A.I.

Recent Activity

liked a model about 2 hours ago

google/gemma-4-E4B-it

liked a model about 11 hours ago

Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign

liked a model 1 day ago

google/gemma-4-E2B-it

View all activity

Organizations

ahk-d 's Spaces 7

Multilingual Anime TTS

HT-Demucs Spleeter Music Stem Separation - AI Audio Source Separation 2025

Separate audio into stems using HT-Demucs and Spleeter

Shakespeare Language Model Generator

Generate text using various language models

RAVE N

Transform audio using AI-powered style transfer

Stem Remixer

Separate music into drums, bass, other, and vocals

VQ VAE Timbre Transfer Demo

Transfer timbre from one audio to another

Speech To Speech Translation