Yunus Dede

ysdede

AI & ML interests

Passionate about audio dataset creation, labeling, and cleaning for domain-specific ASR in healthcare, specializing in fine-tuning models, real-time processing, and ASR error correction using LLMs.

Recent Activity

liked a model about 1 hour ago

microsoft/OptiMind-SFT

liked a model about 1 hour ago

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

liked a model about 1 hour ago

microsoft/VibeVoice-ASR

View all activity

Organizations

None yet

liked 5 models about 1 hour ago

liked 2 models 8 days ago

tencent/HY-WorldPlay

Image-to-Video • Updated Jan 6 • 1.38k • 315

robbyant/lingbot-world-base-cam

Image-to-Video • Updated 8 days ago • 301

liked a model 10 days ago

grikdotnet/parakeet-tdt-0.6b-fp16

Automatic Speech Recognition • Updated Dec 5, 2025 • 50 • 5

liked a Space 13 days ago

VibeVoice

🏃

166

Generate multi‑speaker AI podcasts from a text script

liked 5 models 13 days ago

ekwek/Soprano-1.1-80M

Text-to-Speech • 79.7M • Updated 27 days ago • 36.3k • 198

MiniMaxAI/MiniMax-M2.1

Text Generation • 229B • Updated 13 days ago • 85.6k • • 1.25k

huihui-ai/Huihui-GLM-4.7-Flash-abliterated

Text Generation • 31B • Updated 16 days ago • 7.84k • 66

openbmb/AgentCPM-Report

8B • Updated about 20 hours ago • 5.17k • 293

FlashLabs/Chroma-4B

Any-to-Any • 6B • Updated 13 days ago • 10.1k • 324

liked a Space 13 days ago

Qwen3-TTS Demo

🎙

1.34k

Generate speech with custom, cloned, or preset voices

liked 2 models 13 days ago

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

Text-to-Speech • 2B • Updated 12 days ago • 476k • 911

nvidia/personaplex-7b-v1

Audio-to-Audio • Updated 1 day ago • 228k • 1.72k

liked 2 Spaces 18 days ago

VideoMaMa

⚡

Remove video backgrounds and generate matte videos

SAM2 Video Predictor

🔥

109

Segment and track objects in a video

liked a model 18 days ago

SammyLim/VideoMaMa

Updated 21 days ago • 9

Yunus Dede

AI & ML interests

Recent Activity

Organizations

ysdede's activity

VibeVoice

Qwen3-TTS Demo

VideoMaMa

SAM2 Video Predictor