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

updated a model about 11 hours ago

ysdede/whisper-large-v3-onnx-4graph

published a model about 11 hours ago

ysdede/whisper-large-v3-onnx-4graph

updated a model about 11 hours ago

ysdede/canary-1b-v2-onnx

View all activity

Organizations

None yet

liked 2 models about 14 hours ago

nvidia/NVIDIA-NemotronLabs-RE-USE

Audio-to-Audio • 9.61M • Updated 11 days ago • 27k • 110

nvidia/RE-USE

Audio-to-Audio • 9.61M • Updated 10 days ago • 12.3k • 149

liked 2 Spaces about 15 hours ago

Open TTS Leaderboard

🗣

TTS systems evaluated on objective metrics.

tts Text To Speech

🌍

Text-to-speech (TTS) with Next-gen Kaldi

liked a model 1 day ago

erayyapagci/balbal-v2-manas

Automatic Speech Recognition • Updated 1 day ago • 142 • 10

liked 2 models 8 days ago

Nanbeige/Nanbeige4.3-33B

Text Generation • 33B • Updated 5 days ago • 15.8k • 991

ccore/Qwen3.5-4B-3D-Coder

5B • Updated about 9 hours ago • 44.8k • 517

liked a model 9 days ago

linoyts/Qwen-Image-2.1-DMD2-2steps

Image-to-Image • Updated 3 days ago • 3.02k • 62

liked a model 12 days ago

KRAFTON/Raon-1-mini-preview

Text Generation • 29B • Updated 6 days ago • 3.55k • 230

liked a model 19 days ago

qnguyen3/QUAN-Transcribe-1.0

Automatic Speech Recognition • 0.1B • Updated 19 days ago • 878 • 75

liked a model 21 days ago

beamster/GLM-5.3-Flash-Sushi-2bpw

Image-Text-to-Text • 49B • Updated 21 days ago • 572 • 14

liked 2 models 23 days ago

nvidia/GEN3C-Cosmos-7B

Updated Jun 18, 2025 • 705 • 35

gulucaptain/CameraNoise-I2V

Image-to-Video • Updated Jun 2 • 2

liked a Space 26 days ago

PersistBench Leaderboard

📊

Explore model scores on the PersistBench leaderboard

liked 2 models about 1 month ago

nvidia/PixelUMM

Any-to-Any • Updated 18 days ago • 89

shhivv/taiga-s1

Other • 1.23M • Updated 26 days ago • 818 • 163

liked a Space about 1 month ago

Index-Echo-S2ST-9B

🎙

Voice-preserving speech dubbing across zh/en/es/ja

liked 3 models about 1 month ago