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 6 days ago

mistralai/Voxtral-Small-24B-2507

liked a model 6 days ago

mistralai/Voxtral-Mini-3B-2507

liked a model 11 days ago

kyutai/stt-2.6b-en

View all activity

Organizations

None yet

liked 2 models 6 days ago

mistralai/Voxtral-Small-24B-2507

24B • Updated 1 day ago • 4.67k • 349

mistralai/Voxtral-Mini-3B-2507

5B • Updated 1 day ago • 86k • 450

liked 2 models 11 days ago

kyutai/stt-2.6b-en

Automatic Speech Recognition • Updated 30 days ago • 82

ibm-granite/granite-speech-3.3-8b

Automatic Speech Recognition • 9B • Updated 16 days ago • 11.4k • 94

liked a Space 13 days ago

Export to ONNX

🏎

Export models to ONNX format

liked a model 13 days ago

HuggingFaceTB/SmolLM3-3B

Text Generation • 3B • Updated about 17 hours ago • 425k • • 595

liked a model 18 days ago

istupakov/parakeet-tdt-0.6b-v2-onnx

Automatic Speech Recognition • Updated 13 days ago • 886 • 12

liked a model 20 days ago

onnx-community/parakeet-tdt-0.6b-v2-ONNX

Updated May 6 • 11

liked 4 models 26 days ago

liked 2 models about 1 month ago

tencent/Hunyuan3D-2.1

Image-to-3D • Updated Jun 24 • 61.1k • 571

inclusionAI/Ming-Lite-Omni

Any-to-Any • 19B • Updated 26 days ago • 217 • 160

liked a Space 2 months ago

NVIDIA Parakeet TDT 0.6B V2 Real Time Mic Transcription ASR STT

📊

Real-Time, Speak to Mic, NO MODEL DOWNLOAD NEEDED!!

liked 4 models 2 months ago

google/gemma-3n-E4B-it-litert-preview

Image-Text-to-Text • Updated May 26 • 1.4k

ByteDance-Seed/BAGEL-7B-MoT

Any-to-Any • 15B • Updated Jun 23 • 1.13k • 1.09k

mistralai/Devstral-Small-2505

24B • Updated 1 day ago • 101k • 837

TEN-framework/ten-vad

Updated 17 days ago • 47 • 102