oruk

company

AI & ML interests

Speech foundation models for transcription, speaker diarization, vocal emotion, and delivery. We help AI understand what people say, how they say it, and what they mean—directly from the audio.

Recent Activity

NathanRoll published a model 8 days ago

oruk/oruk-loop-153M

NathanRoll updated a model 8 days ago

oruk/oruk-loop-153M

NathanRoll published a Space 16 days ago

oruk/qwen3-asr

View all activity

Articles

Connectome speech models: why the scrambled-wiring control matters

Sep 8

NathanRoll

published a model 8 days ago

oruk/oruk-loop-153M

Automatic Speech Recognition • 0.2B • Updated 8 days ago • 240 • 16

NathanRoll

updated a model 8 days ago

oruk/oruk-loop-153M

Automatic Speech Recognition • 0.2B • Updated 8 days ago • 240 • 16

NathanRoll

published a Space 16 days ago

Qwen3 ASR by Oruk

🎙

Try Qwen3-ASR on Oruk's dedicated NVIDIA L4

NathanRoll

updated a Space 16 days ago

Qwen3 ASR by Oruk

🎙

Try Qwen3-ASR on Oruk's dedicated NVIDIA L4

NathanRoll

authored a paper over 1 year ago

In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties

Paper • 2505.14887 • Published May 20, 2025 • 2

AI & ML interests

Recent Activity

Articles

Connectome speech models: why the scrambled-wiring control matters

Team members 5

oruk's activity

Qwen3 ASR by Oruk

Qwen3 ASR by Oruk