OCR Verification
Less-relevant results
lbj96347/nemotron-3.5-asr-ios: On-device, offline speech recognition for iPhone/iPad using NVIDIA's Nemotron-3.5-ASR Streaming 0.6B (multilingual) via CoreML.SwiftUI app with mic capture + audio file import, RNN-Tdecoding, and live benchmark metrics (latency, RTF, memory).
🔓Open Source Software Content type: CodeEnd-to-End Training for Discrete Token LLM based TTS System
🤖Grammar Induction Content type: AcademicVision Language Model Helps Private Information De-Identification in Vision Data
📄OCR Content type: AcademicBeyond WER: A Paired Acoustic Stress Test for Ambient Clinical Scribes
🔊Acoustic Forensics Content type: AcademicVTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning
📄OCR Content type: AcademicNo more posts from matmat's subscribed feeds.