WhisperPipe: A Resource-Efficient Streaming Architecture for Real-Time Automatic Speech Recognition

Documenti analoghi

• Uni-ASR: Unified LLM-Based Architecture for Non-Streaming and Streaming Automatic Speech Recognition
  di: Xia, Yinfeng, et al.
  Pubblicazione: (2026)
• PI-Whisper: Designing an Adaptive and Incremental Automatic Speech Recognition System for Edge Devices
  di: Nassereldine, Amir, et al.
  Pubblicazione: (2024)
• ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition
  di: Lee, Junseok, et al.
  Pubblicazione: (2026)
• Probing Whisper for Dysarthric Speech in Detection and Assessment
  di: Yue, Zhengjun, et al.
  Pubblicazione: (2025)
• OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary
  di: Sudo, Yui, et al.
  Pubblicazione: (2025)