PredGen: Accelerated Inference of Large Language Models through Input-Time Speculation for Real-Time Speech Interaction

Documenti analoghi

• CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models
  di: Li, Xiang, et al.
  Pubblicazione: (2024)
• SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models
  di: Zhang, Xin, et al.
  Pubblicazione: (2023)
• Speech Recognition Rescoring with Large Speech-Text Foundation Models
  di: Shivakumar, Prashanth Gurunath, et al.
  Pubblicazione: (2024)
• StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling
  di: Wang, Hui, et al.
  Pubblicazione: (2025)
• Phonikud: Hebrew Grapheme-to-Phoneme Conversion for Real-Time Text-to-Speech
  di: Kolani, Yakov, et al.
  Pubblicazione: (2025)