• English

      • FireRedPunc Series

      Notes

      • Model background: FireRedPunc is an independent punctuation prediction module within the FireRedASR2S integrated speech system. Built on the BERT architecture, it is designed for ASR post‑processing scenarios and supports Chinese‑English bilingual punctuation restoration.
      • Features: The model achieves SOTA performance in the industry, with an average F1 score of 78.90%. It performs excellently across multiple domains for both Chinese and English datasets, adapting to various offline and real‑time transcription tasks.
      • Open source repository: https://github.com/FireRedTeam/FireRedASR2S

      Model List

      Model NameDescriptionDownload Link
      FireRedPunc-zh-en-onnxGeneral Chinese‑English punctuation prediction model, excellent overall accuracy, SOTA‑level performancemodelscope