This project is roughly divided into three parts: OCR Recognition, which uses existing tools to extract captions from videos to text; Speech Recognition, which uses deep learning tools(BaiduSpeech) to translate audios to text; NLP tasks, including segmentation, part-of-speech tagging, named entity recognition, dependency parsing, semantic role labeling and so on. The most important part is Speech Recognition. Since there are few guidences about how to use DeepSpeech model to train Chinese, I will pay more attention to this part and train a model as soon as possible.



Xu Tony


  • Peter Uhrig
  • Mark Turner
  • Francis Steen
  • Weixin Li
  • Huijian Lv
  • littleowen
  • Jacek Wo┼║ny