ictnlp/StreamSpeech

Issues

• Low ASR-Bleu result with simul-s2st.sh

  #12 opened 2 months ago by arararz
  3

• Trained model can generate correct text but incorrect speech

  #13 opened a month ago by chentuochao
  12

• RuntimeError: Input tensor has to be 2D. - When using Web GUI demo with own audio(.mp3)

  #14 opened a month ago by Ztfrederickzheng
  1

• Can this architecture learn the timbre of source speech simultaneously?

  #15 opened 25 days ago by JianyuZhan
  0

• Is there English-Chinese or Chinese-English model?

  #9 opened 2 months ago by bk111
  5

• some folders and files are missing

  #7 opened 2 months ago by nattu22
  1

• pip install fairseq fails due to invalid metadata for PyYAML dependency in omegaconf

  #11 opened 2 months ago by Gan-Xing
  1

• Unable to run test script on local machine

  #1 opened 2 months ago by maxjkwang
  1

• How about the translation function? Is it Google translation or chatGPT like?

  #10 opened 2 months ago by bk111
  0

• which language do you support?will you support dialects,like hokkien

  #6 opened 3 months ago by jackylee1
  0

• Train on other language

  #3 opened 3 months ago by yiwei0730
  5

• Make sure Hugging Face download stats work, better discoverability

  #4 opened 3 months ago by NielsRogge
  0

• Error when loading speech_to_speech_ctc task

  #2 opened 3 months ago by arararz
  2