“2024-07-29”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
第62行: 第62行:
 
** the base model for the 1st iteration is finished on hawk02.
 
** the base model for the 1st iteration is finished on hawk02.
 
** the base model for the 2nd iteration need to migrate to dragon03(in progress)
 
** the base model for the 2nd iteration need to migrate to dragon03(in progress)
 +
** Beginner's Guide for pretraining Hubert with fairseq:[https://z1et6d3xtb.feishu.cn/docx/TGBPdRS8HoTHWdxGn7scbTqPnxd]
 
||
 
||
 
*
 
*

2024年7月29日 (一) 10:34的版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • AIGraph slides done
  • Check for thermal face recognition paper
  • Quick check for Guyue's paper
Lantian Li
  • GPU status [1]
  • AI graph
    • Slides checking (50/50)
    • High school handbook (12/40)
  • High school handbook (20/40)
Ying Shi
Zhenghai You
  • Complete the Reproduce of IRA[2]
  • Design a new TSE structure using U-NET and G&L Transformer (idea form sepreformer)
  • Write the work content for Huawei's first phase as ICCIP2024
Junming Yuan
  • Reimplementation of the Hubert baseline:
    • fix some bugs
    • the base model for the 1st iteration is finished on hawk02.
    • the base model for the 2nd iteration need to migrate to dragon03(in progress)
    • Beginner's Guide for pretraining Hubert with fairseq:[3]
Chen Chen
Xiaolou Li
Zehua Liu
  • LRS3-30h: VSP-LLM - cluster(WER : 28.11%) < VSP-LLM (WER : 29.1%)
  • LRS3-30h: VSP-LLM - cluster + adaptive_mask(WER : 27.75%) < VSP-LLM (WER : 29.1%)
  • LRS3-30h: In-Context-learning (still training)
Pengqi Li
Wan Lin
  • Neural Scoring
    • First draft of paper finished [4]
    • Supplement experimental results
Tianhao Wang
Zhenyu Zhou
Junhui Chen
  • Neural Scoring:
    • Paper Writing (1st Ver. finished with LW)
    • Supplement the experiments
Jiaying Wang
Yu Zhang
Wenqiang Du
Yang Wei
Lily
  • Prepare for high shcool summer trip class(last Sunday)
  • Accident & get sick
Turi
Yue Gu
  • complete and revise the DPR paper
Qi Qu
  • AED:
    • AudioSet data prepared.
    • Positive samples of "cries" collected and to be annotated.
  • KWS:
    • B6-based service optimized with memory consumption considerably reduced (~600MB v.s. formerly ~2GB).