“2024-07-15”版本间的差异

2024年7月15日 (一) 10:13的版本

People	This Week	Next Week
Dong Wang
Lantian Li
Ying Shi
Zhenghai You
Junming Yuan	Start Hubert pretraining experiment using fairseq fix some bug and start pretraining on our Libri-keyword corpus. Beginner's Guide for training Hubert with fairseq:[1]
Chen Chen
Xiaolou Li
Zehua Liu
Pengqi Li
Wan Lin
Tianhao Wang
Zhenyu Zhou
Junhui Chen
Jiaying Wang	wsj dataset： 2mix baseline(done) 2mix + cohort：poor performance, need to test the EER of wsj dataset librimix dataset: 3mix baseline(done) 3mix + cohort: overfit and loss>0 --> plan to see transformer attention map	use condition chain frame on cohort
Yu Zhang
Wenqiang Du	Continuously upgrade the model according to the plan primary school handbook (7/46)
Yang Wei
Lily	Thesis Daily Work at AIRadiance Live Broadcast Prepare Lenovo's Lecture
Turi
Yue Gu	fix bugs read several recently published papers, then complete draft of the abstract and introduction. (6.5/9)
Qi Qu

@@ 第150行： / 第150行： @@
 |Jiaying Wang
 ||
-*
+* wsj dataset：
+** 2mix baseline(done)
+** 2mix + cohort：poor performance, need to test the EER of wsj dataset
+* librimix dataset:
+** 3mix baseline(done)
+** 3mix + cohort: overfit and loss>0 --> plan to see transformer attention map
 ||
-*
+* use condition chain frame on cohort
 ||
 *