AI/wekws
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
wekws/examples/hi_xiaowen/s0
History
Cyan 7d142b9528
[examples] refactor FAR computation to support long audio test (#64) 
* add .gitattributes

* add long wav

* fix some bugs

* updated lint error

* back the hi_xiaowen/run.sh to the same

* remove the space

* better one

* remove 'num_keyword' parameter

* remove files

* flask8 examine

* override the score and compute_det file

* remove defaultdict

* remove import defaultdict
2022-03-24 14:35:07 +08:00
..
conf
[examples] use big model for ds_tcn (#47)
2021-12-15 11:12:24 +08:00
local
[examples] correct a spelling mistake (#24)
2021-12-05 21:24:06 +08:00
kws
[examples] support hi xiaowen dataset
2021-11-10 18:57:52 +08:00
path.sh
add mannul random seed so we can reproduce the experimental results
2021-11-19 16:23:03 +08:00
README.md
[doc] add quantize result (#46)
2021-12-15 11:07:59 +08:00
run.sh
[examples] refactor FAR computation to support long audio test (#64)
2022-03-24 14:35:07 +08:00
tools
[examples] support hi xiaowen dataset
2021-11-10 18:57:52 +08:00

README.md

FRRs with FAR fixed at once per hour:

model params(K) epoch hi_xiaowen nihao_wenwen
GRU 203 80(avg30) 0.088901 0.083827
TCN 134 80(avg30) 0.023494 0.029884
DS_TCN 21 80(avg30) 0.019641 0.018325
DS_TCN(big) 287 80(avg30) 0.012217 0.011653
DS_TCN(big, quantize) 287 80(avg30) 0.017292 0.022178
MDTC 156 80(avg10) 0.007142 0.005920
MDTC_Small 31 80(avg10) 0.005357 0.005920