xiongxinlei
|
347af638e2
|
changet vector train.py local_rank to rank, test=doc
|
3 years ago |
Honei
|
119143d0f1
|
Merge pull request #1731 from qingen/cluster
[vec] add GE2E to support unlabeled data training
|
3 years ago |
Hui Zhang
|
91e24b0480
|
format code
|
3 years ago |
|
Hui Zhang
|
c7d9b11529
|
format
|
3 years ago |
qingen
|
e98845d778
|
[vec][loss] add GE2E to support unlabeled data training, test=doc fix #1730
|
3 years ago |
|
qingen
|
0186f522af
|
Merge pull request #1725 from qingen/database-search
[vec] add GRL to domain adaptation
|
3 years ago |
|
qingen
|
7e8f9f5336
|
[vec][layer] add GRL to domain adaptation, test=doc fix #1724
|
3 years ago |
|
qingen
|
6a7245657f
|
[vec][loss] add FocalLoss to deal with class imbalances, test=doc fix #1721
|
3 years ago |
|
qingen
|
00febff734
|
[vec][loss] update docstring, test=doc fix #1717
|
3 years ago |
|
qingen
|
166757703f
|
[vec][loss] add NCE Loss from RNNLM, test=doc fix #1717
|
3 years ago |
|
qingen
|
159d8fd628
|
Merge branch 'develop' into cluster
|
3 years ago |
|
qingen
|
deb3ba070b
|
[vec] update mata info, test=doc
|
3 years ago |
|
Hui Zhang
|
0cde9f87ab
|
Merge pull request #1710 from Honei/deepspeech_server
[asr][websocket]fix the ws send bug, cache buffer, text=doc
|
3 years ago |
|
xiongxinlei
|
efc269b75f
|
remove unuseful code, test=doc
|
3 years ago |
|
Hui Zhang
|
c7b987c55d
|
format
|
3 years ago |
|
Hui Zhang
|
ec469179bf
|
Merge pull request #1696 from qingen/database-search
[vec][server] vpr demo support
|
3 years ago |
|
qingen
|
240520c0ca
|
Merge branch 'PaddlePaddle:develop' into cluster
|
3 years ago |
|
qingen
|
d3f8715b0a
|
Merge branch 'database-search' of github.com:qingen/PaddleSpeech into database-search
|
3 years ago |
|
qingen
|
89a0ec9018
|
[vec][server] vpr demo support, test=doc fix #1695
|
3 years ago |
|
xiongxinlei
|
d1935d8552
|
add vector necessary note, test=doc
|
3 years ago |
|
qingen
|
0d8e2deb61
|
Merge branch 'PaddlePaddle:develop' into cluster
|
3 years ago |
|
Honei
|
48e0177767
|
Merge pull request #1630 from Honei/vox12
[vec]voxceleb convert dataset format to paddlespeech
|
3 years ago |
|
qingen
|
fc72295334
|
Merge pull request #1651 from ccrrong/ami
[vec] add speaker diarization pipeline
|
3 years ago |
|
xiongxinlei
|
4af007c3fc
|
fix vector ips log bug, test=doc
|
3 years ago |
|
qingen
|
8d9bd9a93a
|
[vec][score] update Copyright, test=doc fix #1667
|
3 years ago |
|
xiongxinlei
|
567286add3
|
wrap the embedding mean and std norm, test=doc
|
3 years ago |
|
qingen
|
44c6623448
|
[vec][score] update plda model, test=doc fix #1667
|
3 years ago |
ccrrong
|
bc53f726fe
|
convert dataset format to paddlespeech, test=doc
|
3 years ago |
|
qingen
|
6446f72cab
|
[vec][score] add plda model, test=doc fix #1667
|
3 years ago |
|
qingen
|
84576d6956
|
[vec][score] add plda model, test=doc fix #1667
|
3 years ago |
|
xiongxinlei
|
a8244dc5b0
|
update the note, test=doc
|
3 years ago |
|
xiongxinlei
|
9b5f7f71ac
|
add part ecapa-tdnn note, test=doc
|
3 years ago |
|
ccrrong
|
378fe5909f
|
add ami diarization pipeline, test=doc
|
3 years ago |
|
xiongxinlei
|
ebfe3e6b13
|
test.py update the CSVDataset, test=doc
|
3 years ago |
|
xiongxinlei
|
acebfad7b7
|
change the vector csv.spk_id to csv.label, test=doc
|
3 years ago |
|
xiongxinlei
|
57c11dcab0
|
add some annotations, test=doc
|
3 years ago |
|
xiongxinlei
|
30b5b3cb9e
|
add vector csv dataset format, test=doc
|
3 years ago |
|
xiongxinlei
|
5b05300e53
|
train process add new voxceleb and rirs dataset, test=doc
|
3 years ago |
|
xiongxinlei
|
965f486dd5
|
add voxceleb and rirs noise dataset
|
3 years ago |
|
Hui Zhang
|
84d712d493
|
format code, test=doc
|
3 years ago |
|
xiongxinlei
|
ed7113f320
|
change the vector output to numpy.array
|
3 years ago |
|
xiongxinlei
|
5ae57206f3
|
add paddlespeech vector modules __init__.py
|
3 years ago |
|
xiongxinlei
|
0f78d25f76
|
add vector cli batch and pipeline test demo, test=doc
|
3 years ago |
|
Honei
|
305bacdcf2
|
Merge branch 'develop' into vox12
|
3 years ago |
|
xiongxinlei
|
62cbce6915
|
add vectorwrapper to extract audio embedding
|
3 years ago |
|
Hui Zhang
|
4051e7b762
|
fix compliance test bug, and format
|
3 years ago |
|
xiongxinlei
|
d85d1deef5
|
exec pre-commit in paddlespeech vector, test=doc
|
3 years ago |
|
xiongxinlei
|
9874fb7d75
|
add some comments in code
|
3 years ago |
|
xiongxinlei
|
d28ccfa96b
|
add vector cli component, test=doc
|
3 years ago |
|
qingen
|
d16ce21d47
|
[wip][vec] update cluster of diarization, test=doc #1304
|
3 years ago |
