9 Commits

Author	SHA1	Message	Date
Edresson Casanova	e78e3cd81e	Merge branch 'dev' into dev	2021-06-18 14:10:03 -03:00
Edresson	14b209c7e9	Create a batch for more fast inference on LSTM Speaker Encoder	2021-06-05 03:12:17 -03:00
Eren Gölge	bec85ac58d	make style	2021-05-31 16:37:15 +02:00
Edresson	208bb0f0ee	add batched speaker encoder inference	2021-05-27 20:01:00 -03:00
Edresson	bc5307caa0	add unit tests for SoftmaxAngleProtoLoss and ResnetSpeakerEncoder and bugfix	2021-05-26 20:35:58 -03:00
Edresson	d570c2d790	pylint fix and data loader bug fix	2021-05-26 01:11:37 -03:00
Edresson	856ea19758	bug fix in dataloader and update inference	2021-05-18 03:43:16 -03:00
Edresson	3433c2f348	add compute embedding for the new speaker encoder	2021-05-12 03:06:46 -03:00
Edresson	3fcc748b2e	implement the Speaker Encoder H/ASP	2021-05-11 16:27:05 -03:00