Commit Graph

22 Commits

Author SHA1 Message Date
68431b848e torchaudio testing 2020-12-17 08:02:29 +01:00
95dcf22f3d Audio Dataset 2020-12-01 16:37:16 +01:00
be097a111a New Model, Many Changes 2020-11-21 09:28:26 +01:00
7bac9e984b Transformer Implementation 2020-10-29 16:40:43 +01:00
b57eabb371 InterSpeech Camera Ready Reporting 2020-08-06 08:12:08 +02:00
d58bcbf14b requirements.txt updated @torch1.4
speed augmentation updated
paramters updated
2020-05-21 14:12:54 +02:00
b529d130df module_mixins.py updated with tensor return 2020-05-21 12:33:36 +02:00
e021e2209b fingerprinted now should work correctly 2020-05-20 13:29:17 +02:00
c083207235 fingerprinted now should work correctly 2020-05-19 08:33:05 +02:00
511b8064cd inference restored 2020-05-16 08:18:27 +02:00
192810bc58 unlinken of already processed training files (seed dependent audio augmentation) 2020-05-15 19:47:57 +02:00
9ae9143544 dataset stretch now optional 2020-05-15 11:06:23 +02:00
09f9dd9131 dataset stretch now optional 2020-05-15 09:43:30 +02:00
e7d1a4895a requirements 2020-05-14 23:08:36 +02:00
407df15bbf requirements 2020-05-13 22:54:19 +02:00
dce799a52b Test Dataset Multiplication by Timeshift 2020-05-12 16:18:02 +02:00
28bfcfdce3 ResidualModule and New Parameters, Speed Manipulation 2020-05-12 12:37:26 +02:00
3fbc98dfa3 LinearModule 2020-05-09 21:56:58 +02:00
5e6b0e598f Parameter Adjustmens and Ensemble Model Implementation 2020-05-08 16:30:55 +02:00
451f78f820 BandwiseBinaryClassifier is work in progress; TODO: Shape Piping. 2020-05-04 18:45:13 +02:00
e4f6506a4b Model Training 2020-05-03 18:00:51 +02:00
76c0e6aa05 Config Anpassungen 2020-04-15 17:15:51 +02:00