opus/dnn/training_tf2
Jean-Marc Valin d45ab6fcb6 Move back to tanh for frame rate network
Swish has lower loss, but doesn't seem to improve quality
2022-09-24 03:22:57 -04:00
..
dataloader.py Properly align LPC with lookahead in data loader 2022-09-24 03:21:36 -04:00
diffembed.py Adds end-to-end LPC training 2021-08-02 19:28:27 -04:00
dump_lpcnet.py removed debug prints in dump_lpcnet.py 2022-09-07 09:10:19 +00:00
dump_plc.py WIP: PLC prediction 2022-01-31 23:21:55 -05:00
lossfuncs.py Add lpc weighting and model parameter handling 2022-09-06 23:14:39 -04:00
lpcnet.py Move back to tanh for frame rate network 2022-09-24 03:22:57 -04:00
lpcnet_plc.py Using Burg cepstrum for feature prediction 2022-02-04 22:04:23 -05:00
mdense.py Convert training code to Tensorflow 2 2020-08-19 14:27:07 -04:00
pade.py Faster activation functions for AVX 2021-06-29 04:05:48 -04:00
parameters.py Add lpc weighting and model parameter handling 2022-09-06 23:14:39 -04:00
plc_loader.py WIP non-causal PLC 2022-02-05 22:57:53 -05:00
test_lpcnet.py Add lpc weighting and model parameter handling 2022-09-06 23:14:39 -04:00
test_plc.py Code for testing PLC models 2022-01-31 18:49:19 -05:00
tf_funcs.py Dumping 16-bit linear training data 2021-10-20 23:35:59 -04:00
train_lpcnet.py Properly align LPC with lookahead in data loader 2022-09-24 03:21:36 -04:00
train_plc.py Biasing for overestimating the pitch correlation 2022-02-25 13:55:21 -05:00
ulaw.py Convert training code to Tensorflow 2 2020-08-19 14:27:07 -04:00