opus/dnn/torch
Jean-Marc Valin ddd5669e79
Pitch and fargan model updates
Removing one of the 2d conv layers for pitch estimation reduces
complexity without noticeable degradation. FARGAN model has more
adversarial training.
Also, no need for the double precision in the low-pass filter.
2023-10-28 23:33:47 -04:00
..
fargan C implementation of FARGAN 2023-10-14 16:42:33 -04:00
fwgan updated dump_model_weights.py 2023-08-01 21:58:08 +02:00
lpcnet added copyright headers 2023-09-05 22:31:19 +02:00
neural-pitch Pitch and fargan model updates 2023-10-28 23:33:47 -04:00
osce added 16kHz version of opus_compare in python 2023-10-20 14:24:27 +02:00
rdovae finalized quantization option in export_rdovae_weights.py 2023-10-20 14:14:31 +02:00
testsuite clean-up 2023-07-22 15:16:23 -07:00
weight-exchange C implementation of FARGAN 2023-10-14 16:42:33 -04:00