eden-emu/opus
15
0
Fork 0
mirror of https://github.com/xiph/opus.git synced 2025-05-25 12:49:12 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
418 commits 284 branches 59 tags 26 MiB
Commit graph

25 commits

Author SHA1 Message Date
janpbuethe
f3c738d45f removed debug prints in dump_lpcnet.py 2022-09-07 09:10:19 +00:00
janpbuethe
920300c546 Add lpc weighting and model parameter handling 
Model now stores LPC gamma, look-ahead, and end-to-end.
Parameters aren't quite reliable yet, YMMV
 2022-09-06 23:14:39 -04:00
Jean-Marc Valin
144b7311bc Dumping 16-bit linear training data 2021-10-20 23:35:59 -04:00
Jean-Marc Valin
a3ef596822 auto-detect end-to-end models 2021-10-20 23:35:59 -04:00
Jean-Marc Valin
b24e53fdfa Adding option to change frame rate network size 2021-10-20 23:35:59 -04:00
Jean-Marc Valin
e4b4613d05 Fix signed-unsigned biases 2021-09-02 02:34:08 -04:00
Jean-Marc Valin
51ef273e06 Using 8-bit recurrent weights for GRU B 2021-09-02 02:33:55 -04:00
Jean-Marc Valin
adc50cab5b dump_lpcnet.py should work the same for end2end 2021-08-04 14:56:02 -04:00
Jean-Marc Valin
ab9a09266f Sharing conditioning network with LPC 2021-08-02 19:30:22 -04:00
Krishna Subramani
c1532559a2 Adds end-to-end LPC training 
Making LPC computation and prediction differentiable
 2021-08-02 19:28:27 -04:00
Jean-Marc Valin
b90729b83b dump_lpcnet.py now checks the size of GRU B 2021-07-20 17:01:54 -04:00
Jean-Marc Valin
8bdbbfa18d Support for sparse GRU B input matrices 
Only on the C side, no sparse GRU B training yet
 2021-07-16 03:07:26 -04:00
Jean-Marc Valin
c74330e850 Pre-compute GRU B conditioning 
Adapted from PR: https://github.com/mozilla/LPCNet/pull/134
by zhuxiaoxu <zhuxiaoxu@ainirobot.com>
but had to be reworked due to previous weight quantization changes.
 2021-07-15 16:06:56 -04:00
Jean-Marc Valin
5a51e2eed1 Adding command-line options to training script 2021-07-13 03:09:04 -04:00
Jean-Marc Valin
54abdb6f5d Sparse matrix indexing optimization 
The 4* is now stored in the table to avoid computing it in the loop
 2021-07-10 01:59:49 -04:00
Jean-Marc Valin
d332100808 Representing output pdf as binary probability tree 
Saves on the MDense/softmax computation since we only need to compute
8 values instead of 256.
 2021-07-10 01:59:49 -04:00
Jean-Marc Valin
40b9fd0a75 Fix some quantization issues 2021-01-16 02:11:21 -05:00
Jean-Marc Valin
1707b960de cleanup, add signed-unsigned biases 2021-01-16 02:11:21 -05:00
Jean-Marc Valin
40b309d92b WIP: 8-bit SIMD for GRU B 2021-01-16 02:11:21 -05:00
Jean-Marc Valin
e695355ba5 some cleanup 2021-01-16 02:11:20 -05:00
Jean-Marc Valin
bce779886d WIP: signed*unsigned arithmetic 2021-01-16 02:11:20 -05:00
Jean-Marc Valin
11736ca9e3 WIP: 8-bit mul 2021-01-16 02:11:19 -05:00
Jean-Marc Valin
73a05f55c7 wip 8x4 2021-01-16 02:11:19 -05:00
Jean-Marc Valin
cc28518699 wip 8x4 sparseness 2021-01-16 02:11:19 -05:00
Jean-Marc Valin
90fec91b12 Convert training code to Tensorflow 2 2020-08-19 14:27:07 -04:00