eden-emu/opus
15
0
Fork 0
mirror of https://github.com/xiph/opus.git synced 2025-05-25 20:59:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
340 commits 284 branches 59 tags 26 MiB
Commit graph

17 commits

Author SHA1 Message Date
Jean-Marc Valin
fe7b54c0e8 Combine LAR+L1 regularization 2021-10-20 23:35:59 -04:00
Jean-Marc Valin
054d984bf3 Freeze LPCs when quantizing e2e models 2021-10-19 15:39:41 -04:00
Jean-Marc Valin
8cdc8081d8 Fix non-128 batch sizes 
Avoid hardcoding the batch size in the model
 2021-10-09 03:20:22 -04:00
Jean-Marc Valin
c5a17a0716 Hard quantization for training 
Also, using stateful GRU to randomize initialization
 2021-10-04 02:53:46 -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
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
6585843237 Removing the unused features 
Down to 20 features
 2021-07-29 03:20:59 -04:00
Jean-Marc Valin
c76756e18a Adding sparse training for GRU B inputs 2021-07-18 02:24:21 -04:00
Jean-Marc Valin
3e223e6015 Fixes Python inference for the binary probability tree 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
d61f7e00f8 Fix missing transpose in the sparity code 
CuDNNGRU and GRU don't use the same weight format
 2021-06-25 13:43:37 -04:00
Jean-Marc Valin
c7ba313a67 Adding extra constraint to avoid saturation for SSE/AVX2 
When implementing using SSSE3 or AVX2, our dot products can saturate
if two adjacent weights sum to more than 127.
 2021-06-18 17:39:35 -04:00
Jean-Marc Valin
237245f815 Support for multi-GPU training 
Not sure why CuDNNGRU doesn't get used by default, but we need
to explicitly use it to get things to run fast.
 2021-06-18 13:20:43 -04:00
Jean-Marc Valin
1657bae024 WIP: Adding a constraint 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