eden-emu/opus
15
0
Fork 0
mirror of https://github.com/xiph/opus.git synced 2025-06-02 16:47:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
268 commits 284 branches 59 tags 26 MiB
Commit graph

267 commits

Author SHA1 Message Date
Jean-Marc Valin
b9c230b346 Add NEON intrinsics 2021-01-16 02:11:22 -05:00
Jean-Marc Valin
b214e684c1 Neon WIP: Compiles but very slow 2021-01-16 02:11:21 -05:00
Jean-Marc Valin
8c3fe6f31d Cleaning up float version 2021-01-16 02:11:21 -05:00
Jean-Marc Valin
40b9fd0a75 Fix some quantization issues 2021-01-16 02:11:21 -05:00
Jean-Marc Valin
83657d0e43 Dot product AVX2 code for non-sparse multiply 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
06489b42dd oops, fix number of columns 2021-01-16 02:11:20 -05:00
Jean-Marc Valin
d87f974431 Vectorizing conversion 2021-01-16 02:11:20 -05:00
Jean-Marc Valin
6b582edbed WIP: remove scalar code from AVX2 code 2021-01-16 02:11:20 -05:00
Jean-Marc Valin
be392e3857 WIP: Got some AVX2 code working 2021-01-16 02:11:20 -05:00
Jean-Marc Valin
2b4652f9f6 WIP: 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
1657bae024 WIP: Adding a constraint 2021-01-16 02:11:19 -05:00
Jean-Marc Valin
c045702e51 Add non-dot-product AVX code 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
8e405b44e0 Improve accuracy of AVX sigmoid 
Reciprocal approximation could cause the sigmoid output to be
greater than 1.0.
 2021-01-16 01:51:39 -05:00
Jean-Marc Valin
56d9f13efd Fix quantization bug where pitch can get too low 
Would cause unused pitch embedding vectors to be used
 2021-01-16 01:51:39 -05:00
Jean-Marc Valin
f0df3e82ec Update to model trained with Tensorflow 2 
No change otherwise
 2020-12-19 00:21:03 -05:00
Jean-Marc Valin
078d90cbdf Merge Tensorflow 2 code 2020-12-19 00:20:23 -05:00
Jean-Marc Valin
90fec91b12 Convert training code to Tensorflow 2 2020-08-19 14:27:07 -04:00
Marcus Asteborg
171b1ba0ce Initialize excitation memory value to unquantized 0 2020-08-17 13:39:24 -04:00
Jean-Marc Valin
88a7878fdb Fix pitch-related bugs 
preventing the pitch from going above 255
 2020-08-15 02:18:59 -04:00
Marcus Asteborg
9a7f3e4a3d Open files in binary mode to enable dump_data to work properly on Windows 2020-08-02 20:45:07 -04:00
Marcus Asteborg
eeb7615bd7 Add conda env file with working tensorflow and keras version for LPCNet 2020-07-31 17:25:29 -04:00
Jean-Marc Valin
14fb264a0f Fix sampling bug for 16-bit rand() 
According to David Rowe, when rand() returns RAND_MAX (which is likely
for 16-bit output), we end up producing a click.
 2020-06-20 23:47:04 -04:00
Jean-Marc Valin
8f887b62f0 Download the model 2019-04-14 03:20:17 -04:00
Jean-Marc Valin
60790784a4 training 2019-04-11 11:07:33 -04:00
Jean-Marc Valin
9b8d72ea87 more noise 2019-04-10 21:30:54 -04:00
Jean-Marc Valin
a3300d7b24 Fix bias in LPC spectrum 2019-04-10 21:13:44 -04:00
Jean-Marc Valin
fd1fc693aa adaptation flag to avoid training the sample rate network 2019-04-01 15:22:00 -04:00
Jean-Marc Valin
2a7a9fa085 Minor README.md tweak again 2019-03-28 11:33:38 -04:00
Jean-Marc Valin
49fc5f741a nothing to see here 2019-03-28 11:29:34 -04:00
Jean-Marc Valin
63a67d4654 Add README.md to tarball 2019-03-28 11:23:52 -04:00
Jean-Marc Valin
ee63653fd4 Update README.md with new paper 2019-03-28 11:19:05 -04:00
Jean-Marc Valin
1f45081548 Implement -feature option 2019-03-28 10:54:33 -04:00
Jean-Marc Valin
77d02dbd2f Using macros for sizes in the demo 2019-03-27 14:12:52 -04:00
Jean-Marc Valin
9f78e58392 Make param ordering consistent for lpcnet_synthesize() 2019-03-27 14:06:46 -04:00
Jean-Marc Valin
623ac9545c Adding API doc 2019-03-24 12:10:36 -04:00
Jean-Marc Valin
219fbff4e6 Making it easier to adapt (or not) a model 2019-03-24 03:48:26 -04:00
Jean-Marc Valin
edee9cd8f2 README.md update 2019-03-22 14:37:01 -04:00
Jean-Marc Valin
a8fb25f11c Remove NaN checks 2019-03-20 13:36:42 -04:00
Jean-Marc Valin
a09815925a Neon: Make gcc actually generate VMLA instructions for sparse mul 
Otherwise it was splitting the mla into a mul and an add
 2019-03-20 12:58:39 -04:00
Jean-Marc Valin
2bc20e65c7 Remove hack to match Python code 2019-03-20 03:21:03 -04:00
Jean-Marc Valin
492ef9b362 Neon implementation of the activation functions 2019-03-20 03:03:44 -04:00
Jean-Marc Valin
3d2b26b7ca Add dump_data 2019-03-19 14:42:23 -04:00
Jean-Marc Valin
df8a0ac3fb build lpcnet_demo in root dir 2019-03-19 14:22:39 -04:00