mirrors/DeepSpeech
2
0
Fork 0
mirror of https://github.com/mozilla/DeepSpeech.git synced 2025-10-26 11:19:39 +00:00
Code Issues Packages Projects Releases Wiki Activity
2,035 Commits 63 Branches 109 Tags 17 GiB
998daa5bca
Commit Graph

384 Commits

Author SHA1 Message Date
Reuben Morais
11ad23cc1f Remove sample rate parameter usage from .NET binding 2019-10-10 15:44:11 +02:00
Reuben Morais
1007d93da2 Remove sample rate parameter usage from Java binding 2019-10-10 15:44:11 +02:00
Reuben Morais
385279bc20 Remove sample rate parameter usage from JavaScript binding 2019-10-10 15:44:11 +02:00
Reuben Morais
97bab38a7e Remove sample rate parameter usage from Python binding 2019-10-10 15:44:11 +02:00
Reuben Morais
abb11f040d Remove sample rate parameter usage from client.cc 2019-10-10 15:44:11 +02:00
Reuben Morais
2f4116695f Remove unused sample rate param from API 2019-10-10 14:34:00 +02:00
Alexandre Lissy
eab8bf5dec Add ElectronJS v6.0 
Fixes #2408
 2019-10-10 13:48:37 +02:00
Reuben Morais
ce785534fe Set sample_rate attribute of ds_audio_buffer in NO_SOX client 2019-10-09 09:38:38 +02:00
Reuben Morais
fb611efd00
Merge pull request #2400 from carlfm01/remove-intptr 
Replace structs with IntPtr .NET
 2019-10-07 08:44:32 +02:00
Carlos Fonseca
acabb26378 Move structs to IntPtr 2019-10-05 03:58:40 +00:00
Alexandre Lissy
9ce8c24165 Move from Markdown to reStructuredText 2019-10-04 12:07:32 +02:00
Reuben Morais
67e3eefb95 Remove incorrect docs on Scorer 
X-DeepSpeech: NOBUILD
 2019-09-30 10:54:59 +02:00
Reuben Morais
ba56407376
Merge pull request #2383 from mozilla/scorer-cleanup 
Don't explicitly score the BOS token, and avoid copies when scoring sentences
 2019-09-27 11:06:24 +02:00
Reuben Morais
a323973521 Address review comments 2019-09-27 11:02:22 +02:00
lissyx
f51f9d9704
Merge pull request #2386 from artie-inc/typo 
Fixing typo s/StreamingContext/StreamingState/
 2019-09-27 10:46:56 +02:00
Alexandre Lissy
86b44a7cb7 Load KenLM with LAZY 
Fixes #2384
 2019-09-26 21:08:27 +02:00
JRMeyer
fed5039cc7 Fixing typo s/StreamingContext/StreamingState/ 
X-DeepSpeech: NOBUILD
 2019-09-26 12:05:37 -07:00
Reuben Morais
6dba6d4a95 Don't explicitly score the BOS token, and avoid copies when scoring sentences 2019-09-26 14:08:32 +02:00
Alexandre Lissy
2b7ab99478 Fix pylint 2019-09-24 18:22:45 +02:00
Alexandre Lissy
bf7cc1df54 Sphinx doc 2019-09-24 18:22:45 +02:00
Alexandre Lissy
458692692e Fix header preprocessor alignment 2019-09-24 10:55:26 +02:00
Reuben Morais
d0e11c73cd Address review comments 2019-09-18 15:09:11 +02:00
Reuben Morais
0ac498bc50 Rename metadata probability field to confidence 2019-09-11 11:09:44 +02:00
Reuben Morais
7abbe077d8 Add a #warning to deepspeech_compat.h 
X-DeepSpeech: NOBUILD
 2019-09-09 16:10:19 +02:00
Reuben Morais
b95ebea9ba Fix linter error 2019-09-09 13:47:26 +02:00
Reuben Morais
f4e57902ba Update Java bindings 2019-09-09 12:03:14 +02:00
Reuben Morais
a8c53d2154 Update .NET bindings and client 2019-09-09 12:03:14 +02:00
Reuben Morais
bc6741cd41 Update JS bindings and client 2019-09-09 12:03:14 +02:00
Reuben Morais
249fdadc32 Update Python bindings and client 2019-09-09 12:03:14 +02:00
Reuben Morais
a815426918 Update client.cc 2019-09-09 11:38:28 +02:00
Reuben Morais
61b9b0e84d Add convenience header for backwards compatibility 2019-09-09 11:36:17 +02:00
Reuben Morais
c402b971d6 Remove unused params and make function names more consistent 2019-09-09 11:35:44 +02:00
Reuben Morais
289e346a66
Merge pull request #2324 from bjornbytes/c-compat 
Make deepspeech.h compilable as C
 2019-08-28 10:38:15 +02:00
bjorn
f7fc74c078 rm trailing whitespace; 2019-08-27 15:38:39 -07:00
bjorn
73b2bbe8da Use struct typedefs for C compatibility; 2019-08-27 15:34:03 -07:00
bjorn
5d24f19115 Only use extern C when compiling as C++; 2019-08-27 15:25:30 -07:00
Reuben Morais
89f63dcd69 Make Scorer init fallible and check it in callers 2019-08-26 13:59:15 +02:00
Reuben Morais
47b9b71776 Automatically format BUILD file with buildifier 2019-08-26 12:01:26 +02:00
Reuben Morais
c730102867 Avoid rebuilding decoder sources for every binary target 2019-08-26 12:01:26 +02:00
Reuben Morais
1b18494e63 Address review comments 2019-08-23 12:19:32 +02:00
Reuben Morais
b2ef9cca83 Make Alphabet init fallible and check it in model creation 2019-08-23 12:19:32 +02:00
Reuben Morais
4dabd248bc Make Alphabet copyable and default-constructable and avoid pointers 2019-08-23 12:19:32 +02:00
Reuben Morais
4d882a8aec Simplify decoder impl by making it object oriented, avoid pointers where possible 2019-08-23 12:19:32 +02:00
Alexandre Lissy
dfe8be30b4 Move to ARMbian Buster 
Fixes #2310
 2019-08-21 22:58:10 +02:00
Alexandre Lissy
8534c0f93a Statically link libsox 2019-08-21 21:35:08 +02:00
lissyx
50e2a99316
Merge pull request #2308 from lissyx/remove-prealloc 
Remove ununsed prealloc frames
 2019-08-21 14:53:47 +02:00
lissyx
0e47048f9c
Merge pull request #2307 from lissyx/rpi-buster 
Build for Raspbian Buster
 2019-08-20 21:49:51 +02:00
Alexandre Lissy
81b3b159c4 Remove ununsed prealloc frames 
Fixes #2298
 2019-08-20 18:38:46 +02:00
Alexandre Lissy
e06fce51ac Move Raspbian support to Buster 
Fixes #2272
 2019-08-20 16:37:26 +02:00
Reuben Morais
e3bf5d3cc6 Only update time step of leaf prefixes 
The intention of this check is to improve the accuracy of the timings by recording the time step where the character saw its highest probability rather than the first time step where it was seen. The problem happens when updating the time step of a prefix that already has children. In that case, if any of the children have a time step that is earlier than `new_timestep`, it'll break the linearity of the timings. My fix is to simply check that the prefix we're updating is a leaf.

For example, say during decoding we have the following beams (format is `(char | time)`, tree node id below, nodes with same id are the same object):

```
1. (-1 | 0 ) -> ('s' | 10) -> ('h' | 13) -> ('e' | 14)
        A                B                  C                D

2. (-1 | 0 ) -> ('s' | 10) -> ('h' | 14)
        A                B                  E
```

And the prefix list is [B, C, D, E]. Currently, if we process character 'h' in time step 15 with a probability higher than both C and E, we update both nodes to have time step 15, which breaks linearity in beam 1. With my fix, we only update node E, which is a leaf. In my tests this does fix the problem, but since we don't have any known good quality data to verify against, it's hard to know if it has other side effects.
 2019-08-20 12:03:59 +02:00