Reuben Morais
|
cc62aa2eb8
|
Merge pull request #3279 from godefv/decoder_timesteps
The CTC decoder timesteps now corresponds to the timesteps of the most probable CTC path, instead of the earliest timesteps of all possible paths.
|
2020-09-17 20:31:05 +02:00 |
|
godeffroy
|
ec55597412
|
PR #3279 - use a tree structure to store timesteps
|
2020-09-07 13:37:27 +02:00 |
|
Reuben Morais
|
ae0cf8db6a
|
Revert "Merge branch 'rename-real'"
This reverts commit ae9fdb183e, reversing
changes made to 2eb75b6206.
|
2020-08-26 11:46:09 +02:00 |
|
godeffroy
|
04a36fbf68
|
The CTC decoder timesteps now corresponds to the timesteps of the most
probable CTC path, instead of the earliest timesteps of all possible paths.
|
2020-08-25 12:08:14 +02:00 |
|
Reuben Morais
|
fa21911048
|
Rename packages, modules, headers, shared libraries to Mozilla Voice STT
|
2020-08-03 18:22:32 +02:00 |
|
Reuben Morais
|
6141740f89
|
Remove unused Scorer method
This method was made unused by https://github.com/mozilla/DeepSpeech/pull/3021
after reports such as https://github.com/mozilla/DeepSpeech/issues/3004
of confusion interpreting the confidence values.
|
2020-07-30 11:00:00 +02:00 |
|
Reuben Morais
|
a84abf813c
|
Deduplicate Alphabet implementations, use C++ one everywhere
|
2020-06-30 09:52:45 +02:00 |
|
Reuben Morais
|
f82c77392d
|
Rewrite data/lm/generate_package.py into native_client/generate_scorer_package.cpp
|
2020-06-30 09:52:44 +02:00 |
|
Alexandre Lissy
|
6c2cbbd725
|
Fix #3053: Check output stream when producing scorer
|
2020-06-16 23:28:01 +02:00 |
|
Reuben Morais
|
7ed900e333
|
Add better error information in Scorer initialization
|
2020-05-18 11:19:19 +02:00 |
|
Reuben Morais
|
5fa1839a7f
|
Use Alphabet to compute string values in get_prev_*
|
2020-04-13 10:23:23 +02:00 |
|
Reuben Morais
|
8dedda7759
|
Address review comments
|
2020-02-11 19:44:36 +01:00 |
|
Reuben Morais
|
efbed73d5c
|
Improve error handling around Scorer loading
|
2020-02-11 19:44:36 +01:00 |
|
Reuben Morais
|
ab08f5ee5a
|
Change decoder API
|
2020-02-11 19:44:26 +01:00 |
|
Reuben Morais
|
16d5632d6f
|
Write default values for alpha and beta into trie header
|
2020-02-11 19:44:26 +01:00 |
|
Reuben Morais
|
b33d90b7bd
|
Load combined format from Scorer
|
2020-02-11 19:44:26 +01:00 |
|
Reuben Morais
|
214b50f490
|
Add generate_package tool to create combined scorer package
|
2020-02-11 19:44:26 +01:00 |
|
Reuben Morais
|
be2229ef29
|
Refactor Scorer so model/trie package can be created by an external tool
|
2020-02-11 19:44:26 +01:00 |
|
Reuben Morais
|
7c0354483e
|
Stop including vocabulary data in LM.binary.
|
2020-02-11 19:44:19 +01:00 |
|
Reuben Morais
|
0e6952c3a8
|
Avoid reconstructing strings twice on decode
|
2019-11-11 12:53:05 +01:00 |
|
Reuben Morais
|
c1b1a59423
|
Score prefix as soon as a grapheme is formed rather than 1 byte later
|
2019-11-11 12:52:48 +01:00 |
|
Reuben Morais
|
f4cdd988df
|
UTF-8 target
|
2019-11-11 11:36:16 +01:00 |
|
Reuben Morais
|
c8802a38e7
|
Don't add special tokens to vocabulary
|
2019-10-14 21:03:14 +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 |
|
Alexandre Lissy
|
86b44a7cb7
|
Load KenLM with LAZY
Fixes #2384
|
2019-09-26 21:08:27 +02:00 |
|
Reuben Morais
|
6dba6d4a95
|
Don't explicitly score the BOS token, and avoid copies when scoring sentences
|
2019-09-26 14:08:32 +02:00 |
|
Reuben Morais
|
89f63dcd69
|
Make Scorer init fallible and check it in callers
|
2019-08-26 13:59:15 +02:00 |
|
Reuben Morais
|
1b18494e63
|
Address review comments
|
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 |
|
Francis Tyers
|
6e53fd8fe0
|
typo
X-DeepSpeech: NOBUILD
|
2019-06-22 22:18:25 +01:00 |
|
Reuben Morais
|
31afc6811f
|
Switch to ConstFst from VectorFst and mmap trie file when reading
|
2019-06-21 22:21:19 -03:00 |
|
Reuben Morais
|
9e8c208be2
|
Don't save/load trie for character based LMs
|
2019-01-07 08:49:37 -02:00 |
|
Carlos Fonseca M
|
1dc6cc490c
|
Add file access defines Windows
|
2018-12-14 14:43:59 -06:00 |
|
Reuben Morais
|
a5bcecbe40
|
Address more review comments
|
2018-11-11 15:24:31 -02:00 |
|
Reuben Morais
|
4d05c9af46
|
Address review comments
|
2018-11-09 08:49:08 -02:00 |
|
Reuben Morais
|
3255f23426
|
ctcdecode binding fixes
|
2018-11-08 18:14:32 -02:00 |
|
Reuben Morais
|
23497fde41
|
Use unique_ptr for Scorer members
|
2018-10-30 09:21:30 -03:00 |
|
Reuben Morais
|
68258e356c
|
Address review comments
|
2018-10-29 23:57:14 -03:00 |
|
Reuben Morais
|
770d742cd5
|
Adjust ctcdecode to use our Alphabet code, support using trie files
|
2018-10-25 17:01:05 -03:00 |
|
Reuben Morais
|
c34fc5b7ac
|
Import parlance/ctcdecode into repository
|
2018-10-25 17:00:48 -03:00 |
|