Commit Graph

50 Commits

Author SHA1 Message Date
Reuben Morais
f70f068484 Update prod tests to point to re-exported 0.5 model 2019-06-20 18:32:30 -03:00
Reuben Morais
f02d79cca2 Update prod tests to point to 0.5 model 2019-06-07 13:14:45 -03:00
Alexandre Lissy
af26d8b2bb Deprecate training on Python 2.7 2019-05-10 17:23:54 +02:00
Alexandre Lissy
d18697d432 Rename task node-package to node-package-cpu 2019-03-20 11:58:56 +01:00
Alexandre Lissy
d993674ac1 Factor EXPECTED_TENSORFLOW_VERSION 2019-02-28 18:55:56 +01:00
Alexandre Lissy
76aa4b6fa8 Update TensorFlow TaskCluster artifacts 2019-02-20 23:27:17 +01:00
Alexandre Lissy
672fad9a9b Update TensorFlow artifacts 2018-12-13 18:39:38 +01:00
Reuben Morais
a0333728eb Build decoder package in automation 2018-11-08 18:35:42 -02:00
Alexandre Lissy
d2438397ce Update TensorFlow r1.12 2018-11-05 23:24:06 +01:00
Alexandre Lissy
740e8584bd Add benchmark_model tests 2018-11-05 20:04:40 +01:00
Alexandre Lissy
26f7bc30f0 Move to TensorFlow r1.12 2018-10-31 22:43:45 +01:00
Reuben Morais
c3860f63a3
Merge pull request #1679 from mozilla/ctcdecode
Use ctcdecode in native client (Fixes #1668)
2018-10-30 10:49:29 -03:00
Alexandre Lissy
5536e5440e Introduce NodeJS v11.x 2018-10-30 12:39:16 +01:00
Reuben Morais
70ff71c4c5 Switch native tests to ctcdecode trie and prodmodel 2018-10-25 17:38:22 -03:00
Alexandre Lissy
ae5303e130 Update TensorFlow r1.11 2018-10-25 12:28:40 +02:00
Alexandre Lissy
a6f9a60967 Update TensorFlow r1.11 2018-10-16 12:30:40 +02:00
Alexandre Lissy
fd9a311f1b Update TensorFlow r1.11 2018-10-11 16:50:07 +02:00
Alexandre Lissy
61a39c0a0a Fix fallout from stricter YAML parser 2018-10-02 19:16:53 +02:00
Alexandre Lissy
6d0ef57946 Switch to stable TensorFlow r1.11 2018-09-28 07:25:49 +02:00
Alexandre Lissy
1e0945e430 Update to TensorFlow r1.11 2018-09-24 19:23:44 +02:00
Alexandre Lissy
3dad37eb05 Remove AOT 2018-09-20 17:02:36 +02:00
Reuben Morais
42c99ee82e Bump to v0.2.0 and update prod model 2018-09-18 12:15:31 -03:00
Reuben Morais
75091a8ef3 Switch prod model to a streaming based one 2018-08-02 23:46:13 -03:00
Reuben Morais
c579b74a1d Switch to updated head in TensorFlow r1.6 branch 2018-08-02 13:25:24 -03:00
Alexandre Lissy
5520a6b29d Improve tag handling 2018-04-28 02:13:13 +02:00
Alexandre Lissy
e01784894e Unify version definition
Fixes #1293
2018-04-27 09:44:51 +02:00
Alexandre Lissy
6f0751d27d Switch to new TensorFlow r1.6 artifacts 2018-04-19 22:03:02 +02:00
Alexandre Lissy
f30bb0e5a2 Update to TensorFlow r1.6 with PYTHON_BIN_PATH forced 2018-04-15 16:30:15 +02:00
Alexandre Lissy
f77a5cdd2a Switch to GCC 7.2 from Linaro and Raspbian Stretch
Fixes #1304
2018-03-19 20:28:06 +01:00
Alexandre Lissy
6c4d4f1e68 Expose versions numbers on stderr
Fixes #1292
2018-03-16 09:46:31 +01:00
Alexandre Lissy
bb1fcc0542 Increase pip default timeout
Fixes #1289
2018-03-15 09:39:09 +01:00
Alexandre Lissy
164f67c972 Add Python2.7 ucs2+ucs4 variants
Fixes #1276
2018-03-01 17:51:52 +01:00
Alexandre Lissy
62034f7bf6 Switch to use Amazon EC2 mirrors
Fixes #1250
2018-02-15 17:38:58 +01:00
Alexandre Lissy
e4773028ba Update doc for mmap-able model
Fixes #1248
2018-02-15 17:23:33 +01:00
Alexandre Lissy
d7653d749b Use LDC93S1 small language model
How to regenerate:
 - Get a KenLM build
 - $ (tr -d '[:digit:]|[:punct:]' < LDC93S1.txt | tr '[:upper:]' '[:lower:]'; head -n 500 ../lm/vocab.txt) > vocab.txt
 - $ bin/lmplz --prune 0 0 1 --order 5 --text vocab.txt --arpa vocab.pruned.arpa
 - $ bin/build_binary  -s vocab.pruned.arpa vocab.pruned.lm
 - $ generate_trie ../alphabet.txt vocab.pruned.lm vocab.txt vocab.trie

Fixes #1245
2018-02-15 14:56:02 +01:00
Alexandre Lissy
0c323e8c67 Support MemmappedFileSystem
Fixes #1231
2018-02-15 12:18:52 +01:00
Alexandre Lissy
72298b8f6d Add different samplerate samples
Fixes #1022
2018-02-08 20:48:53 +01:00
Alexandre Lissy
30857cc288 Switch training model dependency to upstream-based
Currently, self-built Python package is not able to work, likely because
of the visibility of symbols. Let's switch to upstream TensorFlow for
now.
2018-01-31 16:54:37 +01:00
Alexandre Lissy
968c22c392 Avoid over-linking deepspeech.utils Python wrapper
Fixes #1116
2017-12-19 20:33:10 +01:00
Alexandre Lissy
5fdd77d24e Add OSX testing
Fixes #1072
2017-12-07 15:48:11 +01:00
Alexandre Lissy
fb456da394 Test training with multiple Python versions
Fixes #970
2017-12-01 22:43:34 +01:00
Alexandre Lissy
5b0ca1e410 Update to TensorFlow r1.4
Fixes #959
2017-11-30 18:51:13 +01:00
Alexandre Lissy
964e38fccd All NodeJS into one package 2017-11-21 14:36:40 +01:00
Alexandre Lissy
319bfe9730 Run test coverage against prod-similar model
Fixes #918
2017-11-14 16:27:41 +01:00
Alexandre Lissy
b42ade38bc TaskCluster IRC notifications
Fixes #927
2017-11-14 12:38:04 +01:00
Alexandre Lissy
42f605790a TaskCluster enabling of libdeepspeech_model.so 2017-11-03 17:25:25 +01:00
Alexandre Lissy
7e9767f0d8 Remove 'runs/0' references in artifacts path
Generated with:
$ sed -ri 's|runs/0/||g' taskcluster/*.tyml

Fixes #933
2017-11-02 15:28:08 +01:00
Alexandre Lissy
d4f3392aec Proper definition of .build.yml
Array to sr() was undocumented and is not supported in JS.

Fixes #925
2017-10-31 22:10:45 +01:00
Alexandre Lissy
bd0fedc312 Split TaskCluster build scripts and refactor some variables
This will help landing AOT support, avoiding turning tc-build.sh and
tc-package.sh into a spaghetti mess.

Fixes #898
2017-10-19 15:43:47 +02:00
Alexandre Lissy
31616daf02 TaskCluster Decision Task
Fixes #837
2017-09-18 20:59:27 +02:00