Reuben Morais
|
da55cfae86
|
Revert "Merge pull request #3237 from lissyx/rename-training-package"
This reverts commit 3dcb3743ac , reversing
changes made to 457198c88d .
|
2020-08-26 11:46:08 +02:00 |
Alexandre Lissy
|
6f84bd1996
|
Rename deepspeech_training package
|
2020-08-10 16:58:18 +02:00 |
Reuben Morais
|
6eb784bd3e
|
Make DeepSpeech.py executable and call Python interpreter explicitly in docs
X-DeepSpeech: NOBUILD
|
2020-04-29 15:58:44 +02:00 |
Reuben Morais
|
a05baa35c9
|
Package training code to avoid sys.path hacks
|
2020-03-25 21:34:50 +01:00 |
Reuben Morais
|
29a2ac37f0
|
Merge pull request #2779 from reuben/export-metadata
Write model metadata to export folder unconditionally
|
2020-03-17 12:08:35 -03:00 |
Tilman Kamp
|
6b1d6773de
|
SDB support
|
2020-03-10 10:32:58 +01:00 |
Reuben Morais
|
48178005a2
|
Write model metadata to export folder unconditionally
|
2020-02-21 12:46:44 +01:00 |
Daniel
|
17ddc5600e
|
Reduce learning rate on plateau.
|
2020-02-18 16:17:51 +01:00 |
Reuben Morais
|
bd8b96c19d
|
Remove unneeded Saver instances
|
2020-02-17 15:55:16 +01:00 |
Reuben Morais
|
0e2f34f8cf
|
Synchronize TensorFlow logging with --log_level flag
|
2020-02-17 12:46:00 +01:00 |
Reuben Morais
|
c46d8396bc
|
Respect --load when exporting
|
2020-02-17 12:45:37 +01:00 |
JRMeyer
|
5bba9ea5d1
|
Transfer-learning support
|
2020-02-17 08:29:10 +01:00 |
Reuben Morais
|
3637f88c06
|
Fix CI errors, address comments, update examples
|
2020-02-12 10:13:02 +01:00 |
Reuben Morais
|
c512383aec
|
Fix consumers of DS_CreateModel
|
2020-02-12 10:13:02 +01:00 |
Reuben Morais
|
8e9b6ef7b3
|
Embed default beam width into exported graph and remove param from DS_CreateModel
|
2020-02-11 21:23:05 +01:00 |
Reuben Morais
|
1e2eb96248
|
Update all API consumers
|
2020-02-11 19:44:36 +01:00 |
Alexandre Lissy
|
ff401732a3
|
Enforce CTC decoder version check
Fix #2710
|
2020-02-03 10:24:21 +01:00 |
Reuben Morais
|
50830d7022
|
Fix whitespace
|
2020-01-27 15:59:39 +01:00 |
PedroDKE
|
3e349497ed
|
added an argument to choose the final export model name
|
2020-01-25 12:30:07 +01:00 |
Reuben Morais
|
f6cd28ba2d
|
Fix handling of InvalidArgumentError in training loop
X-DeepSpeech: NOBUILD
|
2020-01-08 17:10:47 +00:00 |
Reuben Morais
|
e1d14eb9a9
|
Merge pull request #2560 from mychiux413/sparse_warp
[SpecAugment] Refactor sparse_image_warp for dynamic shape of spectrogram
|
2020-01-03 13:25:31 +01:00 |
Yi-Hua Chiu
|
4133e620bd
|
remove debugging leftover, add UNSUPPORTED note, just skip invertible error
|
2020-01-03 10:32:02 +08:00 |
Yi-Hua Chiu
|
c570cb670a
|
sparse_warp still can have chance to raise error even after millions steps, so just recover the invertible error while training, unless error raise 3 times, it will be aborted
|
2020-01-02 11:06:15 +08:00 |
Alexandre Lissy
|
5f003cfbd6
|
Set forget_bias=0 for static RNN implementation
Fixes #2612
|
2019-12-20 13:28:46 +01:00 |
Yi-Hua Chiu
|
5fbc7e8596
|
[FIX] use time_warping_para to constraint control width, add logic to disable cache [ADD] num_control_points
|
2019-12-04 10:25:36 +08:00 |
Reuben Morais
|
e3b1b5fd42
|
Disable caching features to memory
|
2019-11-29 10:17:15 +01:00 |
Tilman Kamp
|
a160dc72c4
|
Fix: Added executable flag to DeepSpeech.py again
|
2019-11-21 13:08:53 +01:00 |
Tilman Kamp
|
29528ed7b7
|
Separate process per file; less log noise
|
2019-11-20 17:29:13 +01:00 |
Alexandre Lissy
|
fe6230020c
|
Support packaging as Zip file
|
2019-11-13 11:16:11 +01:00 |
Reuben Morais
|
8c82081779
|
Embed alphabet directly in model
|
2019-11-05 09:02:21 +01:00 |
Reuben Morais
|
31ec7a71f2
|
Fix undefined variable when saving test samples to --test_output_file
X-DeepSpeech: NOBUILD
|
2019-10-30 10:30:00 +01:00 |
Reuben Morais
|
44a605c8b7
|
Merge pull request #2435 from mozilla/uplift-utf8-fixes
Uplift general fixes from UTF-8 work
|
2019-10-25 09:09:48 +00:00 |
Reuben Morais
|
12baf5ffbc
|
Expose cutoff_prob and cutoff_top_n as flags
|
2019-10-23 11:15:23 +02:00 |
Alexandre Lissy
|
1939f74ec0
|
Store graph version on TFLite
|
2019-10-16 15:36:45 +02:00 |
Reuben Morais
|
ef3bdb2540
|
Merge PR #2434 - Add flag for automatic mixed precision training
|
2019-10-15 13:45:19 +02:00 |
Reuben Morais
|
31922cb3dc
|
Clarify docs and fix linter
|
2019-10-15 13:44:09 +02:00 |
Reuben Morais
|
e0d8ef75e8
|
Use try_loading and FLAGS.load in --one_shot_infer code
|
2019-10-14 21:03:14 +02:00 |
Reuben Morais
|
e75d1e4b61
|
Respect --test_output_files from DeepSpeech.py
|
2019-10-14 21:03:14 +02:00 |
Vinh Nguyen
|
909fa60601
|
adding automatic mixed precision training support
|
2019-10-14 12:34:10 +00:00 |
Alexandre Lissy
|
4f1f67f55d
|
Use TFLite optimizations flag
Fixes #2415
|
2019-10-09 12:21:35 +02:00 |
lissyx
|
031479d88b
|
Merge pull request #2406 from lissyx/disable-cache-dataaug
Disable cache when data augmentation is set
|
2019-10-08 18:10:32 +02:00 |
Alexandre Lissy
|
c35068f880
|
Disable cache when data augmentation is set
Fixes #2396
|
2019-10-08 17:29:59 +02:00 |
Reuben Morais
|
5a287a65e5
|
Set forget_bias=0 in CPU graph for compatibility with CudnnRNN
|
2019-10-07 21:06:29 +02:00 |
Reuben Morais
|
4302a5f767
|
Make language model scoring optional in Python inference code
|
2019-09-30 11:43:00 +02:00 |
Reuben Morais
|
889f069b1c
|
Merge pull request #2352 from mozilla/data-augmentation-pr
Data augmentation PR
|
2019-09-09 21:29:02 +02:00 |
Bernardo Henz
|
49c6a9c973
|
adding 'train_phase' to create_dataset. Now we can augment only the training-set.
|
2019-09-09 12:07:51 +02:00 |
Reuben Morais
|
371e73eb69
|
Create checkpoint dir before writing flags file in it
|
2019-09-06 13:55:55 +02:00 |
Reuben Morais
|
ba2d29b36f
|
Save flag values next to checkpoints
|
2019-09-06 11:35:10 +02:00 |
Reuben Morais
|
670e06365e
|
Run tf_upgrade_v2 on our code
|
2019-08-28 17:53:24 +02:00 |
Reuben Morais
|
24bcdeb3d6
|
Switch from deprecated tfv1.app to absl-py
|
2019-08-28 10:55:33 +02:00 |