Commit Graph

  • c7676286ab install libsndfile from /usr to thirdparty Luo Tao 2017-07-26 16:25:11 +0800
  • cb0680e8c4 follow comments to modify README.md Yibing Liu 2017-07-20 11:47:46 +0800
  • 724ef18596 update several scripts to support mfcc Yibing Liu 2017-07-19 22:40:01 +0800
  • ee5abbe37d add mfcc feature for DS2 Yibing Liu 2017-07-18 10:14:37 +0800
  • ccea7c0150 enable loading language model in multiple format Yibing Liu 2017-07-10 11:34:47 +0800
  • 8ce9546710 modify README.md Yibing Liu 2017-07-11 14:56:37 +0800
  • d15c48d616 upload the language model Yibing Liu 2017-07-11 13:32:35 +0800
  • 5bfa066920 add setup and README for deployment Yibing Liu 2017-07-06 12:18:09 +0800
  • 94a6811660 code cleanup for the deployment decoder Yibing Liu 2017-07-06 11:25:05 +0800
  • 2e76f82cf7 Merge branch 'develop' into ctc_decoder_deploy Yibing Liu 2017-07-05 15:06:49 +0800
  • 0cadc56a84 follow comments in code format Yibing Liu 2017-07-05 11:05:26 +0800
  • 37e98df74d enable resetting params in scorer Yibing Liu 2017-07-04 19:48:56 +0800
  • d9d9514269 fix bugs Yibing Liu 2017-07-04 19:15:34 +0800
  • 3c77d369ca Make ds2 run on paddle cloud 1. Refine data_utils/data.py to read bytes from tar file 2. Add scripts to submit paddle cloud job for ds2 trainning wanghaoshuang 2017-07-03 15:14:23 +0800
  • fd102c2110 Merge branch 'develop' into ctc_decoder_deploy Yibing Liu 2017-06-29 15:56:25 +0800
  • 7c7e17e249 add deploy.py Yibing Liu 2017-06-29 11:19:39 +0800
  • 2f15a78707 add initial files for deployment Yibing Liu 2017-06-29 10:05:02 +0800
  • 90d83bf739 resolve conflicts in requirements.txt Yibing Liu 2017-06-27 20:27:13 +0800
  • aeccd9851b append README.md Yibing Liu 2017-06-27 20:22:47 +0800
  • db37c34919 modify some detail of augmentor xushaoyong 2017-06-27 18:48:49 +0800
  • 8ba98cb518 fix decoders' unittest Yibing Liu 2017-06-27 18:35:49 +0800
  • e1e2914ec9 remove augmentor unittest xushaoyong 2017-06-27 18:06:16 +0800
  • 7f2e7e1c2c resolve conflict with setup.sh xushaoyong 2017-06-27 17:48:25 +0800
  • 26510f74a6 refine ctc_beam_search_decoder Yibing Liu 2017-06-27 17:42:44 +0800
  • 286228c219 Merge pull request #127 from pkuyym/fix-soundfile xushaoyong 2017-06-27 17:25:17 +0800
  • 29f6ae0807 modify audio resample function xushaoyong 2017-06-27 17:16:35 +0800
  • c5995bb7e1 add 3 augmentor and unittest xushaoyong 2017-06-27 17:05:32 +0800
  • 237df23e7e Merge branch 'develop' of https://github.com/PaddlePaddle/models into ctc_decoder_dev Yibing Liu 2017-06-26 22:01:59 +0800
  • 0dadd14600 Patch for adding missing shift_perturb.py in last commmit (pull request #114). Xinghai Sun 2017-06-26 19:19:16 +0800
  • 7324d41e4a Merge branch 'develop' of https://github.com/PaddlePaddle/models into ctc_decoder_dev Yibing Liu 2017-06-26 17:48:59 +0800
  • cdd52ac270 Fix a missing abs bug for DS2 AudioSegment. Xinghai Sun 2017-06-26 14:17:22 +0800
  • 6d6cdf4057 Refine SoundFile installation process. 1. Install libsndfile first. 2. Install SoundFile using pip. yangyaming 2017-06-26 13:04:36 +0800
  • 13f708739b Improve audio featurizer and add shift augmentor. Xinghai Sun 2017-06-21 20:52:30 +0800
  • 8033845615 add unit test for decoders Yibing Liu 2017-06-21 14:52:06 +0800
  • b340d4ed2f modify setup.sh to delete the install of libsamplerate chrisxu2016 2017-06-21 12:18:33 +0800
  • d6a852a304 modify setup.sh to delete the install of libsamplerate chrisxu2016 2017-06-21 12:11:43 +0800
  • 2450591a44 add 3 augmentor class and change resample module chrisxu2016 2017-06-21 11:47:15 +0800
  • 5398360e5f Add 3 augmentor classes and related unittests chrisxu2016 2017-06-20 18:50:13 +0800
  • df77c6d5db Add 3 augmentor classes and related unittests chrisxu2016 2017-06-20 18:39:48 +0800
  • f20c6d643f Merge branch 'develop' of https://github.com/PaddlePaddle/models into ctc_decoder_dev Yibing Liu 2017-06-20 18:21:11 +0800
  • d64f470078 add augmentor class chrisxu2016 2017-06-20 18:19:43 +0800
  • d104eccf67 Update the default num_threads for DS2 data generator. Xinghai Sun 2017-06-20 18:13:46 +0800
  • 1d8cc4a5a9 Add multi-threading support for DS2 data generator. Xinghai Sun 2017-06-20 17:06:53 +0800
  • 71283d619d add augmentor class chrisxu2016 2017-06-20 16:33:28 +0800
  • 115a06bb37 add augmentor class chrisxu2016 2017-06-20 16:24:03 +0800
  • 0729abe02e tiny adjust Yibing Liu 2017-06-20 12:14:24 +0800
  • d8089315f4 Merge branch 'develop' of https://github.com/PaddlePaddle/models into ctc_decoder_dev Yibing Liu 2017-06-20 12:03:30 +0800
  • a5dcd23bf2 Follow comments. yangyaming 2017-06-19 23:46:44 +0800
  • d35b747175 Fix ci following: 1. Unify the dependency installation process in setup.sh. 2. Change the version of package scipy from 0.13.0b1 to 0.13.1 yangyaming 2017-06-19 23:24:58 +0800
  • b2cf96cc46 adapt to the new data provider Yibing Liu 2017-06-19 19:00:08 +0800
  • d1f5123bcf Merge pull request #99 from PaddlePaddle/new_augmentation_2 Xinghai Sun 2017-06-19 15:30:04 +0800
  • def66a3223 Follow comments. yangyaming 2017-06-19 11:31:34 +0800
  • ddb2bdc190 add audio file chrisxu2016 2017-06-19 00:08:05 +0800
  • 25ce7ebe7b add audio file chrisxu2016 2017-06-18 18:22:48 +0800
  • 36743d3689 add scoring last word in beam search Yibing Liu 2017-06-18 18:11:01 +0800
  • 21161b0165 add audio file chrisxu2016 2017-06-18 17:11:58 +0800
  • 107f8b89ae add audio augmentation chrisxu2016 2017-06-18 16:47:09 +0800
  • ff01d048d3 final refining on old data provider: enable pruning & add evaluation & code cleanup Yibing Liu 2017-06-18 16:36:52 +0800
  • b8341da63d add audio augmentation chrisxu2016 2017-06-18 16:23:30 +0800
  • 26eb54eb37 Follow comments. yangyaming 2017-06-18 14:31:57 +0800
  • 86eeb52c06 Merge branch 'develop' of https://github.com/PaddlePaddle/models into fix-81 yangyaming 2017-06-18 13:55:37 +0800
  • 5ca270d30a add audio file chrisxu2016 2017-06-17 09:03:18 +0800
  • d1ee10be10 modify audio and speech chrisxu2016 2017-06-16 18:29:56 +0800
  • d66d740ea0 add audio part chrisxu2016 2017-06-16 15:17:43 +0800
  • ed5f04afb8 Add shuffle type of instance_shuffle and batch_shuffle_clipped. Xinghai Sun 2017-06-15 17:05:00 +0800
  • 65e34c535b add augmentation chrisxu2016 2017-06-15 03:08:30 +0800
  • 04a225ae4f Enable min_batch_num in train.py and update train info print. Xinghai Sun 2017-06-14 18:14:50 +0800
  • f85f8558cf Add unittest. yangyaming 2017-06-14 15:00:10 +0800
  • 397b2fc288 Merge branch 'develop' of https://github.com/PaddlePaddle/models into fix-81 yangyaming 2017-06-14 14:46:32 +0800
  • 1cef98f210 Update README.md for DS2. Xinghai Sun 2017-06-13 23:33:38 +0800
  • b07ee84a1d Add function, class and module docs for data parts in DS2. Xinghai Sun 2017-06-13 23:16:07 +0800
  • a633eb9cc6 change two arguments Yibing Liu 2017-06-13 15:28:43 +0800
  • 7db13ca9db enable lm in multiprocessing decoder & add script for params tuning Yibing Liu 2017-06-13 14:16:54 +0800
  • bc3224eb14 Follow comments. yangyaming 2017-06-12 12:51:01 +0800
  • cd3617aeb4 Refactor whole data preprocessor for DS2 (re-design classes, re-organize dir, add augmentaion interfaces etc.). Xinghai Sun 2017-06-12 23:19:40 +0800
  • 9c27b1d14e add more comments and update train.py dangqingqing 2017-06-12 19:53:41 +0800
  • bf73540067 Merge branch 'develop' of https://github.com/PaddlePaddle/models into ds2 dangqingqing 2017-06-12 19:07:07 +0800
  • c25c62b8f9 refine audio_data_utils.py dangqingqing 2017-06-12 19:06:55 +0800
  • bb34e90398 correct typos in annotations Yibing Liu 2017-06-12 17:20:22 +0800
  • ae83a25aff add beam search decoder using multiprocesses Yibing Liu 2017-06-12 17:13:48 +0800
  • 453f038df9 optimize the efficiency of beam search Yibing Liu 2017-06-08 16:05:40 +0800
  • 9fda521ee3 improve external scorer Yibing Liu 2017-06-07 19:24:04 +0800
  • b046e651e7 tiny modify to pass CI Yibing Liu 2017-06-07 17:43:12 +0800
  • 44efbed798 rename variables in decoder Yibing Liu 2017-06-07 16:59:11 +0800
  • 21ff590e6d modify language model scoring Yibing Liu 2017-06-07 14:57:04 +0800
  • ac370eca85 add annotations Yibing Liu 2017-06-07 09:06:58 +0800
  • 51f35a5372 code clean & add external scorer Yibing Liu 2017-06-07 02:21:35 +0800
  • dedbfb2654 enable ctc beam search decoder Yibing Liu 2017-06-05 08:48:54 +0800
  • cfe9d22866 update annotations Yibing Liu 2017-06-04 19:19:36 +0800
  • c943ca79ac mv ctc_beam_search_decoder into deep_speech_2/ Yibing Liu 2017-06-04 19:15:09 +0800
  • e016778e20 Merge pull request #78 from xinghai-sun/ds2_libri Xinghai Sun 2017-06-09 11:52:10 +0800
  • 06e9f71389 Remove manifest's line number check from librispeech.py and update README.md. Xinghai Sun 2017-06-08 22:20:11 +0800
  • 3f63e069e0 Fix typos and follow comments. yangyaming 2017-06-08 21:35:17 +0800
  • cc2a4d4e3d Add error rate calculation script. yangyaming 2017-06-08 17:18:38 +0800
  • f49eab5fec Change assert to exception raising. yangyaming 2017-06-07 19:11:21 +0800
  • d3eeb7fd76 Refine librispeech.py for DeepSpeech2. Xinghai Sun 2017-06-07 17:44:11 +0800
  • 7c85e0fdb5 Support variable input batch and sortagrad. dangqingqing 2017-06-07 16:37:13 +0800
  • d2e467385d Add loading model function for train.py. yangyaming 2017-06-05 21:00:15 +0800
  • 730d5c4dd3 Update DS2 README.md and fix bug in librispeech.py Xinghai Sun 2017-06-03 15:18:33 +0800
  • 2a83486500 Refactor decoder interfaces and add ./data directory. Xinghai Sun 2017-06-03 14:52:02 +0800