ESPnet Version 0.6.3

New Features

• [New Features] VCC2020 baseline recipe #1641 by @unilight
• [New Features] Embed defaultlm #1623 by @qmpzzpmq

Enhancement

• [Enhancement] add test -d $(KALDI): tools/Makefile #1718 by @kamo-naoyuki
• [Enhancement] Add option to load pretrained model in TTS #1639 by @kan-bayashi
• [Enhancement] Add reverse_direction option to MT #1658 by @hirofumi0810

Recipe

• [Recipe] Remove unnecessary lines on Fisher-CallHome Spanish #1650 by @hirofumi0810
• [Recipe] Add the Aishell2 recipe for the master branch. #1615 by @pengchengguo
• [Recipe] Reformat the RESULTS.md in vivos #1689 by @sw005320

Documentation

• [Documentation] Added multiple GPU TIPS #1734 by @sw005320
• [Documentation] added pure attention decoding TIPS #1725 by @sw005320

Docker

• [Docker] Docker local updates #1677 by @Fhrozen
• [Docker] Docker updates #1624 by @Fhrozen

Bugfix

• [Bugfix] fix #1751 #1779 by @qmpzzpmq
• [Bugfix] Fix v.0.3.0 pretrained Transformer model compatibility #1778 by @ShigekiKarita
• [Bugfix] Fix torch.ctc not implemented in float16 by casting float32 #1777 by @ShigekiKarita
• [Bugfix] Workaround for bug of configargparse==1.2 #1764 by @kamo-naoyuki
• [Bugfix] change train_iter to be the dataloader object #1741 by @bobchennan
• [Bugfix] fix #1634 #1719 by @kamo-naoyuki
• [Bugfix] [VCC2020 baseline] Extra reference set #1684 by @unilight
• [Bugfix] missing torch version in check_install.py #1675 by @beckgom
• [Bugfix] Fix model link in the tedlium2 recipe #1662 by @sw005320
• [Bugfix] Update Install for Pytorch version #1659 by @Fhrozen
• [Bugfix] Fix lm compatibility for v2 #1653 by @kan-bayashi
• [Bugfix] correct results with builtin CTC and PyTorch 1.3 in WSJ recipe #1652 by @Emrys365
• [Bugfix] Fix lm backward compatibility #1649 by @kan-bayashi
• [Bugfix] fix #1604 #1626 by @TitouanT
• [Bugfix] Fix a bug in csmsc recipe #1618 by @kan-bayashi
• [Bugfix] Update e2e_asr_common.py #1735 by @zh794390558
• [Bugfix] remove non-available options #1738 by @sw005320

Acknowledgements

Special thanks to @Emrys365, @Fhrozen, @ShigekiKarita, @TitouanT, @beckgom, @bobchennan, @hirofumi0810, @kamo-naoyuki, @kan-bayashi, @pengchengguo, @qmpzzpmq, @sw005320, @unilight, @zh794390558.

ESPnet Version 0.6.2

New Features

• [New Features] Transducer v3 (w/ transformer support for encoder/decoder) #1422 by @b-flo
• [New Features] Improving LM training (custom optimizer, custom scheduler, Transformer LM, etc) #1246 by @ShigekiKarita

Enhancement

• [Enhancement] Add MelGAN pretrained model and support in demo notebook #1581 by @kan-bayashi

Recipe

• [Recipe] Update fisher-callhome results #1606 by @hirofumi0810
• [Recipe] Update run_rnnt.sh #1602 by @qmpzzpmq
• [Recipe] Upload Must-C models #1594 by @hirofumi0810
• [Recipe] Upload Libri trans models #1569 by @hirofumi0810
• [Recipe] Upload How2 models #1568 by @hirofumi0810
• [Recipe] Add Mboshi-French corpus #1545 by @hirofumi0810
• [Recipe] Update WSJ results using PyTorch 1.3.1 and builtin CTC #1527 by @Emrys365
• [Recipe] [WIP] IWSLT2016 Recipe #1492 by @butsugiri
• [Recipe] Update for Common Voice recipe & Multilingual training recipe #1485 by @ftshijt
• [Recipe] [WIP] DiPCo Recipe #1472 by @Fhrozen

Documentation

• [Documentation] Support markdown-table for sphinx #1611 by @kamo-naoyuki
• [Documentation] update docs & README.md #1605 by @kamo-naoyuki
• [Documentation] fix a link within README.md #1584 by @sw005320
• [Documentation] Add MT result #1576 by @butsugiri
• [Documentation] update readme to include Linux installation guides from CI #1567 by @sw005320
• [Documentation] Update WSJ results in the main README.md #1537 by @Emrys365

Bugfix

• [Bugfix] Fix a typo in AMI script? #1595 by @HuangZiliAndy
• [Bugfix] ru_open_stt recipe bug fix #1589 by @qmpzzpmq
• [Bugfix] Fix pure CTC decoding #1580 by @takaaki-hori
• [Bugfix] fix snapshot/model test condition #1577 by @IceCreamWW
• [Bugfix] Fix IWSLT16 Script Permission #1543 by @butsugiri
• [Bugfix] Fix bug in MT training script #1515 by @hirofumi0810
• [Bugfix] Use Markdown table instead for WER results #1514 by @lijunzh
• [Bugfix] Fix a compatibility problem with PyTorch 1.3.0 in ESPnet (v0.6.0) #1421 by @Emrys365

Acknowledgements

Special thanks to @Emrys365, @Fhrozen, @HuangZiliAndy, @IceCreamWW, @ShigekiKarita, @b-flo, @butsugiri, @ftshijt, @hirofumi0810, @kamo-naoyuki, @kan-bayashi, @lijunzh, @qmpzzpmq, @sw005320, @takaaki-hori.

ESPnet Version 0.6.1

Happy new year!

New Features

• [New Features] Transformer NMT #1479 by @hirofumi0810
• [New Features] Support knowledge distillation in FastSpeech training #1415 by @kan-bayashi
• [New Features] Support attention constraint for Tacotron 2 #1407 by @kan-bayashi

Enhancement

• [Enhancement] Add focus rate logging in decoding #1412 by @kan-bayashi
• [Enhancement] Support Tacotron 2 as a teacher of FastSpeech #1406 by @kan-bayashi
• [Enhancement] Support length-weighted normalization in loss calculation #1397 by @kan-bayashi
• [Enhancement] Transformer End-to-End Speech Translation #1348 by @hirofumi0810

Recipe

• [Recipe] Add LM training/decoding in swbd recipe #1463 by @YosukeHiguchi
• [Recipe] Add Fisher-CallHome asr1b recipe #1390 by @hirofumi0810
• [Recipe] RECIPE JESC for MT #1346 by @Fhrozen

Documentation

• [Documentation] added interspeech 2019 tutorial link and performed spell check #1476 by @sw005320
• [Documentation] Updated README in ljspeech about FastSpeech training #1468 by @kan-bayashi
• [Documentation] Add knowledge dist based FastSpeech link in README #1465 by @kan-bayashi

Refactoring

• [Refactoring] Unify TTS Transformer mask with ASR Transformer #1470 by @kan-bayashi

Bugfix

• [Bugfix] fixed a small problem in run.sh #1466 by @Peidong-Wang
• [Bugfix] Fix wrong SC2026 fixing #1458 by @kan-bayashi
• [Bugfix] Fix multi-encoder ASR integration test #1432 by @ShigekiKarita
• [Bugfix] Fix wrong type float -> int #1413 by @kan-bayashi
• [Bugfix] Fix missing key error in Tacotron2 #1408 by @kan-bayashi
• [Bugfix] TransformerST on Fisher-Callhome #1398 by @hirofumi0810
• [Bugfix] fix rnnlm load bug #1391 by @Cescfangs
• [Bugfix] Fix gradient accumlation #1388 by @hirofumi0810

Acknowledgements

Special thanks to @Cescfangs, @Fhrozen, @Peidong-Wang, @ShigekiKarita, @YosukeHiguchi, @hirofumi0810, @kan-bayashi, @sw005320.

ESPnet Version 0.6.0

New Features

• [New Features] Support Parallel WaveGAN #1333 by @kan-bayashi
• [New Features] Support save snapshot by iteration #1204 by @fanlu
• [New Features] Multi-encoder architecture with hierarchical attention and per-encoder CTC #1193 by @ruizhilijhu
• [New Features] Support multiple inputs #1180 by @ruizhilijhu
• [New Features] Add E2E-ST specific modules #1139 by @hirofumi0810

Enhancement

• [Enhancement] Fixing compatibility problems with PyTorch 1.3.0 in ESPnet (v0.5.3) #1343 by @Emrys365
• [Enhancement] Change log level info -> warning about batchsize #1336 by @kan-bayashi
• [Enhancement] Support batch decoding for streaming E2E #1270 by @takenori-y
• [Enhancement] Implement attention cache in Transformer for faster decoding #1240 by @ShigekiKarita

Bugfix

• [Bugfix] Fix pretrained model URL for master #1351 by @kan-bayashi
• [Bugfix] Return parser in add_arguments method for transducer #1337 by @b-flo
• [Bugfix] Disabling nonlinear activation of the last encoder layer #1323 by @simpleoier
• [Bugfix] Fixed error: "Expected object of device type cuda but got device type cpu" in decoder of transducer #1315 by @rai4
• [Bugfix] Fix ASR eval for TTS in the case of trans_type=phn #1368 by @kan-bayashi
• [Bugfix] Make --preprocess_conf optional in pack_model.sh #1365 by @kan-bayashi
• [Bugfix] Remove set start method to fix #1290 #1363 by @kan-bayashi
• [Bugfix] Fix pretrained model URL #1354 by @kan-bayashi
• [Bugfix] Fix pretrained model URL #1350 by @kan-bayashi
• [Bugfix] Fix TTS transformer attention weight calculation in inference #1331 by @kan-bayashi
• [Bugfix] Fix decoding for chainer transformer #1101 by @Fhrozen

Recipe

• [Recipe] Update libri_trans asr recipe #1344 by @hirofumi0810
• [Recipe] Update LJSpeech to limit frequency range #1330 by @kan-bayashi
• [Recipe] IWSLT19 Speech Translation recipe #1169 by @hirofumi0810
• [Recipe] Must-C NMT recipe #1168 by @hirofumi0810
• [Recipe] How2 NMT recipe #1165 by @hirofumi0810
• [Recipe] Update how2 recipe #1148 by @hirofumi0810
• [Recipe] Pre-trained CSJ model #1341 by @takenori-y
• [Recipe] TTS: add FastSpeech config and result for jsut #1321 by @r9y9
• [Recipe] Asr commonvoice recipe update #1241 by @ftshijt

Documentation

• [Documentation] Update notebook submodule #1367 by @kan-bayashi
• [Documentation] Fix sphinx warning of TTS modules #1366 by @kan-bayashi
• [Documentation] Update notebook and add to Sphinx document #1364 by @kan-bayashi
• [Documentation] Update notebook #1352 by @kan-bayashi
• [Documentation] Doc for Chainer transformer #1017 by @Fhrozen
• [Documentation] Update README #1342 by @takenori-y

Refactoring

• [Refactoring] Indirect call for training method [chainer] #1256 by @Fhrozen
• [Refactoring] Refact transformer for transformer LM #1223 by @Fhrozen
• [Refactoring] Refine NMT #1152 by @hirofumi0810
• [Refactoring] Small changes in chainer backend #1110 by @Fhrozen
• [Refactoring] Format Chainer E2E transformer forward (fixed) #1034 by @Fhrozen

Acknowledgements

Special thanks to @Emrys365, @Fhrozen, @ShigekiKarita, @b-flo, @fanlu, @ftshijt, @hirofumi0810, @kan-bayashi, @r9y9, @rai4, @ruizhilijhu, @simpleoier, @takenori-y.

ESPnet Version 0.5.4

Bugfix

• [Bugfix] Fixed pretrained model URL in CSMSC reicpe #1314 by @kan-bayashi
• [Bugfix] Fix CSMSC wavenet link #1298 by @kan-bayashi
• [Bugfix] Minor fix of FastSpeech #1295 by @kan-bayashi
• [Bugfix] [bug fixing] Using inplace masked_fill_() #1273 by @Emrys365
• [Bugfix] Fix RuntimeError in setting spawn multiple times #1267 by @kan-bayashi
• [Bugfix] Use spawn in multiprocessing to fix #404 #1251 by @kan-bayashi

Documentation

• [Documentation] Update README.md #1309 by @kan-bayashi
• [Documentation] Fix docstrings #1288 by @kan-bayashi
• [Documentation] Fixed a typo in swbd asr1 #1220 by @Shujian2015
• [Documentation] update notebook #1219 by @ShigekiKarita

Recipe

• [Recipe] Update VAIS1000 recipe RESULTS.md #1308 by @kan-bayashi
• [Recipe] Fix VAIS1000 recipe #1305 by @kan-bayashi
• [Recipe] Update CSMSC results #1299 by @kan-bayashi
• [Recipe] Add vais1000 recipe - Vietnamese TTS #1283 by @enamoria
• [Recipe] Add VIVOS recipe - Vietnamese ASR #1271 by @hieuthi
• [Recipe] Add JNAS tts1 recipe #1269 by @kan-bayashi
• [Recipe] Support Polish speakers in M-AILABS #1265 by @kan-bayashi
• [Recipe] Add TWEB recipe #1263 by @kan-bayashi
• [Recipe] Update M-AILABS results #1262 by @kan-bayashi
• [Recipe] Add CSMSC reicpe #1259 by @kan-bayashi
• [Recipe] Add JVS recipe #1258 by @kan-bayashi
• [Recipe] Add CMU Arctic recipes #1257 by @kan-bayashi
• [Recipe] Add M-AILABS pretrained models #1229 by @kan-bayashi

New Features

• [New Features] Add eval-interval-epochs for the tiny dataset #1306 by @kan-bayashi
• [New Features] ASR-based CER/WER eval for TTS #1190 by @potato-inoue

Enhancement

• [Enhancement] Add Mandarin Pretrained Wavenet #1292 by @kan-bayashi
• [Enhancement] Add pretrained models: JSUT and LibriTTS #1260 by @r9y9
• [Enhancement] Improved JSUT TTS recipe #1216 by @r9y9

Acknowledgements

Special thanks to @Emrys365, @ShigekiKarita, @Shujian2015, @enamoria, @hieuthi, @kan-bayashi, @potato-inoue, @r9y9.

ESPnet Version 0.5.3

Bugfix

• [Bugfix] Fix a bug in building docker container #1197 by @protoget
• [Bugfix] fixed h5py version as 2.9.0 #1183 by @ruizhilijhu
• [Bugfix] Fix error on waveform generation by WaveNet #1170 by @r9y9
• [Bugfix] Sort nbest_hyps without limiting them to beam size #1157 by @elgeish
• [Bugfix] fix recursive make #1153 by @b-flo
• [Bugfix] missing file in iwslt19 #1147 by @sw005320
• [Bugfix] Wsj mix #1145 by @simpleoier

Enhancement

• [Enhancement] Install warp-ctc from PyPI #1196 by @ysk24ok
• [Enhancement] TTS: MoL WaveNet minor update #1195 by @r9y9
• [Enhancement] Transducer v1.2 #1173 by @b-flo

New Features

• [New Features] Add support for MoL WaveNet to synth_wav.sh #1186 by @r9y9
• [New Features] Using pytorch dataloader for pytorch backend #1138 by @bobchennan

Recipe

• [Recipe] dirha_wsj recipe #1179 by @ruizhilijhu
• [Recipe] Update Russian open STT recipe for v0.5 of the dataset #1160 by @akreal
• [Recipe] Blizzard recipe #1056 by @potato-inoue

Refactoring

• [Refactoring] Install warpctc-pytorch from pytorch-0.4 branch when PyTorch version is 0.4.X #1162 by @ysk24ok
• [Refactoring] using python3 as default #1159 by @zh794390558
• [Refactoring] Fix download_from gdrive.sh on osx #1158 by @r9y9

Documentation

• [Documentation] Fix doc/module2rst.py to use glob and remove --nowarn from travis-sphinx #1155 by @ShigekiKarita

Acknowledgements

Special thanks to @ShigekiKarita, @akreal, @b-flo, @bobchennan, @elgeish, @potato-inoue, @protoget, @r9y9, @ruizhilijhu, @simpleoier, @sw005320, @ysk24ok, @zh794390558.

ESPnet Version 0.5.2

Documentation

• [Documentation] Clean up TTS module docstrings #1143 by @kan-bayashi
• [Documentation] update readme for warp-transducer #1125 by @sw005320
• [Documentation] Fix flake8 blacklist #1107 by @ShigekiKarita

Bugfix

• [Bugfix] Minor fix #1142 by @kan-bayashi
• [Bugfix] Fix apex error when opt == “noam" #1134 by @kan-bayashi
• [Bugfix] Fix model compatibility #1133 by @kan-bayashi
• [Bugfix] Fix backward compatibility problem in PositionalEncoding by adding pre-hook to ignore self.pe #1127 by @ShigekiKarita
• [Bugfix] fix iwslt19 recipe #1124 by @sw005320
• [Bugfix] Fix best validation perplexity LM averaging #1122 by @akreal
• [Bugfix] Fix bug in how2 asr1 #1117 by @hirofumi0810
• [Bugfix] Fix: wrong variable in greedy decode #1113 by @b-flo
• [Bugfix] Chainer fix mixed input #1096 by @Fhrozen
• [Bugfix] Fix deleted argument atype #1095 by @Fhrozen
• [Bugfix] Fix guided attention loss in Tacotron2 when reduction factor > 1 #1087 by @kan-bayashi
• [Bugfix] Fix multi gpu LM issues and add hdf5 LM dataset dump #1083 by @ShigekiKarita

Enhancement

• [Enhancement] Add stdout.pl for debugging version run.pl #1141 by @ShigekiKarita
• [Enhancement] Update recog_wav.sh #1140 by @kan-bayashi
• [Enhancement] Update spm_train and test it #1135 by @ShigekiKarita
• [Enhancement] Transducer v1.1 #1129 by @b-flo
• [Enhancement] Allow to extend the length of positional encoding at training and inference #1105 by @ShigekiKarita
• [Enhancement] Update batchfy.py #1104 by @zh794390558
• [Enhancement] Add PYTHONIOENCODING=UTF-8 in path.sh #1099 by @kan-bayashi
• [Enhancement] Improve batch decoding #980 by @takaaki-hori
• [Enhancement] Implement add_arguments method of E2E for rnn. #941 by @kamo-naoyuki

Recipe

• [Recipe] Update swbd #1137 by @sw005320
• [Recipe] Updated symlink in Librispeech #1130 by @kan-bayashi
• [Recipe] Add missing lines to iwslt19 LM training data #1126 by @hirofumi0810
• [Recipe] Add iwslt19 ASR recipe #1120 by @hirofumi0810
• [Recipe] How2 speech translation recipe #1102 by @hirofumi0810
• [Recipe] Must-C ASR recipe #1098 by @hirofumi0810
• [Recipe] Must-C speech translation corpus #1085 by @hirofumi0810
• [Recipe] Replace character-level recipe with the BPE one in iwslt18 #1079 by @hirofumi0810
• [Recipe] Fix swbd recipe v2 #1072 by @sw005320
• [Recipe] Updated REVERB multi-channel E2E recipe #1057 by @Xiaofei-Wang

New Features

• [New Features] Add --train-dtype option for float16/float32/float64 precision training in pytorch ASR and LM #1119 by @ShigekiKarita
• [New Features] transfer learning #1103 by @b-flo
• [New Features] New beam-search framework: ScorerInterface, CPU/GPU float16/32/64 decoding, and new language models (SeqRNNLM and TransformerLM) #1092 by @ShigekiKarita
• [New Features] Support pretrained WaveNet vocoder #1081 by @kan-bayashi
• [New Features] RNN-Transducer #1065 by @b-flo

Acknowledgements

Special thanks to @Fhrozen, @ShigekiKarita, @Xiaofei-Wang, @akreal, @b-flo, @hirofumi0810, @kamo-naoyuki, @kan-bayashi, @sw005320, @takaaki-hori, @zh794390558.

ESPnet Version 0.5.1

Bugfix

• [Bugfix] Fix conda installation error #1076 by @kan-bayashi
• [Bugfix] Minor fix batchsize log when batchsize = 0 #1068 by @kan-bayashi
• [Bugfix] Fix spm decode #1062 by @ShigekiKarita
• [Bugfix] Minor fix to use fastspeech in synth_wav.sh #1061 by @kan-bayashi
• [Bugfix] Fix help message to enable line break #1059 by @kan-bayashi
• [Bugfix] Fix tensorboard interval in validation #1054 by @ShigekiKarita
• [Bugfix] Update E2E-ASR test #1041 by @kan-bayashi
• [Bugfix] Fix Loss Calculation #1039 by @Fhrozen

Refactoring

• [Refactoring] Remove unused conf #1070 by @kan-bayashi
• [Refactoring] [Reopen] Support default arguments #1067 by @kan-bayashi
• [Refactoring] Refactor E2E-TTS test #1042 by @kan-bayashi

CI

• [CI] Add TTS integration test #1069 by @kan-bayashi
• [CI] Make test smaller to speed up #1044 by @kan-bayashi
• [CI] Separate tasks in each job of circleci #1043 by @kan-bayashi

Recipe

• [Recipe] Add data augmentation to ami recipe #1066 by @Jzmo
• [Recipe] Update accum_grad for a single gpu in CSJ #1050 by @kan-bayashi
• [Recipe] add commonvoice recipe #1000 by @YosukeHiguchi
• [Recipe] REVERB multi-channel E2E recipe #985 by @Xiaofei-Wang

New Features

• [New Features] Support multi gpu in pytorch lm #1063 by @ShigekiKarita

Enhancement

• [Enhancement] Use librosa's fast Griffin-Lim #1058 by @kan-bayashi
• [Enhancement] Add option to select the integration type of speaker embedding #1047 by @kan-bayashi
• [Enhancement] update tedlium3 recipe with transformer #1037 by @ShigekiKarita
• [Enhancement] update tedlium2 config #1036 by @ShigekiKarita
• [Enhancement] Support of other recipe in recog_wav.sh #1026 by @hiratake55

Acknowledgements

Special thanks to @Fhrozen, @Jzmo, @ShigekiKarita, @Xiaofei-Wang, @YosukeHiguchi, @hiratake55, @kan-bayashi.

ESPnet Version 0.5.0

CI

• [CI] Integration test with mini AN4 #1035 by @ShigekiKarita
• [CI] codecov support #850 by @ShigekiKarita

Bugfix

• [Bugfix] [Bug] Fix error calculator for report false #1032 by @Fhrozen
• [Bugfix] fix unk scoring #1002 by @sw005320
• [Bugfix] make tensorboard logging done every 100 iters #996 by @sw005320

Refactoring

• [Refactoring] TTS: avoid using asr module in TTS #1031 by @r9y9
• [Refactoring] Exit 1 when source command return 1 #1030 by @kan-bayashi
• [Refactoring] Refactor FileReaderWrapper and FileWriterWrapper #947 by @kamo-naoyuki

Enhancement

• [Enhancement] Use pypi sentencepiece #1029 by @ShigekiKarita
• [Enhancement] Add log of the inference speed of TTS models #1027 by @kan-bayashi
• [Enhancement] Add GPU decodable test for TTS modules #1025 by @kan-bayashi
• [Enhancement] Support multi-speaker FastSpeech #1006 by @kan-bayashi
• [Enhancement] Custom Training extensions for ASR chainer #1004 by @Fhrozen
• [Enhancement] Support multi-speaker Transformer #1001 by @kan-bayashi
• [Enhancement] RFC: Add keep_all_data_on_mem option #999 by @r9y9
• [Enhancement] Support saving of attention weights and probability in decoding #995 by @kan-bayashi
• [Enhancement] Implement Fast Speech #848 by @kan-bayashi
• [Enhancement] Transformer Chainer #774 by @Fhrozen
• [Enhancement] Neural Machine Translation #563 by @hirofumi0810

Recipe

• [Recipe] fix bugs to make a swbd recipe run #1024 by @sw005320
• [Recipe] Add multi-speaker Transformer config in LibriTTS #1022 by @kan-bayashi
• [Recipe] Rename RESULTS to RESULTS.md #1021 by @kan-bayashi
• [Recipe] Clean LibriTTS RESULTS.md #1020 by @kan-bayashi
• [Recipe] Clean LJSPeech RESULTS.md #1019 by @kan-bayashi
• [Recipe] Update JSUT TTS RESULTS.md #1018 by @kan-bayashi
• [Recipe] Add Transformer config in JSUT #1009 by @kan-bayashi
• [Recipe] Update libri trans #949 by @hirofumi0810
• [Recipe] iwslt18 NMT recipe #937 by @hirofumi0810
• [Recipe] libri_trans NMT recipe #931 by @hirofumi0810
• [Recipe] Add fastspeech.v2 result #925 by @kan-bayashi

Documentation

• [Documentation] [Docstrings] Removing empty init files to avoid docs #1016 by @Fhrozen
• [Documentation] add egs info #1015 by @sw005320
• [Documentation] Update docstrings in espnet.nets.chainer_backend #974 by @Masao-Someki
• [Documentation] Reformat docstrings in espnet/asr #914 by @Masao-Someki
• [Documentation] Update TTS module’s docstrings and refactor some modules #898 by @kan-bayashi

Acknowledgements

Special thanks to @Fhrozen, @Masao-Someki, @ShigekiKarita, @hirofumi0810, @kamo-naoyuki, @kan-bayashi, @r9y9, @sw005320.

ESPnet Version 0.4.3

Enhancement

• [Enhancement] Use queue-freegpu.pl in all cmd.sh #1013

Documentation

• [Documentation] nbsphinx support #1003
• [Documentation] Update docstrings #994

Recipe

• [Recipe] CSJ asr1: prettify RESULTS.md #1008
• [Recipe] WSJ asr1: prettify RESULTS.md #1007

Bugfix

• [Bugfix] fix Cupy Import Error #969 #1010
• [Bugfix] Fix a bug in synthesis_wav.sh #989
• [Bugfix] Fix lm_n_average in lang_model #988

Refactoring

• [Refactoring] Remove "free-gpu" from *_train and create queue-freegpu.pl #938

CI

• [ci] reduce travis jobs #1011

Acknowledgements

Special thanks to @Fhrozen @kamo-naoyuki @Magic-Bubble @ShigekiKarita @takenori-y @Xiaofei-Wang.