498 Commits (380afbbc5d828f81204a5b9ab9088d4491ba0b70)

Author	SHA1	Message	Date
WilliamZhang06	147018a8b4	added cli changed code, test=doc	3 years ago
lym0302	332009142b	add server demo, test=doc	3 years ago
WilliamZhang06	7ebe904e20	fixed overload , test=doc	3 years ago
Hui Zhang	60c0877e7a	Merge pull request #1472 from KPatr1ck/cli_batch ... [CLI][Logger]Add cli logger control.	3 years ago
WilliamZhang06	b8f16ac9b0	Merge branch 'develop' into server_asr	3 years ago
WilliamZhang06	da3ea7bb40	added engine type and asr inference , test=doc	3 years ago
Hui Zhang	49f80afe6a	Merge pull request #1381 from PaddlePaddle/server ... [server] speech server init version	3 years ago
lym0302	b508c4d0cb	add readme, test=doc	3 years ago
KP	d36a4ccfc8	Add cli logger control.	3 years ago
KP	94ed5969fa	Add cli logger control.	3 years ago
lym0302	42cbe313c2	improve cli code, test=doc	3 years ago
lym0302	2bf4b4521f	add cli, test=doc	3 years ago
lym0302	8fd117e4da	add cli, test=doc	3 years ago
lym0302	80b83b7434	add cli, test=doc	3 years ago
KP	7814fba07f	Update batch input.	3 years ago
KP	05288fe1c3	Update batch input and stdin input.	3 years ago
KP	1818b058aa	Support batch input in cls task.	3 years ago
WilliamZhang06	35e3be9ac8	Merge remote-tracking branch 'remote/develop' into server	3 years ago
TianYuan	ae521d3700	Update infer.py	3 years ago
lym0302	07158b2f12	move dir, test=doc	3 years ago
lym0302	76391275fc	move dir, test=doc	3 years ago
TianYuan	67ec6242c3	fix ci for waveflow, test=tts	3 years ago
TianYuan	f51097618b	Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into fix_ci_waveflow	3 years ago
TianYuan	fc8c0e3ea2	fix ci for waveflow, test=tts	3 years ago
huangyuxin	95d5274aef	fix sortagrad, test=asr	3 years ago
Hui Zhang	718c849f68	Merge pull request #1445 from yt605155624/update_train ... [TTS]init for all works in train.py when ngpu>1	3 years ago
Hui Zhang	f3ec985aaf	Merge pull request #1439 from Jackwaterveg/tipc ... [TIPC]Add tipc_benchmark of conformer	3 years ago
TianYuan	4ac7db185e	init for all works in train.py when ngpu>1, test=tts	3 years ago
Jackwaterveg	426bae3de1	Merge pull request #1440 from yt605155624/merge_datasets ... [TTS]Merge datasets, change style of docstring	3 years ago
TianYuan	2cec8f6c76	update tts cli, test=doc	3 years ago
TianYuan	9699c00769	change the docstring style from numpydoc to google, test=tts	3 years ago
huangyuxin	aefe9e93a7	add tipc benchmark of conformer	3 years ago
TianYuan	683679bec7	merge data and datasets, test=tts	3 years ago
TianYuan	7dc1f2daa3	fix some librosa bugs, test=tts	3 years ago
TianYuan	30085ac229	Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into rename_tacotron2	3 years ago
TianYuan	25347bb6a3	rename tacotron2, test=tts	3 years ago
huangyuxin	9a55783aa0	fix resample	3 years ago
Hui Zhang	dcfc32f1ec	Merge pull request #1379 from yt605155624/new_wavernn ... [TTS] add wavernn	3 years ago
TianYuan	0747600c95	[TTS]add ljspeech new tacotron2 (#1416) ... * add ljspeech new tacotron2, test=tts * update ljspeech waveflow's synthesize * add config, test=doc Co-authored-by: Hui Zhang <zhtclz@foxmail.com>	3 years ago
TianYuan	348a1a33bf	update tacotron2 voice cloning in aishell3 with new tacotron2, test=tts (#1419)	3 years ago
huangyuxin	f428ec4431	change log of cli/asr/infer	3 years ago
TianYuan	1b0c034134	update wavernn, test=tts	3 years ago
TianYuan	89e69ee10e	[TTS]fix tacotron2 dygraph to static (#1414) ... * fix tacotron2 dygraph to static , test=tts * fix tacotron2 dygraph to static , test=tts * simplify synthesize_e2e.py , test=tts	3 years ago
huangyuxin	2a42421a63	cli add ds2-librispeech offline, fix versionm, test=asr	3 years ago
Hui Zhang	4128f4d61f	fix __version__ error in develop (#1398)	3 years ago
TianYuan	001afee644	fix wavernn dygraph to static , test=tts	3 years ago
TianYuan	2844f388dc	[doc ]add tacotron2 readme (#1385) ... * add tacotron2 readme, test=doc * update changelog.md, test=doc	3 years ago
TianYuan	2071774d81	add wavernn in synthesize_e2e, test=tts	3 years ago
TianYuan	1cc7905d51	rm csmsc.py, test=tts	3 years ago
TianYuan	4c3e57a23c	align preprocess of wavernn, test=tts	3 years ago
Jackwaterveg	f49cf838a8	Update u2.py (#1378)	3 years ago
TianYuan	fb0acd40a2	add wavernn, test=tts	3 years ago
Jackwaterveg	d7222c0453	[ASR] Support CTC decoder online (#821) ... * fix the destructer problem for prefixes * unified offline and online in ctcdecoders, test=asr * rename swig_decoders to paddlespeech_ctcdecoders, test=asr * add reset_stage for ctcdecoder * fix some problems * fix ctconline * fix a bug * fix the format * fix 1xt2x	3 years ago
Jerryuhoo	f515416c4a	fix missing model choice, test=doc	3 years ago
Jerryuhoo	a22080130b	Add speedyspeech multi-speaker support for synthesize_e2e.py, test=tts	3 years ago
Hui Zhang	97db74ca60	Merge pull request #1314 from yt605155624/add_new_tacotron2 ... [TTS]Add new tacotron2	3 years ago
huangyuxin	3845804cc9	Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into Setup	3 years ago
TianYuan	96323816e9	fix yamls, change labels to stop_labels, test=tts	3 years ago
TianYuan	1bf1a876ae	Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into add_new_tacotron2, test=tts	3 years ago
TianYuan	3fd7a7790b	add typehit for updater and evaluator, test=tts	3 years ago
huangyuxin	4e31247633	refacto the code	3 years ago
TianYuan	41d24337cb	fix fastspeech2 multi speaker to static, test=tts	3 years ago
TianYuan	1a9e59612a	fix fastspeech2 multi speaker to static, test=tts	3 years ago
huangyuxin	565a63c5ef	refactor the setup in paddleaudio	3 years ago
huangyuxin	eb91ce84f9	refactor the version	3 years ago
Hui Zhang	4a133619a1	Merge pull request #1356 from Jackwaterveg/CLI ... [CLI] asr, Add Deepspeech2 online and offline model	3 years ago
Hui Zhang	d4acf4704f	Merge pull request #1350 from LittleChenCc/develop ... [ST] beam search with optimality guarantees	3 years ago
huangyuxin	ab759b16de	Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into CLI	3 years ago
huangyuxin	38edfd1a89	Add Deepspeech2 online and offline in cli	3 years ago
TianYuan	d368d57d67	fix low ips bug of speedyspeech and fastspeech2, test=tts (#1349)	3 years ago
TianYuan	9c7f0762b0	update racotron2 and transformer tts, test=tts	3 years ago
huangyuxin	8028f33b7f	synchronize the version	3 years ago
Junkun	44408e5211	sync the variable name to others	3 years ago
Junkun	f866059b74	config and formalize	3 years ago
Junkun	43aad7a018	beam search with optimality guarantees	3 years ago
Jackwaterveg	26524031d2	Merge pull request #1343 from Jackwaterveg/fix ... [ASR] Fix some bugs	3 years ago
huangyuxin	5e7e8a3e24	fix the u2 export, test=asr	3 years ago
TianYuan	a1867c20c3	fix slice bug of speedyspeech expand, test=tts (#1337)	3 years ago
Hui Zhang	ec1c88ae1a	[s2t] remove nltk (#1332)	3 years ago
TianYuan	7ae4f7221e	Update length_regulator.py	3 years ago
TianYuan	acfe2b9084	Update duration_predictor.py	3 years ago
TianYuan	caa391f461	fix speedyspeech inference, test=tts (#1322)	3 years ago
Jackwaterveg	0c4895cd0b	mv the ctcdecoders to third_part (#1313)	3 years ago
TianYuan	8f507ba4ba	Merge pull request #1302 from jerryuhoo/develop ... [TTS] Add support for finetuning speedyspeech	3 years ago
Jerryuhoo	111a452378	Fix the code format, test=tts	3 years ago
TianYuan	89e988a69e	add csmsc tacotron2, test=tts	3 years ago
TianYuan	c088b9a304	add csmsc tacotron2	3 years ago
huangyuxin	fe1dc9d211	refactor the cli/st, test=st	3 years ago
TianYuan	27bb76bdb9	fix tone_sandhi of yi, test=tts	3 years ago
Jerryuhoo	be99807d61	Add durations to gen_gta_mel.py inference	3 years ago
KP	52a8b2f320	Add ECAPA_TDNN. (#1301)	3 years ago
Jerryuhoo	fcc34e3e95	[tts] add gen_gta_mel.py for finetuning speedypeech, test=tts	3 years ago
Jackwaterveg	010aa65b2b	[cli] asr - support English, decode_metod and unified config (#1297) ... * fix config, test=asr * fix config, test=doc_fix * add en and decode_method for cli/asr, test=asr * test=asr * fix, test=doc_fix	3 years ago
KP	c09466ebbe	Add ECAPA_TDNN. (#1295)	3 years ago
TianYuan	fb238d83f4	update vctk voc1, test=tts (#1294)	3 years ago
TianYuan	73dc0e2535	fix_ning	3 years ago
billishyahao	ddf184be60	fix some typos	3 years ago
TianYuan	318cc9e539	Merge branch 'develop' into develop	3 years ago
Jackwaterveg	e69abc9265	Merge pull request #1273 from zh794390558/batch_sampler ... [s2t] Fix Batch sampler set epoch	3 years ago
KP	a810cd4e5c	Add cli logging. (#1274)	3 years ago
Jerryuhoo	d6e9b76e76	change link_wav.py path, test=tts	3 years ago
Jerryuhoo	c94f346207	move link_wav.py to paddlespeech/t2s/exps/gan_vocoder/ ... move link_wav.py to paddlespeech/t2s/exps/gan_vocoder/ so that different vocoders can use one script.	3 years ago
Jerryuhoo	e239ee1cd2	add multi-speaker support for finetuning hifigan vocoder	3 years ago
huangyuxin	07d457859d	use pre-commit, test=doc_fix	3 years ago
Hui Zhang	45832f6770	fix default dist_samlper to False	3 years ago
Hui Zhang	3a2db414e6	format code	3 years ago
Hui Zhang	6f651d762e	fix batch sampler set_epoch when epcoh start	3 years ago
TianYuan	680eac02b9	[tts]Update mb melgan (#1272) ... * update mb melgan * update mb melgan, test=tts	3 years ago
TianYuan	98ce69d0aa	Merge pull request #1259 from jerryuhoo/develop ... [TTS]Add multi-speaker support for the SpeedySpeech model	3 years ago
huangyuxin	ffadbe22a7	merge the develop, test=asr	3 years ago
JiehangXie	bdc48114a4	Update text_normlization.py	3 years ago
JiehangXie	d88ceef7bc	Fix punctuation bug ... 修复顿号和英文冒号停顿和分句的问题	3 years ago
huangyuxin	8b63485ce3	fix some bug, test=asr	3 years ago
JiehangXie	6065b1b607	Fix punctuation bug ... 修复顿号和英文冒号停顿和分句的问题	3 years ago
Jerry	0719698118	Merge branch 'develop' into develop	3 years ago
AdamBear	36c9eaa437	Cache the TextFeaturizer instance for infer speed improvement. (#1260)	3 years ago
huangyuxin	3e2cc898cb	remove default cfg and fix some bugs,test=asr	3 years ago
Jerryuhoo	2dccd5315d	remove useless "other" dataset	3 years ago
Jerryuhoo	f191d0b022	change speaker embedding position ... Change speaker embedding position into the encoder.	3 years ago
Jerryuhoo	11991b6d35	add multi-speaker support for speedyspeech	3 years ago
huangyuxin	a1d8ab0f99	merge the develop	3 years ago
huangyuxin	c907a8deda	change all recipes	3 years ago
TianYuan	b9a55262f1	Update fastspeech2.py	3 years ago
Hui Zhang	c81a3f0f83	[s2t] DataLoader with BatchSampler or DistributeBatchSampler (#1242) ... * batchsampler or distributebatchsampler * format	3 years ago
Junkun Chen	420709e5ce	[st] Distributed sampler and new dataloader with MIMO (#1239) ... * update timit result, test=doc_fix * result update * fix bug * add triplet loader * empty preprocess file * sync to u2, updating * sync to u2 config * fix bugs * code refine * update config * customize decoding batch size * update optimizer and lr scheduler * minor * minor * minor * fix bugs of refs * minor * distributed sampler * minor * refine the loader	3 years ago
TianYuan	fbe3c05137	add style_melgan and hifigan in tts cli, test=tts (#1241)	3 years ago
TianYuan	a232cd8b12	Update fastspeech2.py	3 years ago
huangyuxin	41eeed0450	add librispeech asr1	3 years ago
huangyuxin	fb6d1e2c11	merge the develop	3 years ago
huangyuxin	2c5902d7c5	rename decoding to decode	3 years ago
TianYuan	42c109216d	[tts]add style melgan pretraied model (#1228) ... * add style melgan pretraied model * add style melgan pretraied model, test=tts Co-authored-by: Hui Zhang <zhtclz@foxmail.com>	3 years ago
Hui Zhang	bb2a370b23	[asr] remove useless conf of librispeech (#1227) ... * remve useless conf * format code * update conf * update conf * update conf	3 years ago
huangyuxin	c40b6f4062	refactor the train and test config,test=asr	3 years ago
TianYuan	5692b0ff04	fix log for t2s (#1219)	3 years ago
TianYuan	b031ee43c4	Merge pull request #1215 from yt605155624/refactor_punc ... [text]Refactor punc	3 years ago
TianYuan	e1798e1eeb	update	3 years ago
KP	d362d28d35	Remove logging file in cli api.	3 years ago
TianYuan	15b8904fa1	refactor punc	3 years ago
JiehangXie	927c9bbdb6	Fix a bug when sentence inputed contain English words	3 years ago
KP	1632af7706	Update examples/esc50. (#1203)	3 years ago
Jerryuhoo	3cbfd7bf35	Add speaker embedding and speaker id for style fastspeech2 inference	3 years ago
Hui Zhang	db121226b8	clean aishell asr1 conf & compare ctc loss with torch and warpctc_pytorch (#1191)	3 years ago
Hui Zhang	d852aee2ff	[asr] logfbank with dither (#1179) ... * fix logfbank dither * format	3 years ago
KP	9ec2bc8e2e	Update README. test=doc_fix	3 years ago
Jackwaterveg	879857332d	[version]add paddlespeech.__version__ (#1166) ... * add paddlespeech.__version__ * version 0.1.0 is ready	3 years ago
TianYuan	19ef7210a0	[TTS]Add hifigan (#1097) ... * add hifigan * add hifigan * integrate synthesize synthesize_e2e, inference for tts, test=tts * add some python files, test=tts * update readme, test=doc_fix	3 years ago
TianYuan	675cff258b	[TTS]fix praatio version, test=tts (#1158) ... * fix praatio version, test=tts * fix praatio version, test=tts	3 years ago
Jackwaterveg	e9748faa71	[Cli]optimize the cli, add --yes, and delete transformer_aishell (#1154) ... * optimize the cli/asr,test=asr * test=doc_fix	3 years ago
Jackwaterveg	2bccde3def	update the version of ctcdecoders and feat,test=doc_fix (#1155)	3 years ago
Jackwaterveg	0151f2463f	fix bug of pad_sequence in u2,test=asr (#1153)	3 years ago
Jackwaterveg	68164dd39f	[asr]rename test_hub to test_wav (#1132) ... * add the readme, librispeech_asr1 * fix the test_hub * test=asr	3 years ago
KP	16d6ed3842	Add automatic_video_subtitiles demo.	3 years ago
KP	7394a18732	Add default arguments in cls python api.	3 years ago
TianYuan	f9efbf3063	Update generate_lexicon.py	3 years ago
Jackwaterveg	5b446f6321	[Config]clear the u2 decode config for asr (#1107) ... * clear the u2 decode config * rename the vocab_filepath and cmvn_path	3 years ago
KP	074559fe90	[CLI][Demo][Text]Refactor punctuation_restoration. (#1013) ... * Refactor punctuation_restoration. * Add text cli and punc demo.	3 years ago
Hui Zhang	51d7a07c6d	format and fix pre-commit (#1120)	3 years ago
TianYuan	5f0f76f249	add eval() for inference model (#1114)	3 years ago
TianYuan	59e4a34071	Merge branch 'develop' of github.com:PaddlePaddle/PaddleSpeech into tts_cli	3 years ago
TianYuan	3de4130dfc	update am name	3 years ago
TianYuan	9db1710ba7	add conformer demos (#1108)	3 years ago
TianYuan	3fe75f833d	Merge pull request #1109 from yt605155624/tts_cli ... [cli]update voc name	3 years ago
TianYuan	ca12a83d5a	update voc name	3 years ago
TianYuan	965a57ef0e	Update README.md	3 years ago
Jackwaterveg	9e31a606d1	set default encoding utf8 for win (#1101) ... Co-authored-by: KP <109694228@qq.com>	3 years ago
Hui Zhang	764a5d4271	Merge branch 'develop' into ctc	3 years ago
Hui Zhang	b1c80c45e0	remove ctc grad norm type in config	3 years ago
huangyuxin	1d4002409f	separate the sox and soxbindings with the requirements	3 years ago
TianYuan	df5fe035e5	Update README.md	3 years ago
TianYuan	a6e0a69da8	Merge pull request #1095 from KPatr1ck/demo ... [Demo]Add tts demo.	3 years ago
TianYuan	963e906f56	Merge pull request #1068 from yt605155624/add_style_melgan ... [TTS]add style_melgan	3 years ago
KP	1909f2f620	Add tts demo.	3 years ago
KP	3701fba0be	Update download logic and fix README typos.	3 years ago
TianYuan	f701882b66	update add_style_melgan	3 years ago
gongel	dc60aeb8c2	format	3 years ago
gongel	31510d088c	refactor: rm kaldi_io	3 years ago
TianYuan	2189b46004	add tts cli	3 years ago
KP	70a8a75476	Add st demo.	3 years ago
Hui Zhang	6dedb63e8b	Merge pull request #1087 from Jackwaterveg/setup ... [ctcdecoders] Separate the ctcdecoders	3 years ago
huangyuxin	9fe0beee54	fix the bug: miss import after install	3 years ago
huangyuxin	cea5ffe0e4	refactor the code	3 years ago
gongel	20d88ec673	refactor: update params/input/output/namestyle	3 years ago
KP	6c1e6e7876	Update recommended model to cnn14 and argument name in __call__.	3 years ago
huangyuxin	ed12db61a6	Separate the ctcdecoders	3 years ago
KP	0b7e0d1e2e	Update tags of pretrained_models.	3 years ago
KP	d08b824d72	Update README.	3 years ago
KP	61e39daccc	Optimize model init.	3 years ago
KP	528c70e515	Remove TODO.	3 years ago
KP	b072453ca8	Fix decompressing problem.	3 years ago
KP	29da318379	Add audio classification cli.	3 years ago
gongel	f5c61ced28	feat: add st cli	3 years ago
Hui Zhang	0818c1601d	add __init__.py	3 years ago
TianYuan	7b2ecb6eed	add style_melgan, test=tts	3 years ago
Hui Zhang	03678c08c5	Merge branch 'develop' into fix_cli	3 years ago
huangyuxin	1b57d05d1b	rm the os.chdir in cli asr	3 years ago
TianYuan	aead853b1d	Update zh_frontend.py	3 years ago
huangyuxin	021311c76b	add transformer to cli infer	3 years ago
TianYuan	a070524d37	Merge branch 'develop' of github.com:PaddlePaddle/PaddleSpeech into add_style_melgan, test=tts	3 years ago
TianYuan	dd36eafe34	add style_melgan	3 years ago
KP	54cf048b2a	Merge remote-tracking branch 'update_stream/develop' into cli	3 years ago
huangyuxin	a258a34ec0	revise the convert pcm	3 years ago
Jackwaterveg	8ec576f477	Update infer.py	3 years ago
huangyuxin	b0356ae489	revise	3 years ago
huangyuxin	957f2e3a1c	revise	3 years ago
huangyuxin	aee530af27	revise the sample rate	3 years ago
Junkun	4e31a4445d	eval mode	3 years ago
KP	a19e51d7da	Update python api.	3 years ago
KP	e0642ffc77	Update doc strings.	3 years ago
huangyuxin	90d648a601	support using by __call__	3 years ago
huangyuxin	aecb5f567c	Merge branch 'tmp' into 1048	3 years ago
KP	44e9b032d5	Update inputs and outputs of executor.	3 years ago
huangyuxin	3fadcde5e2	revise the asr infer.py	3 years ago
Hui Zhang	4823892169	Merge pull request #1058 from Jackwaterveg/benchmark ... [benchmark]fix the benchmark	3 years ago
Junkun	3a14b82844	minor	3 years ago
Junkun	f50a2ab4ca	fix bugs	3 years ago
huangyuxin	cb383a39c3	fix the benchmark	3 years ago
huangyuxin	d0bf506fee	fix the load checkpoint	3 years ago
KP	1707244472	Update device usage.	3 years ago
KP	000294132c	Rename s2t to asr.	3 years ago
huangyuxin	43f4d47bfa	add the call in infer.py	3 years ago
Hui Zhang	39228864bb	format code	3 years ago
Hui Zhang	d395c2b8e3	jsonlines reade manifest file	3 years ago
Hui Zhang	7554b6107a	using visualdl; fix read_manifest	3 years ago
huangyuxin	cdc8520969	add the infer	3 years ago
KP	c94ebdc52c	Add python api for executor.	3 years ago
Junkun	d2fab3238b	fix bugs	3 years ago
Junkun	cdd0845127	add translate function	3 years ago
KP	e9798498d6	Update asr inference in paddlespeech.cli.	3 years ago
huangyuxin	895a086fdd	rename the config.feat_size and the config.vocab.size to input_size and output_size	3 years ago
KP	4d39a7746e	Add paddlespeech.cli.	3 years ago
KP	98f0806353	Add paddlespeech.cli.	3 years ago
TianYuan	6e3257ab8a	Create __init__.py	3 years ago
TianYuan	022f1ce8e9	Merge pull request #1040 from yt605155624/fix_frontend ... [TTS]update text frontend	3 years ago
TianYuan	a861e56e91	rm space for pure Chinese	3 years ago
TianYuan	dad1cbbcd6	update text frontend	3 years ago
KP	6e1ac1cc15	Add paddlespeech.cls and esc50 example.	3 years ago
KP	33f0e7622c	Add paddlespeech.cls and esc50 example.	3 years ago
KP	2c531d78ac	Add paddlespeech.cls and esc50 example.	3 years ago
KP	bdb3ce23ee	Add paddlespeech.cls and esc50 example.	3 years ago
KP	1189117784	Add paddlespeech.cls and esc50 example.	3 years ago
Hui Zhang	2bbfdbae91	Merge pull request #1015 from yt605155624/fs2_conformer ... [TTS]fastspeech2 conformer	3 years ago
TianYuan	b0a1d8ab60	fix base	3 years ago
TianYuan	469329221b	refactor encoder, rm old code	3 years ago
Hui Zhang	fe83adfbcb	nproc to ngpu	3 years ago
Hui Zhang	789471bfca	test wav for u2	3 years ago
TianYuan	bc0dd51149	Merge branch 'develop' of github.com:PaddlePaddle/PaddleSpeech into HEAD	3 years ago
Jackwaterveg	09931d2ccc	Merge pull request #1019 from zh794390558/feat ... [bugfix] Kaldi Feature using dither in train	3 years ago
huangyuxin	8aebfeac81	fix the prc-commit	3 years ago
Hui Zhang	56480e1033	fix format	3 years ago
Hui Zhang	7ec0ed4aaf	kaldi feat dither when train	3 years ago