55 Commits (84020a0471b9dbc8014b3326ea6747d0f7e098c1)

Author	SHA1	Message	Date
Hui Zhang	7e136d0893	support no_sync for backward; ds support accum grad	4 years ago
huangyuxin	2451a177b0	fix paddling len bug	4 years ago
huangyuxin	317ffea5e5	simplify the code	4 years ago
huangyuxin	1f050a4d01	make the code simple	4 years ago
huangyuxin	0d0b581181	add static_forward_online and static_forward_offline	4 years ago
huangyuxin	db042a2974	Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into ds2_online_export	4 years ago
huangyuxin	b585684bf4	add function: test export	4 years ago
huangyuxin	2d3b2aed05	add seed in argparse	4 years ago
huangyuxin	9068c0d4f9	Merge branch 'HEAD_1' into ds2_online	4 years ago
huangyuxin	718407b77d	add seed	4 years ago
huangyuxin	e1a2cfef7f	fix the resume bug: the lr is not related to iteration, but epoch	4 years ago
huangyuxin	718ae52e3f	add from_config function to ds2_oneline and ds2	4 years ago
huangyuxin	85d5021475	reconstruct the exp/model.py and the model.export()	4 years ago
huangyuxin	319228653e	fix some small mistakes	4 years ago
huangyuxin	61d8540451	reconstruct the export function and the run.sh in aishell and librispeech	4 years ago
huangyuxin	722c55e4c5	reconstruct the rnn state, from list to tensor	4 years ago
huangyuxin	8f062cad6b	fixed the small problems	4 years ago
huangyuxin	3fb9f6885a	complete model export for ds2_online	4 years ago
huangyuxin	e8a3913422	merge develop_ds2_online	4 years ago
huangyuxin	2537221b61	Complete the modification according to the comments ... , but still need to be unit tested	4 years ago
huangyuxin	745df04f28	complete the pipline of tiny	4 years ago
huangyuxin	6baf9f0620	跑通了deeppseech_online的流程	4 years ago
Jackwaterveg	8716386464	Update model.py	4 years ago
huangyuxin	2c8d28111a	fix some small mistakes	4 years ago
huangyuxin	5dd9e2f8ec	先不暴露出online	4 years ago
huangyuxin	4f392e28b1	complete the encoder of ds_online	4 years ago
huangyuxin	269eecb3be	新建ds2_online文件夹	4 years ago
huangyuxin	2cacbaf48e	修改了deepspeech2.py部分LSTM和GRU的代码，增加了LayerNorm	4 years ago
huangyuxin	ce1e8ab5b6	change the dir	4 years ago
Hui Zhang	b076d3e9bb	fix autolog install; only autolog in test, or will hangup	4 years ago
Jackwaterveg	ec19248f38	autoLog	4 years ago
Jackwaterveg	48e877375d	change autoLog	4 years ago
huangyuxin	d2db706384	added autolog	4 years ago
huangyuxin	3fffd57e8b	added autoLog, but gpu_util is always 0.0%	4 years ago
Haoxin Ma	d55e6b5a0a	revise from_pretrained function	4 years ago
Haoxin Ma	3a743f3717	fix pre-commit	4 years ago
Haoxin Ma	089a8ed602	fix deepspeech2/model.py and deepspeech2/config.py	4 years ago
Haoxin Ma	557427736e	move redundant params	4 years ago
Haoxin Ma	698d7a9bdb	move batch_size, work_nums, shuffle_method, sortagrad to collator	4 years ago
Haoxin Ma	6ee3033cc4	finish aishell/s0	4 years ago
Haoxin Ma	7bae32f384	revise example/ting/s1	4 years ago
Haoxin Ma	b9110af9d3	feat_dim, vocab_size	4 years ago
Haoxin Ma	c706dfec2a	fix bug	4 years ago
Haoxin Ma	279348d786	move process utt to collator	4 years ago
Haoxin Ma	a58b1cb30a	add result output	4 years ago
Haoxin Ma	f3c9f32c9a	add utt to train and test 0607	4 years ago
Haoxin Ma	c8368410e2	utt datapipeline	4 years ago
Hui Zhang	b3bc451328	remove sequnce_mask and change ds2 export audio shape to [B,T,D] (#639) ... * remove sequnce_mask * format * fix ds2 export audio shape from B,D,T to B,T,D	4 years ago
Hui Zhang	0a3a840bee	more decoding method (#618) ... * more decoding method * all decode method test scripts; result readme * exp libri confi * parallel data scripts; more mask test; need pybind11 repo * speed perturb config * libri conf test set	4 years ago
Hui Zhang	295f8bdad5	train ds2 model (#622) ... * default cmvn compute config; more log of grad clip; diff ds2 cmvn compute and conf; ds2 lr step by epoch; * fix ds2 config * fix install and egs link * sox speed pertrub shape (T, C), float64, process using int32 * fix libri ds2 scripts; add ngram and spm doc * aishell ds2 cer7.86 * fix ds2 result	4 years ago