msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity
887 Commits
15 Branches
18 Tags
153 MiB
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '794294e9cb'
${ noResults }
Commit Graph

157 Commits (794294e9cb94de25988a1f497057b1fff05a894c)

Author SHA1 Message Date
Hui Zhang 820b4db287 with all args for scheduler
5 years ago
Hui Zhang c4da9a7f3a filter key by class signature, no print tensor
5 years ago
Hui Zhang 3912c255ef support noam lr and opt
5 years ago
Hui Zhang 1cd4d4bf83 fix tiny conf and refactor optimizer and scheduler
5 years ago
Hui Zhang cc813b18d3 fix install and format code
5 years ago
huangyuxin 319228653e fix some small mistakes
5 years ago
huangyuxin 61d8540451 reconstruct the export function and the run.sh in aishell and librispeech
5 years ago
Junkun 515497ae1f refine the code
5 years ago
Junkun ac0ae57ef2 add collactor and evaluation code for ST
5 years ago
huangyuxin 722c55e4c5 reconstruct the rnn state, from list to tensor
5 years ago
huangyuxin 8f062cad6b fixed the small problems
5 years ago
Junkun 0323151912 add u2 st
5 years ago
huangyuxin 3fb9f6885a complete model export for ds2_online
5 years ago
Hui Zhang ccdfd5b342 format
5 years ago
huangyuxin e8a3913422 merge develop_ds2_online
5 years ago
huangyuxin 2f64ae6495 not change decoder
5 years ago
huangyuxin 6c484923a4 solve the conflicts
5 years ago
huangyuxin 4b5cbe9a12 ds2_online alignment, include prob_chunk_forward, prob_chunk_by_chunk_forward
5 years ago
huangyuxin fccecf9976 add strip for CUDA_VISIBLE_DEVICES
5 years ago
huangyuxin eacad8cf60 fix the bug: can not use the CPU to test the model
5 years ago
huangyuxin d398270f95 æ˜å增加了chunk_by_chunk,初步测试å通过ã
5 years ago
huangyuxin 2537221b61 Complete the modification according to the comments
5 years ago
huangyuxin 745df04f28 complete the pipline of tiny
5 years ago
huangyuxin e4ef8ed31e add the subsampling as conv
5 years ago
huangyuxin 6baf9f0620 跑通了deeppseech_online的流程
5 years ago
Jackwaterveg 8716386464
Update model.py
5 years ago
huangyuxin 2c8d28111a fix some small mistakes
5 years ago
huangyuxin 5dd9e2f8ec 先不暴露出online
5 years ago
huangyuxin 6079a2495d 把ds2中的deepspeech2.py恢复了
5 years ago
huangyuxin 66c59cdeae adding pre-commit
5 years ago
huangyuxin 7b201ba457 增加了online的模型，通过了测试，还需要搭建配套的实验流程代码
5 years ago
huangyuxin 4f392e28b1 complete the encoder of ds_online
5 years ago
huangyuxin 269eecb3be 新建ds2_online文件夹
5 years ago
huangyuxin 2cacbaf48e 修改了deepspeech2.py部分LSTM和GRU的代码，增加了LayerNorm
5 years ago
huangyuxin ce1e8ab5b6 change the dir
5 years ago
Hui Zhang fd8a4ec179
Merge pull request #729 from PaddlePaddle/fst
5 years ago
Hui Zhang ab5411ec16
Merge pull request #698 from yt605155624/thchs30_MFA
5 years ago
Hui Zhang 104743cccc TLG build pass
5 years ago
Hui Zhang b076d3e9bb fix autolog install; only autolog in test, or will hangup
5 years ago
Jackwaterveg ec19248f38 autoLog
5 years ago
Jackwaterveg 48e877375d change autoLog
5 years ago
huangyuxin d2db706384 added autolog
5 years ago
huangyuxin 3fffd57e8b added autoLog, but gpu_util is always 0.0%
5 years ago
huangyuxin fc88745782 revise load parameters
5 years ago
Hui Zhang 259781768e comment u2 model for easy understand
5 years ago
Hui Zhang 2820537fcc fix load param
5 years ago
TianYuan c0ee57d400 Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into thchs30_MFA
5 years ago
TianYuan 7d4eff2b86 add MFA example for THCHS30
5 years ago
Hui Zhang 20117d99ee fix ckpt load
5 years ago
Hui Zhang 43b52082c3
Merge pull request #629 from PaddlePaddle/align
5 years ago
Hui Zhang 6ee67785f6 fix ctc alignment
5 years ago
Hui Zhang 717fe1e4bd
Merge pull request #680 from PaddlePaddle/checkpoint
5 years ago
Haoxin Ma c0f7aac8fc revise conf/*.yaml
5 years ago
Haoxin Ma 08b6213bc8 fix private function
5 years ago
Hui Zhang 7ec623f7ae Merge branch 'develop' into align
5 years ago
Haoxin Ma 6d92417edd optimize the function
5 years ago
Hui Zhang 9b3acddd5d fix conf for new datapipe; u2 export inputspec
5 years ago
Hui Zhang 9c0b6c5bb0 fix audio shape bug for audio len
5 years ago
Haoxin Ma 16210c0587 fix bug
5 years ago
Haoxin Ma 91e70a2857 multi gpus
5 years ago
Haoxin Ma 3965dbc2c3 runtime.py
5 years ago
Hui Zhang 90788b116d more comment; fix datapipe of align
5 years ago
Hui Zhang 1e2a5887aa Merge branch 'develop' into align
5 years ago
Haoxin Ma 340e622953 fix runtime and server
5 years ago
Haoxin Ma c753b9ddf2 fix runtime.py and server.py
5 years ago
Haoxin Ma d55e6b5a0a revise from_pretrained function
5 years ago
Haoxin Ma 8af2eb073a revise config
5 years ago
Haoxin Ma 68bcc46940 save best and test on tiny/s0
5 years ago
Haoxin Ma 3652b87f33 fix
5 years ago
Haoxin Ma 3a743f3717 fix pre-commit
5 years ago
Haoxin Ma 089a8ed602 fix deepspeech2/model.py and deepspeech2/config.py
5 years ago
Haoxin Ma 557427736e move redundant params
5 years ago
Haoxin Ma 698d7a9bdb move batch_size, work_nums, shuffle_method, sortagrad to collator
5 years ago
Haoxin Ma 89a00eabeb revise deepspeech/exps/u2/model.py
5 years ago
Haoxin Ma 6ee3033cc4 finish aishell/s0
5 years ago
Haoxin Ma 7bae32f384 revise example/ting/s1
5 years ago
Haoxin Ma b9110af9d3 feat_dim, vocab_size
5 years ago
Haoxin Ma 3855522ee3 config
5 years ago
Haoxin Ma a1c6ee5ca1 merge
5 years ago
Haoxin Ma 3d5f294363 dataset
5 years ago
Blank 875139ca04
Merge branch 'develop' into spec_aug
5 years ago
Hui Zhang 1cd88d2619
Merge pull request #657 from PaddlePaddle/add_utt
5 years ago
Haoxin Ma 2b51d612dd delete _instance_reader_creator func in dataset
5 years ago
Haoxin Ma b4bda290aa fix bugs
5 years ago
Haoxin Ma c706dfec2a fix bug
5 years ago
Haoxin Ma 279348d786 move process utt to collator
5 years ago
Haoxin Ma 8781ab58cf fix export and run.sh
5 years ago
Haoxin Ma a58b1cb30a add result output
5 years ago
Haoxin Ma f3c9f32c9a add utt to train and test 0607
5 years ago
Haoxin Ma c8368410e2 utt datapipeline
5 years ago
Hui Zhang 69dfc2a5fa fix mask for bool type; fix other
5 years ago
Hui Zhang 4acaaba349 replace list zip by stack
5 years ago
Hui Zhang d05ae8eeb0 Merge branch 'develop' into align
5 years ago
Hui Zhang 34689bd1df add crf
5 years ago
Hui Zhang b3bc451328
remove sequnce_mask and change ds2 export audio shape to [B,T,D] (#639)
5 years ago
Hui Zhang 92381451fb format
5 years ago
Hui Zhang 30aba26693 add align code
5 years ago
Hui Zhang 0a7958b3f1
add tarball utils (#626)
5 years ago
Hui Zhang 0a3a840bee
more decoding method (#618)
5 years ago
Hui Zhang 295f8bdad5
train ds2 model (#622)
5 years ago