billishyahao
|
ddf184be60
|
fix some typos
|
3 years ago |
Jackwaterveg
|
e69abc9265
|
Merge pull request #1273 from zh794390558/batch_sampler
[s2t] Fix Batch sampler set epoch
|
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 |
|
huangyuxin
|
8b63485ce3
|
fix some bug, test=asr
|
3 years ago |
|
huangyuxin
|
3e2cc898cb
|
remove default cfg and fix some bugs,test=asr
|
3 years ago |
|
huangyuxin
|
a1d8ab0f99
|
merge the develop
|
3 years ago |
|
huangyuxin
|
c907a8deda
|
change all recipes
|
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 |
|
huangyuxin
|
41eeed0450
|
add librispeech asr1
|
3 years ago |
|
huangyuxin
|
2c5902d7c5
|
rename decoding to decode
|
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 |
KP
|
d362d28d35
|
Remove logging file in cli api.
|
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 |
|
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 |
|
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 |
|
Hui Zhang
|
51d7a07c6d
|
format and fix pre-commit (#1120)
|
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
|
2189b46004
|
add tts cli
|
3 years ago |
|
huangyuxin
|
9fe0beee54
|
fix the bug: miss import after install
|
3 years ago |
|
huangyuxin
|
cea5ffe0e4
|
refactor the code
|
3 years ago |
|
huangyuxin
|
ed12db61a6
|
Separate the ctcdecoders
|
3 years ago |
|
Hui Zhang
|
0818c1601d
|
add __init__.py
|
3 years ago |
|
Junkun
|
4e31a4445d
|
eval mode
|
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 |
|
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 |
|
Junkun
|
d2fab3238b
|
fix bugs
|
3 years ago |
|
Junkun
|
cdd0845127
|
add translate function
|
3 years ago |
|
huangyuxin
|
895a086fdd
|
rename the config.feat_size and the config.vocab.size to input_size and output_size
|
3 years ago |
|
Hui Zhang
|
fe83adfbcb
|
nproc to ngpu
|
3 years ago |
|
Hui Zhang
|
789471bfca
|
test wav for u2
|
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 |
