Hui Zhang
|
789471bfca
|
test wav for u2
|
3 years ago |
huangyuxin
|
50cf88b7f1
|
Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into doc
|
3 years ago |
Jackwaterveg
|
563568a2b8
|
Merge pull request #1031 from yt605155624/fix_docs
[TTS]update ipynb, add eval loss
|
3 years ago |
TianYuan
|
7d3985bff9
|
update table
|
3 years ago |
|
TianYuan
|
f3fbce005e
|
update ipynb, add eval loss
|
3 years ago |
|
Hui Zhang
|
042bbe5ed5
|
update ds2 offline result
|
3 years ago |
|
TianYuan
|
bc0dd51149
|
Merge branch 'develop' of github.com:PaddlePaddle/PaddleSpeech into HEAD
|
3 years ago |
|
Hui Zhang
|
b119cfe06d
|
fix preprocess of libri asr2
|
3 years ago |
|
huangyuxin
|
649fcc4c16
|
revise some programming mistakes
|
3 years ago |
|
huangyuxin
|
2274a07235
|
Merge branch 'develop' into doc
|
3 years ago |
|
Jackwaterveg
|
04cfcd96ca
|
Merge pull request #1023 from zh794390558/dict
[asr] put vocab into data/lang_char
|
3 years ago |
|
Jackwaterveg
|
88d4208430
|
Merge pull request #1022 from yt605155624/fix_tts_doc
[TTS]fix readme
|
3 years ago |
|
TianYuan
|
f5a3b21f45
|
fix readme
|
3 years ago |
|
Hui Zhang
|
cdeb5cf6b6
|
update librispeech transformer result
|
3 years ago |
|
Jackwaterveg
|
09931d2ccc
|
Merge pull request #1019 from zh794390558/feat
[bugfix] Kaldi Feature using dither in train
|
3 years ago |
|
huangyuxin
|
f765171111
|
add the readme for the run.sh in aishsll asr1
|
3 years ago |
|
Hui Zhang
|
4f54e36294
|
vocab into data/lang_char
|
3 years ago |
gongel
|
3a31547516
|
refactor: rename t1 to st1
|
3 years ago |
|
gongel
|
d4ee5916b1
|
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into ted_en_zh_t0
|
3 years ago |
|
gongel
|
7cef93a6f4
|
refactor: update
|
3 years ago |
|
huangyuxin
|
8aebfeac81
|
fix the prc-commit
|
3 years ago |
|
Hui Zhang
|
56480e1033
|
fix format
|
3 years ago |
|
TianYuan
|
4537e900ef
|
Update README.md
|
3 years ago |
|
Jackwaterveg
|
524658a04f
|
Merge pull request #1018 from yt605155624/fix_url
[TTS]fix urls
|
3 years ago |
|
TianYuan
|
2d808a3c64
|
fix urls
|
3 years ago |
|
Hui Zhang
|
6750770e54
|
Merge pull request #1012 from zh794390558/datapipe
[asr] independent dataloader
|
3 years ago |
|
gongel
|
5b5c73f9bb
|
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into ted_en_zh_t0
|
3 years ago |
|
TianYuan
|
bdd2fb8f93
|
add aishell3/vc1 readme, add csmsc/voc1 readme
|
3 years ago |
|
Hui Zhang
|
2f4f744071
|
rename asr egs
|
3 years ago |
|
Hui Zhang
|
2ba3f00bbd
|
Merge branch 'develop' into datapipe
|
3 years ago |
|
Hui Zhang
|
b57b865989
|
rename egs
|
3 years ago |
|
Hui Zhang
|
b944418d6f
|
new format data support ds2/st
|
3 years ago |
|
Hui Zhang
|
02c7ef3198
|
format data support multi output
|
3 years ago |
|
Hui Zhang
|
e79e00a6b2
|
pack model
|
3 years ago |
|
Hui Zhang
|
0defc658e1
|
update aishell/librispeech transformer result; wenetspeech pretrain conformer result
|
3 years ago |
|
TianYuan
|
4370c5cfa6
|
Merge branch 'develop' of github.com:PaddlePaddle/PaddleSpeech into fs2_conformer
|
3 years ago |
|
Hui Zhang
|
a7858551b7
|
add utt2spk for all dataset
|
3 years ago |
|
Hui Zhang
|
638b96bf07
|
check if cmvn_file in config for u2
|
3 years ago |
|
TianYuan
|
ea81c772ce
|
Merge pull request #1010 from zh794390558/statis
[asr]disable export for u2
|
3 years ago |
|
Hui Zhang
|
a87ba13d93
|
disable export for u2
|
3 years ago |
|
Hui Zhang
|
c354e9154b
|
Merge pull request #1003 from yt605155624/fs2_ge2e
[TTS]add fastspeech2 voice cloning in aishell3
|
3 years ago |
|
TianYuan
|
133ee7db0b
|
rename num_speakers
|
3 years ago |
|
TianYuan
|
3d5e078c91
|
add conformer
|
3 years ago |
|
TianYuan
|
a97c7b5206
|
rename spembs
|
3 years ago |
|
gongel
|
9f42ec4bc2
|
feat: add ted_en_zh t1
|
3 years ago |
|
Hui Zhang
|
b9790d03f2
|
add wenetspeech egs
|
3 years ago |
|
Hui Zhang
|
171fa353ee
|
refactor libri s2 conf
|
3 years ago |
|
Hui Zhang
|
26258949ab
|
Merge pull request #995 from yt605155624/mbmelgan_fine
[TTS]add multi-band melgan finetune scripts
|
3 years ago |
|
TianYuan
|
8d025451de
|
add fastspeech2 voice cloning in aishell3
|
3 years ago |
|
TianYuan
|
c5c9f19091
|
rename to gen_gta_mel.py, remove stats compute when gen fintune data
|
3 years ago |
Zeyu Chen
|
4a28751df0
|
Formalize the terms in README
|
3 years ago |
|
Hui Zhang
|
3046a22719
|
aishell support utt2spk
|
3 years ago |
|
TianYuan
|
b9dc017011
|
Update synthesize_e2e.sh
|
3 years ago |
|
TianYuan
|
c4234b3ecd
|
Update synthesize.sh
|
3 years ago |
|
TianYuan
|
a6ac497f8e
|
add multi-band melgan finetune scripts
|
3 years ago |
|
TianYuan
|
39400e5ee8
|
Update synthesize.sh
|
3 years ago |
|
Hui Zhang
|
bc4e2e4ee2
|
Merge pull request #982 from Jackwaterveg/develop
Optimizer the hips while downloading the LM
|
3 years ago |
|
huangyuxin
|
754c0b560b
|
optimizer the hips of downloading LM
|
3 years ago |
|
TianYuan
|
30d09b411d
|
fix style_syn, replace DeepSpeech with PaddleSpeech in readme
|
3 years ago |
Mingxue-Xu
|
f26db2e762
|
Update README.md
|
3 years ago |
|
Mingxue-Xu
|
6641b97d44
|
Update README.md
|
3 years ago |
|
TianYuan
|
0bc9450c51
|
Merge branch 'develop' of github.com:PaddlePaddle/DeepSpeech into fix_docs
|
3 years ago |
|
Hui Zhang
|
81598e6ff0
|
default gpu 0 for scripts
|
3 years ago |
Junkun
|
7c8843448c
|
add word reward into beam search.
|
3 years ago |
|
Jackwaterveg
|
67551c6557
|
Add notes in example/aishell/s0/run.sh
|
3 years ago |
|
Hui Zhang
|
9a71c091c5
|
remove debug info and format code
|
3 years ago |
|
Hui Zhang
|
8b0e344c69
|
fix logfbank using PCM16
|
3 years ago |
|
Hui Zhang
|
d62092ac28
|
fix specaug param
|
3 years ago |
|
TianYuan
|
2931903add
|
Rename READEME.md to README.md
|
3 years ago |
|
huangyuxin
|
61ad2c87a7
|
update the ds2 online conf
|
3 years ago |
|
Hui Zhang
|
7b3a901b08
|
more conf with preprocess.yaml
|
3 years ago |
|
Hui Zhang
|
44743622d4
|
filter example; cmvn stride and window int; libri/s1 conf
|
3 years ago |
|
Hui Zhang
|
56d06f2aaf
|
Merge pull request #968 from yt605155624/merge_paddlespeech
[TTS] change nprocs to ngpu
|
3 years ago |
|
Hui Zhang
|
6a7e0265cd
|
add josn global cmvn
|
3 years ago |
|
TianYuan
|
bacdf5756b
|
Merge remote-tracking branch 'origin/develop' into merge_paddlespeech
|
3 years ago |
|
Hui Zhang
|
69055698a2
|
transformer using batch data loader
|
3 years ago |
|
TianYuan
|
35c37ace17
|
change nprocs to ngpu, add aishell3/voc1
|
3 years ago |
|
huangyuxin
|
d647cde870
|
change the lm dataset dir
|
3 years ago |
|
Hui Zhang
|
3f3442b98a
|
remove useless third lib
|
3 years ago |
|
Hui Zhang
|
aba37810ff
|
update BZNSYP.rar link
|
3 years ago |
|
Hui Zhang
|
e2bcaee4f1
|
merge deepspeech, parakeet and text_processing into paddlespeech
|
3 years ago |
|
Jackwaterveg
|
782b0ddceb
|
Merge pull request #957 from PaddlePaddle/ds2_offline
revert ds2 offline rnn bw_cell to fw_cell which loss can be 5.73
|
3 years ago |
|
Hui Zhang
|
2fa681237f
|
Merge pull request #955 from Jackwaterveg/fix
fix the run_test in test_export
|
3 years ago |
|
Hui Zhang
|
4ce4e7926e
|
revert ds2 offline rnn bw_cell to fw_cell which loss can be 5.73, but is not the birnn
|
3 years ago |
|
huangyuxin
|
b966bb8a31
|
fix the run_test in test_export
|
3 years ago |
|
Hui Zhang
|
980944dab1
|
Merge pull request #952 from Jackwaterveg/dev_transformerLM
Add the feature: caculating the perplexity of transformerLM
|
3 years ago |
|
Hui Zhang
|
04d84a87ae
|
Merge pull request #948 from yt605155624/fs2_tostatic
fix fastspeech2 to static
|
3 years ago |
|
Hui Zhang
|
1372a08813
|
Merge pull request #953 from Jackwaterveg/fix_bug
[Bug fix] fix the bug of 'dev/null' and the test_export
|
3 years ago |
|
TianYuan
|
b68c9c05c4
|
fix fs2 inference bug
|
3 years ago |
|
huangyuxin
|
d64f6e9ea5
|
Add the feature: caculating the perplexity of transformerLM
|
3 years ago |
|
Jackwaterveg
|
8741da5a68
|
Update README.md
|
3 years ago |
|
huangyuxin
|
542ee3f070
|
add the model description in 1xt2x doc
|
3 years ago |
|
huangyuxin
|
02083cdbd6
|
fix the bug of 'dev/null' and the test_export
|
3 years ago |
|
TianYuan
|
fc8a7a152e
|
Merge pull request #951 from yt605155624/add_mbmelgan
[TTS] add global init for multi band melgan
|
3 years ago |
|
TianYuan
|
d3d9f83594
|
add global init for multi band melgan to avoid large output in the begin
|
3 years ago |
|
TianYuan
|
79e7a4d44e
|
align ouput of dygraph and static graph
|
3 years ago |
|
Hui Zhang
|
28519c1f44
|
Merge pull request #949 from Jackwaterveg/develop
fix the bug of chooing dataloader, remove the log of downloads lm, ch…
|
3 years ago |
|
huangyuxin
|
e66da76db9
|
fix the bug of chooing dataloader, remove the log of downloads lm, change the epoch in tiny
|
3 years ago |
|
TianYuan
|
9125d71a81
|
fix pwg inference
|
3 years ago |
|
TianYuan
|
36d60a717e
|
Merge branch 'develop' of github.com:PaddlePaddle/DeepSpeech into add_mbmelgan
|
3 years ago |
|
TianYuan
|
88668513b1
|
fix mv writer to visualdl in train
|
3 years ago |
|
TianYuan
|
670a68ad95
|
fix textfrontend readme, fix imgs link
|
3 years ago |
|
TianYuan
|
950d17cbcf
|
Merge branch 'develop' of github.com:PaddlePaddle/DeepSpeech into add_mbmelgan
|
3 years ago |
|
TianYuan
|
41526ca1b8
|
Merge branch 'develop' of github.com:PaddlePaddle/DeepSpeech into fix_docs
|
3 years ago |
|
TianYuan
|
3f9e30c9b3
|
refactor docs
|
3 years ago |
|
TianYuan
|
304d71747a
|
Merge pull request #939 from Jackwaterveg/doc
fix the doc
|
3 years ago |
|
huangyuxin
|
cef36521f9
|
fix the doc
|
3 years ago |
|
Hui Zhang
|
0812a3df20
|
add more join ctc decode conf
|
3 years ago |
|
Hui Zhang
|
8370604084
|
Merge pull request #936 from PaddlePaddle/fix_lm
[asr] fix egs of transformer lm usage
|
3 years ago |
|
Hui Zhang
|
e4852e3bf9
|
Merge pull request #934 from yt605155624/fix_readme
[TTS]fix link in readme
|
3 years ago |
|
Hui Zhang
|
c89820e7b2
|
fix egs of transformer lm usage
|
3 years ago |
|
TianYuan
|
6dbcd7720d
|
add csmsc mb melgan example
|
3 years ago |
|
TianYuan
|
02055eb26a
|
fix link in readme
|
3 years ago |
|
Hui Zhang
|
b878027c9a
|
format code
|
3 years ago |
|
Hui Zhang
|
8cda812857
|
Merge branch 'develop' into join_ctc
|
3 years ago |
|
Hui Zhang
|
b7bdaf6f8f
|
add lm conf and load
|
3 years ago |
|
TianYuan
|
20226b4fdd
|
fix benchmark and chain, add parse_options in run.sh, move tacotron2_ge2e into voice_cloning
|
3 years ago |
|
Hui Zhang
|
8f869b4c1f
|
update gitignore
|
3 years ago |
|
Hui Zhang
|
a107b75bac
|
transform; librispeech/s2 data process ok
|
3 years ago |
|
TianYuan
|
2e9d9dc9a7
|
Merge branch 'develop' of github.com:PaddlePaddle/DeepSpeech into merge_parakeet
|
3 years ago |
|
TianYuan
|
3ce5dff460
|
refactor parakeet examples
|
3 years ago |
|
Hui Zhang
|
614a004c37
|
update librispeech/s2 result
|
3 years ago |
|
Hui Zhang
|
a37cfbfb96
|
add fbank/pitch conf
|
3 years ago |
|
Hui Zhang
|
7509dc4056
|
update path and flac
|
3 years ago |
|
Hui Zhang
|
871fc5b70d
|
more utils to support kaldi/espnet data preocess
|
3 years ago |
|
Hui Zhang
|
c5f6692191
|
update lirbi s2 result
|
3 years ago |
|
Hui Zhang
|
12f788dd0e
|
Merge branch 'develop' into join_ctc
|
3 years ago |
|
Hui Zhang
|
7cfb3334e3
|
Merge pull request #927 from PaddlePaddle/nn_ctc
[asr] not change ctc grad norm manually
|
3 years ago |
|
Hui Zhang
|
dfd80b3aa2
|
recog into decoders, format code
|
3 years ago |
|
Hui Zhang
|
a4e27da64b
|
decoder with ctc prefix score
|
3 years ago |
|
Hui Zhang
|
7d54ee4d1d
|
ctc_grad_norm_type by null
|
3 years ago |
|
Hui Zhang
|
30499a7654
|
not change ctc grad manual
|
3 years ago |
|
Hui Zhang
|
190f4cc4bc
|
update u2 result; fix test.sh
|
3 years ago |
|
huangyuxin
|
b1a90d4d7a
|
add hub for s1 in aishell and librispeech
|
3 years ago |
|
Hui Zhang
|
8539689b15
|
u2 kaldi wer4p0
|
3 years ago |
|
Hui Zhang
|
f55267f2b3
|
fix img link; rsl format;
|
3 years ago |
|
huangyuxin
|
bfda49bf40
|
fix the bug of benchmark after merge the parakeet, add the condition of using kaldi in aishll s1
|
3 years ago |
|
Hui Zhang
|
fa5531c03e
|
Merge pull request #908 from PaddlePaddle/speech
[TTS] merge parakeet repo into deepspeech
|
3 years ago |
|
Hui Zhang
|
b079577e08
|
merge parakeet repo into deepspeech
|
3 years ago |
|
Hui Zhang
|
50b2114b3b
|
fix error condition
|
3 years ago |
|
Hui Zhang
|
feaf71d468
|
u2 kaldi mutli process test with batchsize one
|
3 years ago |
|
Jackwaterveg
|
aaa87698c4
|
Merge pull request #906 from PaddlePaddle/rsl
update librispeech conformer result
|
3 years ago |
|
Hui Zhang
|
b34da366ee
|
update librispeech conformer result
|
3 years ago |
|
Hui Zhang
|
302afed42a
|
update librispeech conformer transformer config
|
3 years ago |
|
Jackwaterveg
|
20488c56bc
|
Merge pull request #885 from PaddlePaddle/exp
compute cmvn before build vocab
|
3 years ago |
|
Hui Zhang
|
8ebd4245d7
|
fix detoken for char
|
3 years ago |
|
Hui Zhang
|
b10af1688c
|
update librispeech transformer test w/o length filter of test clean
|
3 years ago |
|
Hui Zhang
|
13a4bee8be
|
using simple test for multi decode type, and gpu
|
3 years ago |
|
Junkun
|
75bb1c0444
|
update timit result
|
3 years ago |
|
Hui Zhang
|
eef8847a82
|
compute cmvn before build vocab
|
3 years ago |
|
Hui Zhang
|
f5ec6e34c6
|
disable __pycache__
|
3 years ago |
|
Hui Zhang
|
37563d975e
|
ds2 model_type more info
|
3 years ago |
|
Hui Zhang
|
81f89c53e6
|
Merge pull request #872 from Jackwaterveg/Hub
change test chain and g2p
|
3 years ago |
|
Hui Zhang
|
d05baeb6b0
|
update ted zh en
|
3 years ago |
|
huangyuxin
|
f5159ba6bc
|
g2p
|
3 years ago |
|
Hui Zhang
|
251d32a609
|
fix timit scripts; reader filtype case;
|
3 years ago |
|
Junkun
|
46df01151f
|
Merge branch 'develop' of https://github.com/LittleChenCc/DeepSpeech into develop
|
3 years ago |
|
Junkun
|
a0c94209e2
|
update the result of timit
|
3 years ago |
|
Hui Zhang
|
4745e15ece
|
tiny run w cpu
|
3 years ago |
|
Hui Zhang
|
3e37cef8e1
|
fix test.sh opts
|
3 years ago |
|
Hui Zhang
|
b7b1bda34f
|
test refactor collator
|
3 years ago |
|
Junkun
|
c32cb734a6
|
update the result of TED-EN-ZH
|
3 years ago |
|
huangyuxin
|
1a46125175
|
add bin for hub
|
3 years ago |
|
Jackwaterveg
|
4b225b7602
|
Merge pull request #858 from PaddlePaddle/ctc
ctc using nn.Dropout; ds2 libri vald batch_size / 4
|
3 years ago |
|
Hui Zhang
|
9abf03bb6b
|
fix libri s1 transformer config
|
3 years ago |
|
Hui Zhang
|
88a198972f
|
Merge pull request #851 from Jackwaterveg/release_model
Optimize the 1xt2x code
|
3 years ago |
|
huangyuxin
|
d9a9126496
|
fix the run.sh in g2p/zh
|
3 years ago |
|
huangyuxin
|
30b3e237e2
|
optimize the 1xt2x
|
3 years ago |
|
huangyuxin
|
285e0c9cad
|
merge the change
|
3 years ago |
|
Hui Zhang
|
8e16315ada
|
librispeech s1 support multi process decode and sclite
|
3 years ago |
|
Hui Zhang
|
20178e0e09
|
librispeech s1 support sclite and multi process decode
|
3 years ago |
|
Hui Zhang
|
f29caf8dee
|
refactor ds 1.x exp
|
3 years ago |
|
Hui Zhang
|
9abe33b4bd
|
add score_sclite
|
3 years ago |
|
Hui Zhang
|
c6e8a33b73
|
fix set_device; more utils; args.opts support multi same name
|
3 years ago |
|
huangyuxin
|
264bba760b
|
fix the bug: read space as unk
|
3 years ago |
|
Hui Zhang
|
913b2300c3
|
nprocs 0 for cpu, other for gpu
|
3 years ago |
|
Hui Zhang
|
80eb6b7f01
|
fix espnet kaldi libri s2 config
|
3 years ago |
|
Hui Zhang
|
45a75acee1
|
Delete nohup_test.out
|
3 years ago |
|
huangyuxin
|
7e96942c58
|
Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into release_model
|
3 years ago |
|
huangyuxin
|
f0184352f5
|
change the code format to 2.x style
|
3 years ago |
|
Hui Zhang
|
b9beea5ab1
|
fix bench
|
3 years ago |
|
Hui Zhang
|
15d26cc4ad
|
update u2 transformer config
|
3 years ago |
|
Hui Zhang
|
b381f5b447
|
fix profiler optitons config
|
3 years ago |
|
Hui Zhang
|
0e91d26ae3
|
fix log; add report to trainer
|
3 years ago |
|
huangyuxin
|
4c7fefd4e3
|
add transformed v1.8 model
|
3 years ago |
|
Hui Zhang
|
cda6ca8323
|
add benchmark flags, and logic
|
3 years ago |
|
Hui Zhang
|
7907319288
|
fix profiler
|
3 years ago |
|
Hui Zhang
|
5fdda953b9
|
add op profiling
|
3 years ago |
|
Hui Zhang
|
ec76df6cbc
|
do not set seed since break model covergence, aishell s0 seed 10086 test ok
|
3 years ago |
|
Hui Zhang
|
256e9c1b9c
|
more doc for egs
|
3 years ago |
|
Hui Zhang
|
3843372958
|
u2 with chianer updater
|
3 years ago |
|
Hui Zhang
|
28a0a64153
|
fix train.sh
|
3 years ago |
|
Hui Zhang
|
890a28f9bf
|
add more ctc conf
|
3 years ago |
|
Hui Zhang
|
41ed7a184c
|
add ctc conf
|
3 years ago |
|
Hui Zhang
|
1a8c5278a1
|
export ctc grad norm config
|
3 years ago |
|
Hui Zhang
|
7e136d0893
|
support no_sync for backward; ds support accum grad
|
3 years ago |
|
Hui Zhang
|
184d30dd9c
|
relase librispeech audio max len to 30 second
|
3 years ago |
|
Hui Zhang
|
d028c8416d
|
fix recipe train and avg shell
|
3 years ago |
|
huangyuxin
|
04d9db199f
|
add blank_id parameter
|
3 years ago |
|
Hui Zhang
|
f54dc983b6
|
using bw rnn in ds2
|
3 years ago |
