Hui Zhang
|
0a5cc5556e
|
rope for streaming decoding
|
1 year ago |
|
Hui Zhang
|
b56fb85ca0
|
RoPE with position interpolation
|
1 year ago |
|
Hui Zhang
|
b91b1c9b08
|
support position interpolation for langer attention context windown length.
|
1 year ago |
|
Hui Zhang
|
55870ffbb3
|
fix bugs
|
1 year ago |
|
Hui Zhang
|
03e9ea9e52
|
add roformer
|
1 year ago |
zxcd
|
5fee985dd1
|
remove fluid.
|
1 year ago |
|
Hui Zhang
|
a2ae6396ef
|
old grad clip has 0d tensor problem, fix it (#3334)
|
1 year ago |
gmm
|
5153ac8318
|
fix profiler (#3323)
|
1 year ago |
|
Hui Zhang
|
ffb17a250a
|
hotfix english G2P
|
1 year ago |
|
Hui Zhang
|
89d959fc8e
|
remove print
|
1 year ago |
|
Hui Zhang
|
d53c499447
|
fix long text oom using ssml; filter comma; update polyphonic
|
1 year ago |
|
Hui Zhang
|
108e73e1a0
|
add mix frontend test
|
1 year ago |
|
Hui Zhang
|
40124ed34f
|
add en_frontend file
|
1 year ago |
|
Hui Zhang
|
9727e67a3f
|
add ssml unit test
|
1 year ago |
|
Hui Zhang
|
4d867700eb
|
move ssl into t2s.frontend; fix spk_id for 0-D tensor;
|
1 year ago |
|
Hui Zhang
|
42f2186d71
|
more comment on tts frontend
|
1 year ago |
|
Hui Zhang
|
8aa9790c75
|
Merge pull request #3305 from zh794390558/tts
[t2s] add assets and tts codeswitch scripts
|
1 year ago |
|
Hui Zhang
|
46de1b0379
|
Merge pull request #3268 from shuishu/patch-1
[TTS][tn]Update phonecode.py
|
1 year ago |
|
Hui Zhang
|
6b4d1f80ac
|
add t2s assets
|
1 year ago |
|
zxcd
|
9b8ac050de
|
add dtype param for arange API. (#3302)
|
1 year ago |
|
Hui Zhang
|
6e7c71b26c
|
refactor rhy
|
1 year ago |
jiamingkong
|
8432e8626f
|
Final cleaning; Modified SSL/infer.py and README for wavlm inclusion in model options
|
1 year ago |
|
jiamingkong
|
ba874db5dc
|
Fixed the transpose usages ignored before
|
1 year ago |
|
jiamingkong
|
0e2068e2cf
|
Code clean up for CIs
|
1 year ago |
jiamingkong
|
3ef28dee45
|
Merge branch 'PaddlePaddle:develop' into develop
|
1 year ago |
|
Hui Zhang
|
4453430ac0
|
Merge pull request #3265 from zoooo0820/fix_0d_error
fix error in tts and st for 0-d tensor
|
1 year ago |
|
jiamingkong
|
2ea00755f7
|
Changed the MD5 of the pretrained tar file due to bug fixes
|
1 year ago |
|
jiamingkong
|
232dcf8660
|
Adapted wavlmASR model to pretrained weights and CLI
|
1 year ago |
shuishu
|
1f7eabee0f
|
Update phonecode.py
# 固话的正则 错误修改
参考https://github.com/speechio/chinese_text_normalization/blob/master/python/cn_tn.py
固化的正则为：
pattern = re.compile(r"\D((0(10|2[1-3]|[3-9]\d{2})-?)?[1-9]\d{6,7})\D")
|
1 year ago |
zoooo0820
|
17f2944a17
|
fix error in tts/st
|
1 year ago |
|
jiamingkong
|
60bd7f202e
|
Code clean up according to comments in https://github.com/PaddlePaddle/PaddleSpeech/pull/3242
|
1 year ago |
|
zxcd
|
b1b8859290
|
fix model m5s
|
1 year ago |
|
jiamingkong
|
3b6651ba7c
|
Adding WavLM implementation
|
1 year ago |
guanyc
|
5f53e902e1
|
fix: 🐛 修复服务端 python ASREngine 无法使用conformer_talcs模型 (#3230)
* fix: 🐛 fix python ASREngine not pass codeswitch
* docs: 📝 Update Docs
* 修改模型判断方式
|
1 year ago |
|
zxcd
|
caca8e2f12
|
[ASR] fix asr 0-d tensor. (#3214)
* fix asr infer.py
* add readme.
|
1 year ago |
TianHao Zhang
|
12e3e76092
|
[ASR] Support Hubert, fintuned on the librispeech dataset (#3088)
* librispeech hubert, test=asr
* librispeech hubert, test=asr
* hubert decode
* review
* copyright, notes, example related
* hubert cli
* pre-commit format
* fix conflicts
* fix conflicts
* doc related
* doc and train config
* librispeech.py
* support hubert cli
|
1 year ago |
|
Hui Zhang
|
8371d14f5d
|
Merge pull request #3167 from zxcd/amp
[ASR] add amp for U2 conformer
|
1 year ago |
|
Hui Zhang
|
225737d4e3
|
[s2t] fix cli args to config (#3194)
* fix cli args to config
* fix train cli
|
1 year ago |
|
Hui Zhang
|
e3dcfa8815
|
Merge pull request #3186 from PaddlePaddle/vits_pr
[TTS]update lr schedulers from per iter to per epoch for VITS
|
1 year ago |
|
zxcd
|
bc365cbb52
|
Merge branch 'develop' into amp
|
1 year ago |
|
zxcd
|
9d8660b2f6
|
add new aishell model for better CER.
|
1 year ago |
WongLaw
|
305375c310
|
VITS learning rate revised, test=tts
|
1 year ago |
|
WongLaw
|
fdeb9b88a7
|
VITS learning rate revised, test=tts
|
1 year ago |
TianYuan
|
fc670339d1
|
[TTS]Fix losses of StarGAN v2 VC (#3184)
|
1 year ago |
|
Hui Zhang
|
df3be4acae
|
[s2t] move s2t data preprocess into paddlespeech.dataset (#3189)
* move s2t data preprocess into paddlespeech.dataset
* avg model, compute wer, format rsl into paddlespeech.dataset
* fix format rsl
* fix avg ckpts
|
1 year ago |
Shuangchi He
|
8c7859d3bc
|
Fix some typos. (#3178)
Signed-off-by: Yulv-git <yulvchi@qq.com>
|
1 year ago |
|
Hui Zhang
|
35d874c532
|
[s2t] mv dataset into paddlespeech.dataset (#3183)
* mv dataset into paddlespeech.dataset
* add aidatatang
* fix import
|
1 year ago |
|
WongLaw
|
47e31f46cb
|
VITS learning rate revised, test=tts
|
1 year ago |
|
WongLaw
|
414de3747c
|
VITS learning rate revised, test=tts
|
1 year ago |
|
TianYuan
|
3ad55a31e7
|
[TTS]StarGANv2 VC fix some trainer bugs, add add reset_parameters (#3182)
|
1 year ago |
