Mattheliu
|
09e5d8a4ac
|
【Fix Speech Issue No.8】issue 3652 merge_yi function has a bug (#3786)
* 【Fix Speech Issue No.8】issue 3652 merge_yi function has a bug
* 【Fix Speech Issue No.8】issue 3652 merge_yi function has a bug
|
6 months ago |
jzhang533
|
969f33999f
|
Merge pull request #3538 from fazledyn-or/develop
Fixed implementation of a special method
|
9 months ago |
JeffLu
|
02a5f7bce8
|
bugfix: audio_len should be 1D, no 0D, which will raise list index out (#3490)
of range error in the following decode process
Co-authored-by: Luzhenhui <luzhenhui@mqsz.com>
|
9 months ago |
Color_yr
|
39ba32fafb
|
增加文件编码读取 (#3606)
Fixed #3605
|
10 months ago |
gmm
|
1b8ca706d6
|
【benchmark】fix gpu_mem unit (#3634)
* fix profiler
* add max_mem_reserved for benchmark
* fix benchmark
|
12 months ago |
luyao-cv
|
f2416ff365
|
fix develop bug function:view to reshape (#3633)
|
12 months ago |
|
gmm
|
a1f9339181
|
【benchmark】add max_mem_reserved for benchmark (#3604)
* fix profiler
* add max_mem_reserved for benchmark
|
1 year ago |
fazledyn-or
|
1a693448fa
|
FIX: Fixed the implementation of a special method
|
1 year ago |
|
fazledyn-or
|
1113a68a6d
|
FIX: Added missing imports
|
1 year ago |
Kai Song
|
9a50647592
|
Add XPU support for FastSpeech2 (#3514)
* Add XPU support for FastSpeech2
* optimize
|
1 year ago |
|
Kai Song
|
08599b7300
|
Add XPU support for SpeedySpeech (#3502)
* Add XPU support for SpeedySpeech
* fix typos
* update description of nxpu
|
1 year ago |
Wang Huan
|
790f183f68
|
fix develop view confict with model's
|
1 year ago |
Hui Zhang
|
2faa49a39f
|
fix weight decay
|
1 year ago |
|
Hui Zhang
|
d94db47f78
|
fix rotary embeding
|
1 year ago |
|
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
|
2 years ago |
|
jiamingkong
|
2ea00755f7
|
Changed the MD5 of the pretrained tar file due to bug fixes
|
2 years ago |
|
jiamingkong
|
232dcf8660
|
Adapted wavlmASR model to pretrained weights and CLI
|
2 years 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")
|
2 years ago |
zoooo0820
|
17f2944a17
|
fix error in tts/st
|
2 years ago |
|
jiamingkong
|
60bd7f202e
|
Code clean up according to comments in https://github.com/PaddlePaddle/PaddleSpeech/pull/3242
|
2 years ago |
|
zxcd
|
b1b8859290
|
fix model m5s
|
2 years ago |
|
jiamingkong
|
3b6651ba7c
|
Adding WavLM implementation
|
2 years 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
|
2 years ago |
|
zxcd
|
caca8e2f12
|
[ASR] fix asr 0-d tensor. (#3214)
* fix asr infer.py
* add readme.
|
2 years 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
|
2 years ago |
