yinfan98
5b3612f273
【Hackathon 7th】fix whisper at Paddle 3.0 ( #3880 )
...
* fix whisper at Paddle 3.0
* fix whisper at Paddle 3.0
* fix whisper at Paddle 3.0
* fix lint
* fix
* fix whisper ci
* Update TTSCppFrontend
* Update utils
* Update steps
* Update utils
* Update __init__.py
* Update whisper.py
* Update utils
* Update utils
10 months ago
megemini
5e8c727fd6
[Hackathon 7th] 修复 `tal_cs` 测试中 0D tensor to 1D ( #3913 )
...
* [Fix] 0D tensor to 1D
* [Update] feat dim
10 months ago
megemini
a397ebe207
[Fix] import print_arguments ( #3918 )
10 months ago
megemini
3e53497a28
[Hackathon 7th] 修复 vctk 中 `spk_emb` 维度问题 ( #3916 )
...
* [Fix] vctk spk_emb dim
* [Update] dim == 1
10 months ago
Wang Xin
61728f8db6
NumPy compatibility enhancements ( #3907 )
...
* NumPy compatibility enhancements
* update code
10 months ago
张春乔
7dc806dc1d
run with aishell/asr3 ( #3904 )
10 months ago
megemini
7fd5abd75d
[Fix] max between int and value ( #3903 )
10 months ago
zxcd
d32ced7f1a
separate paddle.logsumexp ( #3897 )
10 months ago
zxcd
89bfd44293
fix file name ( #3895 )
10 months ago
Wang Xin
62c21e951f
replace view with reshape in aishell/asr1 ( #3887 )
10 months ago
张春乔
6f44ac92c8
fix the shape error in layer_norm ( #3884 )
10 months ago
Wang Xin
4fdb0647f4
fix type promotion TypeError in tensor_utils.py ( #3883 )
10 months ago
张春乔
419af4503c
【Hackathon 7th】Remove parser.add_argument ( #3878 )
...
* Update test_wav.py
* Update export.py
* Update test_export.py
* Update model.py
* Update README.md
* Apply suggestions from code review
* Apply suggestions from code review
* Update README.md
* Update README.md
* Update test.py
* Update README.md
10 months ago
wanx7130
99d4b7061a
Add GCU Backend ( #3875 )
10 months ago
张春乔
290d161d8a
【Hackathon 7th】add implemention of strtobool ( #3877 )
...
* add implemention of strtobool
* Apply suggestions from code review
* Apply suggestions from code review
* Apply suggestions from code review
10 months ago
Wang Xin
21b55419c7
fix scipy import error ( #3874 )
10 months ago
张春乔
5f40262a96
Fix wav2vec error in Demos/ssl ( #3872 )
...
* Update infer.py
* Update wav2vec2_ASR.py
* Apply suggestions from code review
* Apply suggestions from code review
* Update infer.py
* Update wav2vec2_ASR.py
* Apply suggestions from code review
11 months ago
SuiYunsy
8279539978
Fix a bug of streaming_tts_server ( #3865 )
...
* Fix a bug of streaming_tts_server
Fix "Failed to get model related files" when using fastspeech2_csmsc_onnx model in streaming_tts_server.
* Fix CodeStyle
11 months ago
undefined
6f84388189
添加量词和单位符号 ( #3837 )
...
* 添加对公里、公引、公丈、公尺、公寸、公分、公釐的支持
> 低于100公里或超过110公里时
先前生成```低于幺零零公里或超过幺幺零公里时```
修改后```低于一百公里或超过一百一十公里时```
* 添加更多单位
11 months ago
megemini
6316514329
[Fix] type promotion ( #3817 )
11 months ago
zxcd
188444f778
fix ( #3856 )
12 months ago
zhuyipin
a9ece28ba6
speedyspeech code adapt for mlu ( #3828 )
...
* speedyspeech code adapt for mlu
* fix inference
* fix help message
1 year ago
zhuyipin
0b568136d9
speedyspeech code adapt for npu ( #3804 )
...
* speedyspeech code adapt for npu
* fix npu inference
* fix e2e synthesize
* add paddle version control for memory optim config
* fix code style
* fix code style
* fix help message
* fix code style
* fix help message
1 year ago
zxcd
91170bd260
adapt view behavior change, fix KeyError. ( #3794 )
...
* adapt view behavior change, fix KeyError.
* fix readme demo run error.
* fixed opencc version
1 year ago
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
1 year ago
jzhang533
969f33999f
Merge pull request #3538 from fazledyn-or/develop
...
Fixed implementation of a special method
2 years 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>
2 years ago
Color_yr
39ba32fafb
增加文件编码读取 ( #3606 )
...
Fixed #3605
2 years ago
gmm
1b8ca706d6
【benchmark】fix gpu_mem unit ( #3634 )
...
* fix profiler
* add max_mem_reserved for benchmark
* fix benchmark
2 years ago
luyao-cv
f2416ff365
fix develop bug function:view to reshape ( #3633 )
2 years ago
gmm
a1f9339181
【benchmark】add max_mem_reserved for benchmark ( #3604 )
...
* fix profiler
* add max_mem_reserved for benchmark
2 years ago
fazledyn-or
1a693448fa
FIX: Fixed the implementation of a special method
2 years ago
fazledyn-or
1113a68a6d
FIX: Added missing imports
2 years ago
Kai Song
9a50647592
Add XPU support for FastSpeech2 ( #3514 )
...
* Add XPU support for FastSpeech2
* optimize
2 years ago
Kai Song
08599b7300
Add XPU support for SpeedySpeech ( #3502 )
...
* Add XPU support for SpeedySpeech
* fix typos
* update description of nxpu
2 years ago
Wang Huan
790f183f68
fix develop view confict with model's
2 years ago
Hui Zhang
2faa49a39f
fix weight decay
2 years ago
Hui Zhang
d94db47f78
fix rotary embeding
2 years ago
Hui Zhang
0a5cc5556e
rope for streaming decoding
2 years ago
Hui Zhang
b56fb85ca0
RoPE with position interpolation
2 years ago
Hui Zhang
b91b1c9b08
support position interpolation for langer attention context windown length.
2 years ago
Hui Zhang
55870ffbb3
fix bugs
2 years ago
Hui Zhang
03e9ea9e52
add roformer
2 years ago
zxcd
5fee985dd1
remove fluid.
2 years ago
Hui Zhang
a2ae6396ef
old grad clip has 0d tensor problem, fix it ( #3334 )
2 years ago
gmm
5153ac8318
fix profiler ( #3323 )
2 years ago
Hui Zhang
ffb17a250a
hotfix english G2P
2 years ago
Hui Zhang
89d959fc8e
remove print
2 years ago
Hui Zhang
d53c499447
fix long text oom using ssml; filter comma; update polyphonic
2 years ago
Hui Zhang
108e73e1a0
add mix frontend test
2 years ago
Hui Zhang
40124ed34f
add en_frontend file
2 years ago
Hui Zhang
9727e67a3f
add ssml unit test
2 years ago
Hui Zhang
4d867700eb
move ssl into t2s.frontend; fix spk_id for 0-D tensor;
2 years ago
Hui Zhang
42f2186d71
more comment on tts frontend
2 years ago
Hui Zhang
8aa9790c75
Merge pull request #3305 from zh794390558/tts
...
[t2s] add assets and tts codeswitch scripts
2 years ago
Hui Zhang
46de1b0379
Merge pull request #3268 from shuishu/patch-1
...
[TTS][tn]Update phonecode.py
2 years ago
Hui Zhang
6b4d1f80ac
add t2s assets
2 years ago
zxcd
9b8ac050de
add dtype param for arange API. ( #3302 )
2 years ago
Hui Zhang
6e7c71b26c
refactor rhy
2 years ago
jiamingkong
8432e8626f
Final cleaning; Modified SSL/infer.py and README for wavlm inclusion in model options
2 years ago
jiamingkong
ba874db5dc
Fixed the transpose usages ignored before
2 years ago
jiamingkong
0e2068e2cf
Code clean up for CIs
2 years ago
jiamingkong
3ef28dee45
Merge branch 'PaddlePaddle:develop' into develop
2 years 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
Hui Zhang
8371d14f5d
Merge pull request #3167 from zxcd/amp
...
[ASR] add amp for U2 conformer
2 years ago
Hui Zhang
225737d4e3
[s2t] fix cli args to config ( #3194 )
...
* fix cli args to config
* fix train cli
2 years ago
Hui Zhang
e3dcfa8815
Merge pull request #3186 from PaddlePaddle/vits_pr
...
[TTS]update lr schedulers from per iter to per epoch for VITS
2 years ago
zxcd
bc365cbb52
Merge branch 'develop' into amp
2 years ago
zxcd
9d8660b2f6
add new aishell model for better CER.
2 years ago
WongLaw
305375c310
VITS learning rate revised, test=tts
2 years ago
WongLaw
fdeb9b88a7
VITS learning rate revised, test=tts
2 years ago
TianYuan
fc670339d1
[TTS]Fix losses of StarGAN v2 VC ( #3184 )
2 years 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
2 years ago
Shuangchi He
8c7859d3bc
Fix some typos. ( #3178 )
...
Signed-off-by: Yulv-git <yulvchi@qq.com>
2 years ago
Hui Zhang
35d874c532
[s2t] mv dataset into paddlespeech.dataset ( #3183 )
...
* mv dataset into paddlespeech.dataset
* add aidatatang
* fix import
2 years ago
WongLaw
47e31f46cb
VITS learning rate revised, test=tts
2 years ago
WongLaw
414de3747c
VITS learning rate revised, test=tts
2 years ago
TianYuan
3ad55a31e7
[TTS]StarGANv2 VC fix some trainer bugs, add add reset_parameters ( #3182 )
2 years ago
PiaoYang
5a0103b2ae
[BUG] Fix progress bar unit. ( #3177 )
2 years ago
ljhzxc
dc56c3a10e
[TTS] [黑客松]Add JETS ( #3109 )
2 years ago
TianYuan
bd0d69ca74
[TTS]add StarGANv2VC preprocess ( #3163 )
2 years ago
zxcd
a1e5f27003
mv scaler.unscale_ blow grad_clip.
2 years ago
zxcd
7399d560e7
fix scaler save and load.
2 years ago
zxcd
2f4414a5f8
fix scaler save
2 years ago
zxcd
fbd27aab41
add amp for U2 conformer.
2 years ago
TianYuan
c7d24ba42c
fix some preprocess bugs ( #3155 )
2 years ago
longRookie
df37798598
[TTS]【Hackathon + No.190】 + 模型复现:iSTFTNet ( #3006 )
...
* iSTFTNet implementation based on hifigan, not affect the function and execution of HIFIGAN
* modify the comment in iSTFT.yaml
* add the comments in hifigan
* iSTFTNet implementation based on hifigan, not affect the function and execution of HIFIGAN
* modify the comment in iSTFT.yaml
* add the comments in hifigan
* add iSTFTNet.md
* modify the format of iSTFTNet.md
* modify iSTFT.yaml and hifigan.py
* Format code using pre-commit
* modify hifigan.py,delete the unused self.istft_layer_id , move the self.output_conv behind else, change conv_post to output_conv
* update iSTFTNet_csmsc_ckpt.zip download link
* modify iSTFTNet.md
* modify hifigan.py and iSTFT.yaml
* modify iSTFTNet.md
2 years ago
TianYuan
72aa19c32c
[TTS]add starganv2 vc trainer ( #3143 )
...
* add starganv2 vc trainer
* fix StarGANv2VCUpdater and losses
* fix StarGANv2VCEvaluator
* add some typehint
2 years ago
TianYuan
54ef90fcec
[TTS]Fix VITS lite infer ( #3098 )
2 years ago
liangym
e83b491c34
rm unused dep, test=tts ( #3097 )
3 years ago