9b8ac050de
add dtype param for arange API. ( #3302 )
2 years ago
6e7c71b26c
refactor rhy
2 years ago
8432e8626f
Final cleaning; Modified SSL/infer.py and README for wavlm inclusion in model options
2 years ago
ba874db5dc
Fixed the transpose usages ignored before
2 years ago
0e2068e2cf
Code clean up for CIs
2 years ago
3ef28dee45
Merge branch 'PaddlePaddle:develop' into develop
2 years ago
4453430ac0
Merge pull request #3265 from zoooo0820/fix_0d_error
...
fix error in tts and st for 0-d tensor
2 years ago
2ea00755f7
Changed the MD5 of the pretrained tar file due to bug fixes
2 years ago
232dcf8660
Adapted wavlmASR model to pretrained weights and CLI
2 years ago
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
17f2944a17
fix error in tts/st
2 years ago
60bd7f202e
Code clean up according to comments in https://github.com/PaddlePaddle/PaddleSpeech/pull/3242
2 years ago
b1b8859290
fix model m5s
2 years ago
3b6651ba7c
Adding WavLM implementation
2 years ago
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
caca8e2f12
[ASR] fix asr 0-d tensor. ( #3214 )
...
* fix asr infer.py
* add readme.
2 years ago
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
8371d14f5d
Merge pull request #3167 from zxcd/amp
...
[ASR] add amp for U2 conformer
2 years ago
225737d4e3
[s2t] fix cli args to config ( #3194 )
...
* fix cli args to config
* fix train cli
2 years ago
e3dcfa8815
Merge pull request #3186 from PaddlePaddle/vits_pr
...
[TTS]update lr schedulers from per iter to per epoch for VITS
2 years ago
bc365cbb52
Merge branch 'develop' into amp
2 years ago
9d8660b2f6
add new aishell model for better CER.
2 years ago
305375c310
VITS learning rate revised, test=tts
2 years ago
fdeb9b88a7
VITS learning rate revised, test=tts
2 years ago
fc670339d1
[TTS]Fix losses of StarGAN v2 VC ( #3184 )
2 years ago
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
8c7859d3bc
Fix some typos. ( #3178 )
...
Signed-off-by: Yulv-git <yulvchi@qq.com>
2 years ago
35d874c532
[s2t] mv dataset into paddlespeech.dataset ( #3183 )
...
* mv dataset into paddlespeech.dataset
* add aidatatang
* fix import
2 years ago
47e31f46cb
VITS learning rate revised, test=tts
2 years ago
414de3747c
VITS learning rate revised, test=tts
2 years ago
3ad55a31e7
[TTS]StarGANv2 VC fix some trainer bugs, add add reset_parameters ( #3182 )
2 years ago
5a0103b2ae
[BUG] Fix progress bar unit. ( #3177 )
2 years ago
dc56c3a10e
[TTS] [黑客松]Add JETS ( #3109 )
2 years ago
bd0d69ca74
[TTS]add StarGANv2VC preprocess ( #3163 )
2 years ago
a1e5f27003
mv scaler.unscale_ blow grad_clip.
2 years ago
7399d560e7
fix scaler save and load.
2 years ago
2f4414a5f8
fix scaler save
2 years ago
fbd27aab41
add amp for U2 conformer.
2 years ago
c7d24ba42c
fix some preprocess bugs ( #3155 )
2 years ago
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
72aa19c32c
[TTS]add starganv2 vc trainer ( #3143 )
...
* add starganv2 vc trainer
* fix StarGANv2VCUpdater and losses
* fix StarGANv2VCEvaluator
* add some typehint
2 years ago
54ef90fcec
[TTS]Fix VITS lite infer ( #3098 )
2 years ago
e83b491c34
rm unused dep, test=tts ( #3097 )
2 years ago
6894a2a77d
[TTS]fix elementwise_floordiv's fill_constant ( #3075 )
...
* fix elementwise_floordiv's fill_constant
* add float converter for min_value in attention
2 years ago
0a2e367ff4
[TTS]clean starganv2 vc model code and add docstring ( #2987 )
...
* clean code
* add docstring
2 years ago
880c172db7
[TTS] add svs frontend ( #3062 )
2 years ago
d5720e4e7b
fix input dtype of elementwise_mul op from bool to int64 ( #3054 )
2 years ago
31a4562ae8
[ASR]add squeezeformer model ( #2755 )
...
* add squeezeformer model
* change CodeStyle, test=asr
* change CodeStyle, test=asr
* fix subsample rate error, test=asr
* merge classes as required, test=asr
* change CodeStyle, test=asr
* fix missing code, test=asr
* split code to new file, test=asr
* remove rel_shift, test=asr
2 years ago
9bf5471613
optional tokenizer and fix some doc. ( #3042 )
2 years ago
706a68bde9
fix dtype diff of last expand_v2 op of VITS ( #3041 )
2 years ago
348064de0d
[TTS] add opencpop HIFIGAN example ( #3038 )
...
* add opencpop voc, test=tts
* soft link
* add opencpop hifigan, test=tts
* update
2 years ago
4e9bca177a
[ASR] change optimizer and fix import error, test=asr ( #3023 )
...
* mv dataio.py to s2t.io.speechbrain.dataio
mv dataio.py to paddlespeech.s2t.io.speechbrain.dataio
* remove transformers import.
* change optimizer same with released model
* add paddlenlp version in RESULT.md.
* fix run.sh
* fix data.sh step_num.
* add adadelta optimizer config.
* fix wav2vec2 test_wav.sh run error.
* add tokenizer config.
2 years ago
435fc5cc19
[TTS] add opencpop PWGAN example ( #3031 )
...
* add opencpop voc, test=tts
* soft link
2 years ago
271112ca69
fix vits reduce_sum's input/output dtype, test=tts ( #3028 )
2 years ago
1afd14acd9
[TTS]add Diffsinger with opencpop dataset ( #3005 )
2 years ago
319c805968
[TTS] Support set device id for tts prediction, test=tts ( #3019 )
2 years ago
3145325b4e
[ASR] add wav2vec2 aishell model result, test=asr ( #3012 )
...
* Create RESULT.md
* add wav2vec2ASR-large-aishell1 finetune model.
* update model link and add readme.
* fix released model info.
2 years ago
5186319f48
fix load model schedule error, config optional. ( #3008 )
2 years ago
528ae58a67
[TTS]remove pad op in static model by replace F.pad with nn.Pad1D and nn.Pad2D ( #3002 )
...
* remove pad op in static model by replace F.pad with nn.Pad1D and nn.Pad2D
* fix variable names
* add note
2 years ago
59cabdc967
[TTS]Cli Cantonese onnx, test=tts ( #2990 )
...
Co-authored-by: TianYuan <white-sky@qq.com>
2 years ago
c02bc087f6
rearrange-encoder-infer-param ( #2983 )
2 years ago
f7fd111647
[TTS]add StarGANv2-VC model scripts ( #2842 )
2 years ago
c8196d45ae
[TTS]Canton CLI, test=tts ( #2977 )
2 years ago
ad239eb444
[TTS]add VITS inference ( #2972 )
2 years ago
84f751f529
[TTS]vits dygraph to static ( #2883 )
...
Co-authored-by: 0x45f <wangzhen45@baidu.com>
2 years ago
11bc392617
[TTS]Canton phonetic fix, test=tts ( #2950 )
2 years ago
c8d5a01bdb
[TTS]fix dygraph to static for tacotron2, test=doc ( #2426 )
...
* fix dygraph to static for tacotron2, test=doc
* Fix dy2st error for taco2
* Update attentions.py
---------
Co-authored-by: 0x45f <wangzhen45@baidu.com>
2 years ago
d9b041e999
[TTS]Cli male onnx ( #2945 )
2 years ago
dcf8ef04e0
[ASR] Remove fluid api and useless import, test=asr ( #2944 )
...
* remove fluid api and useless import.
* fix variable name
2 years ago
a5c0bffd2a
add Cantonese test examples ( #2937 )
2 years ago
a8a353d0ac
[ASR] add python simple adadelta optimizer, test=asr ( #2925 )
...
* add simple adeadelta optimizer.
* remove useless log
* remove useless and fluid import.
* add framework.dygraph_only back
2 years ago
1af9bd47d9
[TTS]Cantonese FastSpeech2 e2e infer, test=tts ( #2927 )
2 years ago
004a4d6096
[ASR] rm transformers import and modify variable name consistent with infer.py, test=asr ( #2929 )
...
* rm transformers import and modify variable name consistent with infer.py
* add condition ctc_prefix_beam_search decode.
2 years ago
17a7ebddfa
fix dist_sampler AttributeError ( #2918 )
2 years ago
acfa057dc7
[TTS]Cantonese FastSpeech2 Training, test=tts ( #2907 )
2 years ago
047092de8e
add wav2vev2_zh aishell recipe, and speechbrain dataloader. ( #2916 )
2 years ago
bcd8e309ec
[TTS]Add diffusion noise clip to optimize sample result ( #2902 )
...
* add diffusion module for training diffsinger
* add wavenet denoiser final conv initializer
* add diffusion noise clip to optimize sample result
2 years ago
6728db5b59
[ASR]Whisper remove audio duration limit, test=asr ( #2900 )
2 years ago
f6b624ddc8
add encoding=utf8 for text cli. ( #2896 )
2 years ago
c764710aa1
[TTS]Avoid using variable "attn_loss" before assignment ( #2860 )
...
* Avoid using variable "attn_loss" before assignment
* Update tacotron2_updater.py
---------
Co-authored-by: TianYuan <white-sky@qq.com>
2 years ago
a283f8a57e
[TTS]fix open encoding ( #2865 )
2 years ago
a55fd2e556
[TTS]Fix diffusion wavenet denoiser final conv init param ( #2868 )
...
* add diffusion module for training diffsinger
* add wavenet denoiser final conv initializer
2 years ago
ac3ed3c5a8
Update zh_frontend.py ( #2863 )
2 years ago
64aeb6dccc
remove some fluid api (elementwise_div elementwise_mul sqrt reduce_sum). ( #2859 )
2 years ago
31c2c226ca
clean fluid elementwise_max and square api. ( #2852 )
2 years ago
140aed4b54
[TTS]VITS init sampler reverse, test=tts ( #2843 )
2 years ago
57b9d4bca4
add diffusion module for training diffsinger ( #2832 )
2 years ago
1fd38c0e8b
fix o ( #2831 )
2 years ago
742523fb38
[tts]For mixed Chinese and English speech synthesis, add SSML support for Chinese ( #2830 )
...
* 添加.history
* [tts]添加中英混合语音合成时对中文SSML的支持
2 years ago
a99244d86e
fix: whisper language choice, test=asr ( #2828 )
2 years ago
ad40dafa85
fix some bug. ( #2825 )
2 years ago
faa2f86651
[TTS]update VITS init method ( #2809 )
2 years ago
88fe26f17c
[ASR] add asr code-switch cli and demo, test='asr' ( #2816 )
...
* add asr code-switch cli and demo.
* fix some model named problem.
2 years ago
964211a81b
Change optimizer for vits, test=tts ( #2791 )
2 years ago
96d76c83ad
multi-spk tts static model ( #2779 )
...
* updata readme, test=doc
* update yaml and readme, test=tts
* fix batch_size, test=tts
* update readme, test=doc
* chmod, test=tts
* add multi-spk tts static model infer on server, test=tts
2 years ago
2e51e0da90
[TTS]Fix attention bugs and sort VITS data with feats_lengths ( #2770 )
2 years ago
6725bcd823
revise paddlenlp's version ( #2767 )
2 years ago
979bbd9dcb
add mkldnn and trt config for paddleInference ( #2748 )
2 years ago
a8a240d4ef
remove paddle.fluid ( #2740 )
2 years ago
12fa8a2d19
[audio]patch:fix tensor_utils error ( #2738 )
...
* fix tensor utils
2 years ago
zxcd
Hui Zhang
jiamingkong
jiamingkong
shuishu
zoooo0820
guanyc
TianHao Zhang
WongLaw
TianYuan
Shuangchi He
PiaoYang
ljhzxc
longRookie
liangym
夜雨飘零
MistEO
JiehangXie
mooncake
艾梦
章宏彬
QuanZ9
晋东毅
cxumol
YangZhou