zxcd
|
9d8660b2f6
|
add new aishell model for better CER.
|
1 year ago |
|
zxcd
|
a1e5f27003
|
mv scaler.unscale_ blow grad_clip.
|
1 year ago |
|
zxcd
|
7399d560e7
|
fix scaler save and load.
|
1 year ago |
|
zxcd
|
2f4414a5f8
|
fix scaler save
|
1 year ago |
|
zxcd
|
fbd27aab41
|
add amp for U2 conformer.
|
1 year ago |
liangym
|
e83b491c34
|
rm unused dep, test=tts (#3097)
|
2 years ago |
TianYuan
|
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 |
|
TianYuan
|
0a2e367ff4
|
[TTS]clean starganv2 vc model code and add docstring (#2987)
* clean code
* add docstring
|
2 years ago |
|
liangym
|
880c172db7
|
[TTS] add svs frontend (#3062)
|
2 years ago |
|
TianYuan
|
d5720e4e7b
|
fix input dtype of elementwise_mul op from bool to int64 (#3054)
|
2 years ago |
夜雨飘零
|
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 |
|
zxcd
|
9bf5471613
|
optional tokenizer and fix some doc. (#3042)
|
2 years ago |
|
TianYuan
|
706a68bde9
|
fix dtype diff of last expand_v2 op of VITS (#3041)
|
2 years ago |
|
liangym
|
348064de0d
|
[TTS] add opencpop HIFIGAN example (#3038)
* add opencpop voc, test=tts
* soft link
* add opencpop hifigan, test=tts
* update
|
2 years ago |
|
zxcd
|
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 |
|
liangym
|
435fc5cc19
|
[TTS] add opencpop PWGAN example (#3031)
* add opencpop voc, test=tts
* soft link
|
2 years ago |
|
TianYuan
|
271112ca69
|
fix vits reduce_sum's input/output dtype, test=tts (#3028)
|
2 years ago |
|
liangym
|
1afd14acd9
|
[TTS]add Diffsinger with opencpop dataset (#3005)
|
2 years ago |
MistEO
|
319c805968
|
[TTS] Support set device id for tts prediction, test=tts (#3019)
|
2 years ago |
|
zxcd
|
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 |
|
zxcd
|
5186319f48
|
fix load model schedule error, config optional. (#3008)
|
2 years ago |
|
TianYuan
|
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 |
JiehangXie
|
59cabdc967
|
[TTS]Cli Cantonese onnx, test=tts (#2990)
Co-authored-by: TianYuan <white-sky@qq.com>
|
2 years ago |
mooncake
|
c02bc087f6
|
rearrange-encoder-infer-param (#2983)
|
2 years ago |
|
TianYuan
|
f7fd111647
|
[TTS]add StarGANv2-VC model scripts (#2842)
|
2 years ago |
HuangLiangJie
|
c8196d45ae
|
[TTS]Canton CLI, test=tts (#2977)
|
2 years ago |
|
TianYuan
|
ad239eb444
|
[TTS]add VITS inference (#2972)
|
2 years ago |
|
TianYuan
|
84f751f529
|
[TTS]vits dygraph to static (#2883)
Co-authored-by: 0x45f <wangzhen45@baidu.com>
|
2 years ago |
|
HuangLiangJie
|
11bc392617
|
[TTS]Canton phonetic fix, test=tts (#2950)
|
2 years ago |
|
TianYuan
|
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 |
|
liangym
|
d9b041e999
|
[TTS]Cli male onnx (#2945)
|
2 years ago |
|
zxcd
|
dcf8ef04e0
|
[ASR] Remove fluid api and useless import, test=asr (#2944)
* remove fluid api and useless import.
* fix variable name
|
2 years ago |
|
JiehangXie
|
a5c0bffd2a
|
add Cantonese test examples (#2937)
|
2 years ago |
|
zxcd
|
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 |
|
HuangLiangJie
|
1af9bd47d9
|
[TTS]Cantonese FastSpeech2 e2e infer, test=tts (#2927)
|
2 years ago |
|
zxcd
|
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 |
|
zxcd
|
17a7ebddfa
|
fix dist_sampler AttributeError (#2918)
|
2 years ago |
|
HuangLiangJie
|
acfa057dc7
|
[TTS]Cantonese FastSpeech2 Training, test=tts (#2907)
|
2 years ago |
|
zxcd
|
047092de8e
|
add wav2vev2_zh aishell recipe, and speechbrain dataloader. (#2916)
|
2 years ago |
艾梦
|
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 |
|
zxcd
|
6728db5b59
|
[ASR]Whisper remove audio duration limit, test=asr (#2900)
|
2 years ago |
|
zxcd
|
f6b624ddc8
|
add encoding=utf8 for text cli. (#2896)
|
2 years ago |
章宏彬
|
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 |
|
TianYuan
|
a283f8a57e
|
[TTS]fix open encoding (#2865)
|
2 years ago |
|
艾梦
|
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 |
QuanZ9
|
ac3ed3c5a8
|
Update zh_frontend.py (#2863)
|
2 years ago |
|
zxcd
|
64aeb6dccc
|
remove some fluid api (elementwise_div elementwise_mul sqrt reduce_sum). (#2859)
|
2 years ago |
|
zxcd
|
31c2c226ca
|
clean fluid elementwise_max and square api. (#2852)
|
2 years ago |
|
HuangLiangJie
|
140aed4b54
|
[TTS]VITS init sampler reverse, test=tts (#2843)
|
2 years ago |
|
艾梦
|
57b9d4bca4
|
add diffusion module for training diffsinger (#2832)
|
2 years ago |
