fazledyn-or
|
1a693448fa
|
FIX: Fixed the implementation of a special method
|
12 months ago |
|
fazledyn-or
|
1113a68a6d
|
FIX: Added missing imports
|
12 months 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 |
|
zxcd
|
9b8ac050de
|
add dtype param for arange API. (#3302)
|
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
|
232dcf8660
|
Adapted wavlmASR model to pretrained weights and CLI
|
1 year ago |
|
jiamingkong
|
60bd7f202e
|
Code clean up according to comments in https://github.com/PaddlePaddle/PaddleSpeech/pull/3242
|
1 year ago |
|
jiamingkong
|
3b6651ba7c
|
Adding WavLM implementation
|
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 |
|
zxcd
|
bc365cbb52
|
Merge branch 'develop' into amp
|
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 |
|
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 |
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 |
|
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 |
|
zxcd
|
5186319f48
|
fix load model schedule error, config optional. (#3008)
|
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 |
|
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 |
|
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 |
|
zxcd
|
047092de8e
|
add wav2vev2_zh aishell recipe, and speechbrain dataloader. (#2916)
|
2 years ago |
|
zxcd
|
6728db5b59
|
[ASR]Whisper remove audio duration limit, test=asr (#2900)
|
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 |
cxumol
|
a99244d86e
|
fix: whisper language choice, test=asr (#2828)
|
2 years ago |
|
zxcd
|
ad40dafa85
|
fix some bug. (#2825)
|
2 years ago |
|
zxcd
|
a8a240d4ef
|
remove paddle.fluid (#2740)
|
2 years ago |
YangZhou
|
12fa8a2d19
|
[audio]patch:fix tensor_utils error (#2738)
* fix tensor utils
|
2 years ago |
|
YangZhou
|
42ff946007
|
[audio] mv paddlespeech/audio to paddleaudio (#2706)
* split paddlespeech/audio to paddleaudio.
* add sox io ,sox effect, kaldi native fbank to paddleaudio.
|
2 years ago |
|
Zth9730
|
c67bf7b4ef
|
[ASR] support wav2vec2-zh cli, test=asr (#2697)
* support wav2vec2-zh cli, test=asr
* support wav2vec2-zh cli, test=asr
* support wav2vec2-zh cli, test=asr
* support wav2vec2-zh cli, test=asr
|
2 years ago |
|
zxcd
|
4542684694
|
[ASR] fix Whisper cli model download path error. test=asr (#2679)
* add all whisper model size support
* add choices in parser.
* fix Whisper cli model download path error.
* fix resource download path.
* fix code style
|
2 years ago |
|
Zth9730
|
fc02cd0540
|
[doc] update wav2vec2 demos README.md, test=doc (#2674)
* fix wav2vec2 demos, test=doc
* fix wav2vec2 demos, test=doc
* fix enc_dropout and nor.py, test=asr
|
2 years ago |
|
zxcd
|
b71f1428c7
|
add all whisper model size support, test=asr (#2677)
* add all whisper model size support
* add choices in parser.
|
2 years ago |
