338 Commits (develop)

Author	SHA1	Message	Date
jiamingkong	232dcf8660	Adapted wavlmASR model to pretrained weights and CLI	3 years ago
jiamingkong	60bd7f202e	Code clean up according to comments in https://github.com/PaddlePaddle/PaddleSpeech/pull/3242	3 years ago
jiamingkong	3b6651ba7c	Adding WavLM implementation	3 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	3 years ago
Hui Zhang	8371d14f5d	Merge pull request #3167 from zxcd/amp ... [ASR] add amp for U2 conformer	3 years ago
Hui Zhang	225737d4e3	[s2t] fix cli args to config (#3194) ... * fix cli args to config * fix train cli	3 years ago
zxcd	bc365cbb52	Merge branch 'develop' into amp	3 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	3 years ago
Shuangchi He	8c7859d3bc	Fix some typos. (#3178) ... Signed-off-by: Yulv-git <yulvchi@qq.com>	3 years ago
zxcd	a1e5f27003	mv scaler.unscale_ blow grad_clip.	3 years ago
zxcd	7399d560e7	fix scaler save and load.	3 years ago
zxcd	2f4414a5f8	fix scaler save	3 years ago
zxcd	fbd27aab41	add amp for U2 conformer.	3 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	3 years ago
zxcd	9bf5471613	optional tokenizer and fix some doc. (#3042)	3 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.	3 years ago
zxcd	5186319f48	fix load model schedule error, config optional. (#3008)	3 years ago
zxcd	dcf8ef04e0	[ASR] Remove fluid api and useless import, test=asr (#2944) ... * remove fluid api and useless import. * fix variable name	4 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	4 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.	4 years ago
zxcd	17a7ebddfa	fix dist_sampler AttributeError (#2918)	4 years ago
zxcd	047092de8e	add wav2vev2_zh aishell recipe, and speechbrain dataloader. (#2916)	4 years ago
zxcd	6728db5b59	[ASR]Whisper remove audio duration limit, test=asr (#2900)	4 years ago
zxcd	64aeb6dccc	remove some fluid api (elementwise_div elementwise_mul sqrt reduce_sum). (#2859)	4 years ago
zxcd	31c2c226ca	clean fluid elementwise_max and square api. (#2852)	4 years ago
cxumol	a99244d86e	fix: whisper language choice, test=asr (#2828)	4 years ago
zxcd	ad40dafa85	fix some bug. (#2825)	4 years ago
zxcd	a8a240d4ef	remove paddle.fluid (#2740)	4 years ago
YangZhou	12fa8a2d19	[audio]patch:fix tensor_utils error (#2738) ... * fix tensor utils	4 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.	4 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	4 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	4 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	4 years ago
zxcd	b71f1428c7	add all whisper model size support, test=asr (#2677) ... * add all whisper model size support * add choices in parser.	4 years ago
Zth9730	94a487bd81	[ASR] support wav2vec2 command line and demo (#2658) ... * wav2vec2_cli * wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr * wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr * wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr * wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr * Update RESULTS.md * Update RESULTS.md * Update base_commands.py * wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr * wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr	4 years ago
zxcd	b1d3f59bcb	[s2t] add whisper asr large model (#2640) ... * add whisper asr large model decoding, test=asr * fix code style. * fix json code style. * remove resource and fix code style. * fix yapf * add cli and demos, fix some code style. * fix some problem by comment. * fix yapf	4 years ago
Zth9730	8d3494320d	[ASR] wav2vec2_en, test=asr (#2637) ... * wav2vec2_en, test=asr * wav2vec2_en, test=asr * wav2vec2_en, test=asr	4 years ago
Hui Zhang	2c34481ea0	[s2t] quant with wav scp (#2568) ... * add quant hint * add paddleslim * using paddleslim 2.3.4 and paddle 2.4	4 years ago
Zth9730	8d3464c050	[s2t] Update wav2vec2 license (#2600)	4 years ago
YangZhou	bbf2401e3e	Merge pull request #2524 from zh794390558/u2 ... [speechx] add u2/u2pp asr inference	4 years ago
Hui Zhang	eac545e1db	Merge pull request #2544 from Zth9730/fix_attention ... [s2t] fix attention eval bug, do not compose kv in infer	4 years ago
tianhao zhang	1ea828c30e	fix attention val bug	4 years ago
Hui Zhang	964c22c677	Merge pull request #2532 from Zth9730/wav2vec2.0 ... [s2t] fix wav2vec2 report loss bug	4 years ago
tianhao zhang	86f65f0b8e	fix wav2vec2 report loss bug	4 years ago
Hui Zhang	f1ca564731	Merge pull request #2518 from Zth9730/wav2vec2.0 ... [ASR] wav2vec2 ASR, pre-trained wav2vec2 based CTC for librispeech	4 years ago
tianhao zhang	2ae94bd277	freeze wav2vec2=True, change loss report and update README.md	4 years ago
tianhao zhang	3d994f5c23	format wav2vec2 demo	4 years ago
tianhao zhang	19180d359d	format wav2vec2 demo	4 years ago
tianhao zhang	6e429f0513	support wav2vec2ASR on librispeech	4 years ago
Hui Zhang	290c23b9d7	add u2 nnet, u2 nnet main, codelab, and can compile	4 years ago
tianhao zhang	cda440e6f0	use reverse_weight in decode.yaml	4 years ago
Hui Zhang	c98b5dd173	fix masked_fill which will nan in trainning	4 years ago
Hui Zhang	9277fcb8a8	fix attn can not train	4 years ago
Hui Zhang	1f4f98b171	fix bug	4 years ago
Hui Zhang	e86337a423	fix bug	4 years ago
Hui Zhang	925abcca23	format	4 years ago
Hui Zhang	2a75405e9a	Merge branch 'develop' into u2pp_export	4 years ago
Hui Zhang	3ed24474d2	wenetspeech asr1 quant	4 years ago
Hui Zhang	467cfd4e75	Merge pull request #2489 from Zth9730/u2++_server ... [ASR] support u2pp based cli and server, optimiz code of u2pp decode (reversed_weight parameter)	4 years ago
tianhao zhang	5bbe6e9897	support u2pp cli and server, optimiz code of u2pp decode, test=asr	4 years ago
Hui Zhang	bdf876ea7b	Merge branch 'develop' into u2pp_export	4 years ago
Hui Zhang	afda7ed7d1	remove useless code	4 years ago
Hui Zhang	b20bf7d5de	masked_fill by multiply, remove while	4 years ago
Hui Zhang	feb27e2a84	fuse linear kv	4 years ago
Hui Zhang	3adb20b468	eliminate shape and slice	4 years ago
Hui Zhang	46088c0a16	elimiate attn transpose	4 years ago
Hui Zhang	f9e3eaa024	transpose in matmul	4 years ago
Hui Zhang	3d7ca93861	bool type slice	4 years ago
Hui Zhang	c2c8a662b1	refactor reshape	4 years ago
Hui Zhang	6de81d74d9	elimiete cast dtype for bool op	4 years ago
Hui Zhang	8e7a315e00	remove comment	4 years ago
Hui Zhang	b7388ce25a	eliminate useless unsqueese	4 years ago
Hui Zhang	1a1ce92cb4	Merge pull request #2415 from Zth9730/u2++_decoder ... [s2t] support bitransformer decoder	4 years ago
tianhao zhang	d3e5937591	support bitransformer decoder	4 years ago
Hui Zhang	7382050e21	fix bug on win	4 years ago
Hui Zhang	d25871a7b0	format	4 years ago
Hui Zhang	b10512eb0e	more config or u2pp	4 years ago
Hui Zhang	00b2c1c8fb	fix forward attention decoder caller	4 years ago
Hui Zhang	309c8d70d9	add reverse weight	4 years ago
Hui Zhang	9b66680ea4	Merge branch 'u2++_decoder' into u2pp_export	4 years ago
tianhao zhang	027535dec1	support bitransformer decoder, test=asr	4 years ago
tianhao zhang	0a95689461	support bitransformer decoder	4 years ago
tianhao zhang	455379b88e	support bitransformer decoder	4 years ago
tianhao zhang	1a56a6e42b	add bitransformer decoder, test=asr	4 years ago
Hui Zhang	53d6baff0b	format	4 years ago
Hui Zhang	549d477592	fix code style	4 years ago
Hui Zhang	4d5cfd4003	export param from cnofig	4 years ago
Hui Zhang	e3298c79ce	Merge branch 'develop' into u2_export	4 years ago
Hui Zhang	260752aa2a	using forward_attention_decoder	4 years ago
Hui Zhang	8690a00bd8	add feature pipeline layer(cmvn, fbank), but to_static and jit.layer output is not equal	4 years ago
Hui Zhang	3a8869fba4	rm to_static decarator; configure jit save for ctc_activation	4 years ago
Hui Zhang	1c9f238ba0	configurable export	4 years ago
Hui Zhang	63aeb747b0	more comment	4 years ago
Hui Zhang	d638325c46	do not jit save forward; using slice for zeros([0,0,0,0]) tensor	4 years ago
tianhao zhang	663e3ab58e	fix dp init	4 years ago
tianhao zhang	6745e9dd6b	fix dp init	4 years ago
tianhao zhang	598eb1a5ef	Merge branch 'develop' into fix_dp_init	4 years ago
tianhao zhang	9560d650db	fix dp init	4 years ago
tianhao zhang	82e04d7815	fix trianer	4 years ago
Hui Zhang	2bb40c41ba	Merge pull request #2351 from Zth9730/fix_deepspeech ... [s2t] fix deepspeech2 decode_wav	4 years ago