108 Commits

Author	SHA1	Message	Date
zr_jin	e96f533b44	Update compute_fbank_wenetspeech_splits.py	2024-03-07 16:48:29 +08:00
zr_jin	262792f821	Update prepare.sh ... minor updates	2024-03-07 16:46:37 +08:00
zr_jin	211ce4c5fd	Update train.py ... minor updates	2024-03-07 16:45:48 +08:00
zr_jin	4cca65ac98	Update compute_fbank_wenetspeech_splits.py ... removed unnecessary comments	2024-03-07 16:43:47 +08:00
Yuekai Zhang	19e21ba3ff	Merge branch 'master' into whisper_zh	2024-03-07 13:53:35 +07:00
Yuekai Zhang	a00c0c5279	add speechio results	2024-03-07 14:44:38 +08:00
zr_jin	242002e0bd	Strengthened style constraints (#1527)	2024-03-04 23:28:04 +08:00
Wei Kang	aac7df064a	Recipes for open vocabulary keyword spotting (#1428) ... * English recipe on gigaspeech; Chinese recipe on wenetspeech	2024-02-22 15:31:20 +08:00
Yuekai Zhang	be001a896c	fix index error	2024-02-20 10:20:00 +08:00
Yuekai Zhang	ff75cf6cb3	using soft links	2024-01-31 14:12:59 +08:00
Yuekai Zhang	97aa482ead	only test net	2024-01-31 14:02:39 +08:00
Yuekai Zhang	955d16e6b8	only test net	2024-01-31 14:02:39 +08:00
Yuekai Zhang	4826f0801c	remove utterance more than 30s in test_net	2024-01-31 14:02:39 +08:00
Yuekai Zhang	d8a329eca5	decode all wav files	2024-01-31 14:02:39 +08:00
Yuekai Zhang	341c29e6e2	fix whisper version to support multi batch beam	2024-01-31 14:02:39 +08:00
Yuekai Zhang	c19891ee8e	add remove long short	2024-01-31 14:02:39 +08:00
Yuekai Zhang	bb07b65e45	add remove long short	2024-01-31 14:02:39 +08:00
Yuekai Zhang	1600f7db95	fix too long audios	2024-01-31 14:02:39 +08:00
Yuekai Zhang	b76cd65abf	fix subsampling factor	2024-01-31 14:02:39 +08:00
Yuekai Zhang	ad796d929d	remove useless file	2024-01-31 14:02:39 +08:00
Yuekai Zhang	e49534f2dd	add monkey patch codes	2024-01-31 14:02:39 +08:00
Yuekai Zhang	e1a55b945b	add wenetspeech fine-tune scripts	2024-01-31 14:02:39 +08:00
Yuekai Zhang	baa7c5fb8d	use multi machines	2024-01-31 14:02:39 +08:00
Yuekai Zhang	cf85019290	parallel jobs	2024-01-31 14:02:39 +08:00
Yuekai Zhang	df54121c41	fix io issue	2024-01-31 14:02:39 +08:00
Yuekai Zhang	af29455c3d	add kaldifeatwhisper fbank	2024-01-31 14:02:39 +08:00
Yuekai Zhang	08db3051ad	regression	2024-01-31 14:02:39 +08:00
Yuekai Zhang	f66b266aa4	fix executor	2024-01-31 14:02:39 +08:00
Yuekai Zhang	e46e9b77ee	fix overwrite	2024-01-31 14:02:39 +08:00
Yuekai Zhang	fd77c5758c	change compute feature batch	2024-01-31 14:02:39 +08:00
Yuekai Zhang	f4cf9fb2d3	add aishell2 feat	2024-01-31 14:02:39 +08:00
Yuekai Zhang	aa7b17e410	test feature extractor speed	2024-01-31 14:02:39 +08:00
Yuekai Zhang	d1b010463c	add original model decode with 30s	2024-01-31 14:02:39 +08:00
Yuekai Zhang	38f5f45c67	add requirments.txt	2024-01-31 14:02:39 +08:00
Yuekai Zhang	72c9d01724	add decode for wenetspeech	2024-01-31 14:02:39 +08:00
Yuekai Zhang	046e071ca3	add str to bool	2024-01-31 14:02:39 +08:00
Yuekai Zhang	315175a362	add whisper fbank for other dataset	2024-01-31 14:02:39 +08:00
Yuekai Zhang	e43c4da91d	add whisper fbank for wenetspeech	2024-01-31 14:02:39 +08:00
zr_jin	37b975cac9	fixed a CI test for wenetspeech (#1476) ... * Comply to issue #1149 https://github.com/k2-fsa/icefall/issues/1149	2024-01-27 06:41:56 +08:00
Fangjun Kuang	8d39f9508b	Fix torchscript export to use tokens.txt instead of lang_dir (#1475)	2024-01-26 19:18:33 +08:00
zr_jin	9c494a3329	typos fixed (#1472)	2024-01-25 18:41:43 +08:00
Yifan Yang	5dfc3ed7f9	Fix buffer size of DynamicBucketingSampler (#1468) ... * Fix buffer size * Fix for flake8 --------- Co-authored-by: yifanyeung <yifanyeung@yifanyeung.local>	2024-01-21 02:10:42 +08:00
Karel Vesely	716b82cc3a	streaming_decode.py, relax the audio range from [-1,+1] to [-10,+10] (#1448) ... - some AudioTransform classes produce audio signals out of range [-1,+1] - Resample produced 1.0079 - The range [-10,+10] was chosen to still be able to reliably distinguish from the [-32k,+32k] signal... - this is related to : https://github.com/lhotse-speech/lhotse/issues/1254	2024-01-05 10:21:27 +08:00
Fangjun Kuang	8136ad775b	Use high_freq -400 in computing fbank features. (#1447) ... See also https://github.com/k2-fsa/sherpa-onnx/issues/514	2024-01-04 13:59:32 +08:00
Wei Kang	11d816d174	Add cumstomized score for hotwords (#1385) ... * add custom score for each hotword * Add more comments * Fix deocde * fix style * minor fixes	2023-11-18 18:47:55 +08:00
wnywbyt	c3bbb32f9e	Update the parameter 'vocab-size' (#1364) ... Co-authored-by: wdq <dongqin.wan@desaysv.com>	2023-11-02 20:45:30 +08:00
zr_jin	1814bbb0e7	typo fixed (#1334)	2023-10-25 00:03:33 +08:00
Rudra	eef47adee9	fix typo (#1324)	2023-10-19 22:54:43 +08:00
marcoyang1998	52c24df61d	Fix model avg (#1317) ... * fix a bug about the model_avg during finetuning by exchanging the order of loading pre-trained model and initializing avg model * only match the exact module prefix	2023-10-18 17:36:14 +08:00
zr_jin	d2bd0933b1	Compatibility with the latest Lhotse (#1314)	2023-10-17 21:22:32 +08:00