1239 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Bailey Hirota	4b634602d6	update musan path	2025-07-10 13:23:30 +09:00
Bailey Hirota	6ef0fec6e8	resolve typos and import issues	2025-07-09 14:06:29 +09:00
Bailey Hirota	8b25152edf	remove comment	2025-07-04 15:40:14 +09:00
Bailey Hirota	f6bae95ebd	commenting	2025-07-01 21:21:25 +09:00
Bailey Hirota	55d0664339	typos	2025-07-01 21:04:18 +09:00
Bailey Hirota	d8cb41f4f6	changes to asr_datamodule for musan support	2025-07-01 18:18:25 +09:00
Bailey Hirota	252e5eb2e1	remove unused local scripts	2025-06-13 00:49:40 +09:00
Bailey Hirota	fe9f975ec2	changes to train script - no need for limiting utterance length here	2025-06-13 00:48:37 +09:00
Bailey Hirota	e1f140a50e	remove commented out codels	2025-06-13 00:33:47 +09:00
Bailey Hirota	78d4e50d0f	add stage 6 - update cutset paths to prepare	2025-06-12 00:21:52 +09:00
Bailey Hirota	da75835639	update manifest dir path	2025-06-12 00:20:41 +09:00
Bailey Hirota	5a120cbcb3	add step 4: display manifest stats to mls_eng	2025-06-11 18:06:29 +09:00
Kinan Martin	003e94fac2	Update README.md to reflect MLS English dataset	2025-06-11 09:19:07 +09:00
Kinan Martin	c7c74b8658	Add failsafe for MLS English dev set key alternate name as validation	2025-06-11 09:18:28 +09:00
Kinan Martin	c8d932b0c2	Parametrize dev and test split sizes.	2025-06-10 10:11:33 +09:00
Kinan Martin	a6f60de9dd	add utility file for creating subsets of mls english. must be fixed to make dev and test splits have matching sizes to reazonspeech	2025-06-06 11:44:27 +09:00
Kinan Martin	052fcc3218	add utility file for updating the storage_path of cutsets for use in the multilingual training recipe directory structure	2025-06-06 11:42:08 +09:00
Kinan Martin	6255ba5cb2	fix decode script data module usage	2025-06-06 11:29:29 +09:00
Kinan Martin	ce894a7ba2	Combined updates. Changed BBPE path structure, changed dataset path structure, added script to update cutset paths. WIP	2025-06-04 10:12:39 +09:00
Kinan Martin	1f11ba4d28	use huggingface_hub library to download mls_english	2025-05-22 09:15:12 +09:00
Kinan Martin	f3f04fa626	switch mls_english clone from https to ssh	2025-05-21 10:25:47 +09:00
Kinan Martin	e6615df4eb	fix stage 5 output pathing	2025-05-15 09:11:40 +09:00
Kinan Martin	daff070d68	restore version of mls_english compute_fbank_mls_english.py and prepare.sh from commit 547f5c5	2025-05-15 07:24:26 +09:00
Kinan Martin	e34f2dbb2a	merge change to remove bilingual param with new multidataset_datamodule	2025-05-14 08:51:11 +09:00
Kinan Martin	eb5004880f	deprecate params.bilingual=0, replace ReazonSpeechAsrDataModule for MultiDatasetAsrDataModule, not tested yet	2025-05-14 08:41:03 +09:00
Bailey Hirota	7ef1811063	remove bilingual tag from train.py	2025-05-14 08:37:44 +09:00
Bailey Hirota	b2df5bbb83	Revert "add fbank" ... This reverts commit ba603e0a0a514056ec6d32677053c41743a1a5dd.	2025-05-13 09:43:17 +09:00
Bailey Hirota	82bd37cacd	add fbank	2025-05-13 09:43:05 +09:00
Kinan Martin	21d1bf73bb	new version of multi_ja_en prepare.sh script which swaps Librispeech for MLS English	2025-05-09 10:57:41 +09:00
Kinan Martin	547f5c5cfb	optimize with num_jobs on save_audios	2025-05-02 07:22:38 +09:00
Kinan Martin	88249f0eb4	fix stage 2 and 3	2025-05-01 08:15:07 +09:00
Kinan Martin	90326c1f43	fix validation manifest name	2025-05-01 08:05:42 +09:00
Kinan Martin	dbe270ba94	adjusted prepare.sh to only calculate fbank and manifest together; adjust datamodule to load from manifest files	2025-04-30 10:06:13 +09:00
Kinan Martin	cf425173af	move compute_fbank_mls_english.py, add validate_manifest.py, add shared symlink to librispeech	2025-04-24 09:39:54 +09:00
Kinan Martin	4f743993ef	instead of on-the-fly features, precompute fbank and manifests in prepare.sh	2025-04-23 10:13:15 +09:00
Kinan Martin	4e2a4fdcd8	readme	2025-04-16 08:13:59 +09:00
Kinan Martin	bb6d672b54	pre-commit hooks	2025-04-16 08:05:05 +09:00
Kinan Martin	e69e1c04b2	separate transcript prep stage from bpe train stage	2025-04-16 07:15:25 +09:00
Kinan Martin	6e81d9aa5b	symlink copied files to librispeech recipe dir	2025-04-16 07:11:25 +09:00
Kinan Martin	0e868049a6	Merge branch 'k2-fsa:master' into mls_english_clean	2025-04-15 17:52:18 -04:00
Kinan Martin	cf8e9a8a1c	cleaned-up version of recipe	2025-04-15 10:19:51 +09:00
Kinan Martin	a4be3cb3db	replace file	2025-04-14 08:27:50 +09:00
Kinan Martin	1e9bb87305	change default path	2025-04-11 10:30:08 +09:00
Kinan Martin	3eeadd0f3a	update prepare.sh, fix asr_datamodule.py	2025-04-11 10:29:27 +09:00
math345	64c5364085	Fix bug: When resuming training from a checkpoint, model_avg was not assigned, resulting in a None error. (#1914)	2025-04-10 11:37:28 +08:00
Fangjun Kuang	300a821f58	Fix aishell training (#1916)	2025-04-10 10:30:37 +08:00
Fangjun Kuang	171cf8c9fe	Avoid redundant computation in PiecewiseLinear. (#1915)	2025-04-09 11:52:37 +08:00
Kinan Martin	93766fc24f	WIP v0 MLS English recipe	2025-04-09 10:22:20 +09:00
Wei Kang	86bd16d496	[KWS]Remove graph compiler (#1905)	2025-04-02 22:10:06 +08:00
Fangjun Kuang	db9fb8ad31	Add scripts to export streaming zipformer(v1) to RKNN (#1882)	2025-02-27 17:10:58 +08:00