mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-12-11 06:55:27 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,350 Commits 5 Branches 3 Tags
Commit Graph

1350 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Kinan Martin
68bff93940 fix decode script data module usage 2025-08-05 18:36:27 +09:00
Kinan Martin
1b1a317603 Combined updates. Changed BBPE path structure, changed dataset path structure, added script to update cutset paths. WIP 2025-08-05 18:35:20 +09:00
Kinan Martin
1093e78612 use huggingface_hub library to download mls_english 2025-08-05 18:34:15 +09:00
Kinan Martin
5682978c64 switch mls_english clone from https to ssh 2025-08-05 18:33:03 +09:00
Kinan Martin
2265e1afed fix stage 5 output pathing 2025-08-05 18:31:48 +09:00
Kinan Martin
7bea23e954 restore version of mls_english compute_fbank_mls_english.py and prepare.sh from commit 547f5c5 2025-08-05 18:30:41 +09:00
Bailey Hirota
8b035a0c96 remove bilingual tag from train.py 2025-08-05 18:29:29 +09:00
Kinan Martin
99db0e4643 deprecate params.bilingual=0, replace ReazonSpeechAsrDataModule for MultiDatasetAsrDataModule, not tested yet 2025-08-05 18:16:17 +09:00
Bailey Hirota
31a37c7e44 Revert "add fbank" 
This reverts commit ba603e0a0a514056ec6d32677053c41743a1a5dd.
 2025-08-05 18:15:04 +09:00
Bailey Hirota
7d462aa8b4 add fbank 2025-08-05 18:13:51 +09:00
Kinan Martin
06e429131b new version of multi_ja_en prepare.sh script which swaps Librispeech for MLS English 2025-08-05 18:12:40 +09:00
Kinan Martin
0e86ef805c optimize with num_jobs on save_audios 2025-08-05 18:11:22 +09:00
Kinan Martin
73dea24fd9 fix stage 2 and 3 2025-08-05 18:10:15 +09:00
Kinan Martin
2504b23861 fix validation manifest name 2025-08-05 18:09:00 +09:00
Kinan Martin
eb2168bc49 adjusted prepare.sh to only calculate fbank and manifest together; adjust datamodule to load from manifest files 2025-08-05 18:07:45 +09:00
Kinan Martin
a8f45bc08b move compute_fbank_mls_english.py, add validate_manifest.py, add shared symlink to librispeech 2025-08-05 18:06:28 +09:00
Kinan Martin
fe88d1db36 instead of on-the-fly features, precompute fbank and manifests in prepare.sh 2025-08-05 18:05:18 +09:00
Kinan Martin
996334f520 readme 2025-08-05 18:04:04 +09:00
Kinan Martin
24db8c11ba pre-commit hooks 2025-08-05 18:02:50 +09:00
Kinan Martin
c532a503e7 separate transcript prep stage from bpe train stage 2025-08-05 18:01:41 +09:00
Kinan Martin
313afea773 symlink copied files to librispeech recipe dir 2025-08-05 18:00:24 +09:00
Kinan Martin
e76b749450 cleaned-up version of recipe 2025-08-05 17:59:15 +09:00
Kinan Martin
1b8a3061b0 replace file 2025-08-05 17:57:59 +09:00
Kinan Martin
0ab027411f change default path 2025-08-05 17:56:51 +09:00
Kinan Martin
ba6d8e8b26 update prepare.sh, fix asr_datamodule.py 2025-08-05 17:55:40 +09:00
Kinan Martin
c92c606c5f WIP v0 MLS English recipe 2025-08-05 17:54:30 +09:00
Fangjun Kuang
1c5d792bf1 Validate generated manifest files. (#338) 2025-08-05 17:46:36 +09:00
Kinan Martin
dbd89773d5 Manually fix merge conflict in multi_ja_en/ASR/zipformer/train.py 2025-07-28 17:59:47 +09:00
Bailey Machiko Hirota
aed139f125 Musan implementation for ReazonSpeech (#1988) 2025-07-28 17:52:36 +09:00
Bailey Machiko Hirota
9d93d63cf2 Update RESULTS.md 2025-07-28 17:52:36 +09:00
Bailey Hirota
dc4db379ea PR review suggestions implemented 2025-07-28 17:52:36 +09:00
Bailey Hirota
6012edbc17 black and isort formatting 2025-07-28 17:52:36 +09:00
Bailey Machiko Hirota
154ef43206 Update egs/multi_ja_en/ASR/local/utils/update_cutset_paths.py 
Co-authored-by: Yubo <54519381+yuta0306@users.noreply.github.com>
 2025-07-28 17:52:36 +09:00
Bailey Machiko Hirota
f7fec4a6e7 Update egs/multi_ja_en/ASR/local/utils/update_cutset_paths.py 
Co-authored-by: Yubo <54519381+yuta0306@users.noreply.github.com>
 2025-07-28 17:52:36 +09:00
Bailey Machiko Hirota
542620c4e3 Update egs/multi_ja_en/ASR/local/utils/update_cutset_paths.py 
Co-authored-by: Yubo <54519381+yuta0306@users.noreply.github.com>
 2025-07-28 17:52:36 +09:00
Bailey Machiko Hirota
310aaec3cc Update egs/multi_ja_en/ASR/local/utils/update_cutset_paths.py 
Co-authored-by: Yubo <54519381+yuta0306@users.noreply.github.com>
 2025-07-28 17:52:36 +09:00
Bailey Hirota
aee7b87adb working changes for musan mixing 2025-07-28 17:52:36 +09:00
Bailey Hirota
d5cc0301d4 attempt to fix musan paths 2025-07-28 17:52:36 +09:00
Bailey Hirota
0f700ed0b2 update musan symlinks 2025-07-28 17:52:36 +09:00
Bailey Hirota
093a035935 update musan paths 2025-07-28 17:52:36 +09:00
Bailey Hirota
4e92879751 update musan path 2025-07-28 17:52:36 +09:00
Bailey Hirota
f51621b374 resolve typos and import issues 2025-07-28 17:52:36 +09:00
Bailey Hirota
de35cc2760 remove comment 2025-07-28 17:52:36 +09:00
Bailey Hirota
5ec9389909 commenting 2025-07-28 17:52:36 +09:00
Bailey Hirota
df923f3a16 typos 2025-07-28 17:52:36 +09:00
Bailey Hirota
70a7940c95 changes to asr_datamodule for musan support 2025-07-28 17:52:36 +09:00
Kinan Martin
5f2f6843c9 make prepare.sh symlinks relative 2025-07-28 17:52:36 +09:00
Bailey Hirota
19b62c008d remove unused local scripts 2025-07-28 17:52:36 +09:00
Bailey Hirota
f6ad423398 changes to train script - no need for limiting utterance length here 2025-07-28 17:52:36 +09:00
Bailey Hirota
ddc2daaccd remove commented out codels 2025-07-28 17:52:36 +09:00