mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-08 09:32:20 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,219 Commits 5 Branches 3 Tags
Commit Graph

55 Commits

Author SHA1 Message Date
Fangjun Kuang
34fc1fdf0d
Fix transformer decoder layer (#1995) 2025-07-18 20:12:29 +08:00
Teo Wen Shen
da87e7fc99
add weights_only=False to torch.load (#1984) 2025-07-10 15:27:08 +08:00
Yifan Yang
89728dd4f8
Refactor data preparation for GigaSpeech recipe (#1986) 2025-07-10 11:17:37 +08:00
Fangjun Kuang
fba5e67d5e
Fix CI tests. (#1974) 
- Introduce unified AMP helpers (create_grad_scaler, torch_autocast) to handle 
  deprecations in PyTorch ≥2.3.0

- Replace direct uses of torch.cuda.amp.GradScaler and torch.cuda.amp.autocast 
  with the new utilities across all training and inference scripts

- Update all torch.load calls to include weights_only=False for compatibility with 
  newer PyTorch versions
 2025-07-01 13:47:55 +08:00
Wei Kang
f80a2ee110
Decrease num_buckets & remove shuffle_buffer_size (#1955) 2025-06-19 12:26:37 +08:00
Fangjun Kuang
d4d4f281ec
Revert "Replace deprecated pytorch methods (#1814)" (#1841) 
This reverts commit 3e4da5f78160d3dba3bdf97968bd7ceb8c11631f.
 2024-12-18 16:49:57 +08:00
Li Peng
3e4da5f781
Replace deprecated pytorch methods (#1814) 
* Replace deprecated pytorch methods

- torch.cuda.amp.GradScaler(...) => torch.amp.GradScaler("cuda", ...)
- torch.cuda.amp.autocast(...) => torch.amp.autocast("cuda", ...)

* Replace `with autocast(...)` with `with autocast("cuda", ...)`


Co-authored-by: Li Peng <lipeng@unisound.ai>
 2024-12-16 10:24:16 +08:00
Fangjun Kuang
f23c8ce9dd
Fix CI test for gigaspeech (#1787) 2024-10-29 15:50:49 +08:00
Yifan Yang
cea0dbe7b1
fix gigaspeech_prepare.sh (#1734) 2024-08-28 12:15:01 +08:00
Zengwei Yao
334beed2af
fix usages of returned losses after adding attention-decoder in zipformer (#1689) 2024-07-12 16:50:58 +08:00
zr_jin
eb132da00d
additional instruction for the grad_scale is too small error (#1550) 2024-03-14 11:33:49 +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
Xiaoyu Yang
777074046d
Fine-tune recipe for Zipformer (#1484) 
1. support finetune zipformer
2. update the usage; set a very large batch count
 2024-02-06 18:25:43 +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
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
Fangjun Kuang
79a42148db
Add CI test to cover zipformer/train.py (#1424) 2023-12-23 00:38:36 +08:00
zr_jin
23913f6afd
Minor refinements for some stale but recently merged PRs (#1354) 
* incorporate https://github.com/k2-fsa/icefall/pull/1269

* incorporate https://github.com/k2-fsa/icefall/pull/1301

* black formatted

* incorporate https://github.com/k2-fsa/icefall/pull/1162

* black formatted
 2023-10-31 10:28:20 +08:00
zr_jin
1814bbb0e7
typo fixed (#1334) 2023-10-25 00:03:33 +08:00
Yifan Yang
416852e8a1
Add Zipformer recipe for GigaSpeech (#1254) 
Co-authored-by: Yifan Yang <yifanyeung@qq.com>
Co-authored-by: yfy62 <yfy62@d3-hpc-sjtu-test-005.cm.cluster>
 2023-10-21 15:36:59 +08:00
zr_jin
d2bd0933b1
Compatibility with the latest Lhotse (#1314) 2023-10-17 21:22:32 +08:00
zr_jin
7cc2dae940
Fixes to incorporate with the latest Lhotse release (#1249) 2023-09-13 12:39:49 +08:00
Fangjun Kuang
7b0afbdc16
Remove cur_batch_idx (#1102) 2023-05-30 14:49:54 +08:00
marcoyang1998
57d6482a79
Streaming Zipformer with multi-dataset (#984) 
* modify train.py

* add right padding option in decode.py

* update RESULTS.md
 2023-04-21 15:43:28 +08:00
Yifan Yang
81d386ef3e
Add compute_ppl.py and ngram_entropy_pruning.py (#1013) 2023-04-20 12:27:43 +08:00
Yifan Yang
6434c8eadc
Add averaged model && change start from 0 to 1 && fix typo for gigaspeech (#990) 
* Add averaged model && change start from 0 to 1 && fix typo

* Update train.py

* Set use-averaged-model False for BC

---------

Co-authored-by: yifanyang <yifanyeung@yifanyangs-MacBook-Pro.local>
 2023-04-09 20:53:47 +08:00
Yifan Yang
180c7c2b7a
Add UniqueLexicon for gigaspeech (#982) 2023-04-03 12:39:34 +08:00
Yifan Yang
12a222aa4b
Fix comments on the usage of train.py (#981) 2023-04-02 16:32:43 +08:00
Fangjun Kuang
f5de2e90c6
Fix style issues. (#937) 2023-03-08 22:56:04 +08:00
pehonnet
07243d136a
remove key from result filename (#936) 
Co-authored-by: pe-honnet <pe.honnet@telepathy.ai>
 2023-03-08 21:06:07 +08:00
Yifan Yang
070c77e724
Add Blankskip to Zipformer+CTC (#730) 
* init files

* add ctc as auxiliary loss and ctc_decode.py

* tuning the scalar of HLG score for 1best, nbest and nbest-oracle

* rename to pruned_transducer_stateless7_ctc

* fix doc

* fix bug, recover the hlg scores

* modify ctc_decode.py, move out the hlg scale

* fix hlg_scale

* add export.py and pretrained.py, and so on

* upload files, update README.md and RESULTS.md

* add CI test

* update .gitignore

* create symlinks

* Add Blank Skip to Zipformer+CTC

* Add warmup to blank skip

* Add warmup to blank skip

* Add __init__.py

* Add parameters_names to Adam

* Add warmup to blank skip

* Modify frame_reducer

* Modify frame_reducer

* Add Blank Skip to decode.

* Add ctc_decode.py

* Add blank skip to Zipformer+CTC

* process conflict

* process conflict

* modify ctc_guild_decode_bk.py

* modify Lconv

* produce the conflict

* Add export.py

* finish export

* fix for running black

* Add ci test

* Add ci-test

* chmod

* chmod

* fix bug for ci-test

* fix bug for ci-test

* fix bug for ci-test

* rename the dirname

* rename the dirname

* change dirname

* change dirname

* fix notes

* add pretrained.py

* add pretrained.py

* add pretrained.py

* add pretrained.py

* add pretrained.py

* add pretrained.py

* fix

* fix

* fix

* finished

* add the Copyright info and notes

Co-authored-by: Zengwei Yao <yaozengwei@outlook.com>
Co-authored-by: yifanyang <yifanyeung@yifanyangs-MacBook-Pro.local>
 2022-12-21 17:41:31 +08:00
marcoyang
53454701cb fix segmentation fault 2022-11-22 11:39:21 +08:00
Desh Raj
d31db01037 manual correction of black formatting 2022-11-17 14:18:05 -05:00
Desh Raj
107df3b115 apply black on all files 2022-11-17 09:42:17 -05:00
Fangjun Kuang
60317120ca
Revert "Apply new Black style changes" 2022-11-17 20:19:32 +08:00
Desh Raj
d110b04ad3 apply new black formatting to all files 2022-11-16 13:06:43 -05:00
Fangjun Kuang
aa7bae1ecd
fix decode.py for conformer_ctc in gigaspeech (#688) 2022-11-16 19:58:28 +08:00
Fangjun Kuang
d1f16a04bd
fix type hints for decode.py (#623) 2022-10-18 06:56:12 +08:00
LIyong.Guo
923b60a7c6
padding zeros (#591) 2022-09-28 21:20:33 +08:00
Fangjun Kuang
e18fa78c3a
Check that read_manifests_if_cached returns a non-empty dict. (#555) 2022-08-28 11:50:11 +08:00
Wei Kang
5c17255eec
Sort results to make it more convenient to compare decoding results (#522) 
* Sort result to make it more convenient to compare decoding results

* Add cut_id to recognition results

* add cut_id to results for all recipes

* Fix torch.jit.script

* Fix comments

* Minor fixes

* Fix torch.jit.tracing for Pytorch version before v1.9.0
 2022-08-12 07:12:50 +08:00
Fangjun Kuang
ec69967584
Set overwrite=True when extracting features in batches. (#487) 2022-07-29 11:17:19 +08:00
Jun Wang
d792bdc9bc
fix typo (#445) 2022-06-25 11:00:53 +08:00
Mingshuang Luo
998091ef52
do some changes for export.py (#437) 2022-06-20 14:57:08 +08:00
Fangjun Kuang
dbda1644b5
Replace load_manifest_lazy with load_manifest for MUSAN. (#412) 2022-06-09 11:42:18 +08:00
Fangjun Kuang
f1abce72f8
Use jsonl for CutSet in the LibriSpeech recipe. (#397) 
* Use jsonl for cutsets in the librispeech recipe.

* Use lazy cutset for all recipes.

* More fixes to use lazy CutSet.

* Remove force=True from logging to support Python < 3.8

* Minor fixes.

* Fix style issues.
 2022-06-06 10:19:16 +08:00
Ewald Enzinger
8c5722de8c
[egs] Add prefix when reading manifests due to recent lhotse changes (#382) 
* [egs] Add prefix when reading manifests due to recent lhotse changes

* Fix wenetspeech

* Fix style issues
 2022-05-23 23:37:35 +08:00
Daniel Povey
4e23fb2252
Improve diagnostics code memory-wise and accumulate more stats. (#373) 
* Update diagnostics, hopefully print more stats.

# Conflicts:
#	egs/librispeech/ASR/pruned_transducer_stateless4b/train.py

* Remove memory-limit options arg

* Remove unnecessary option for diagnostics code, collect on more batches
 2022-05-19 11:45:59 +08:00