Xiaoyu Yang
a6c02a4d8c
zipformer BF16 training recipe ( #1700 )
...
Support Zipformer AMP +BF16 training
2024-08-23 09:42:22 +08:00
Yuekai Zhang
3b434fe83c
fix triton onnx export ( #1730 )
2024-08-23 09:33:46 +08:00
Yifan Yang
ad61d72dfa
Update pretrain.py
2024-08-22 18:32:33 +08:00
Yifan Yang
6357d420b7
Merge branch 'k2-fsa:master' into dev/k2ssl
2024-08-22 18:29:05 +08:00
Xiaoyu Yang
3fc06cc2b9
Support AudioSet training with weighted sampler ( #1727 )
2024-08-22 15:27:25 +08:00
Yifan Yang
f672df2a63
Update run_multi_node_multi_gpu.sh
2024-08-22 10:57:26 +08:00
Yifan Yang
6dbcdbac5d
Update pretrain.py
2024-08-22 10:55:23 +08:00
Yifan Yang
8fe6713d10
Update pretrain.py
2024-08-21 12:53:19 +08:00
Yifan Yang
eca8afcb83
Update pretrain.py
2024-08-21 12:47:45 +08:00
Yifan Yang
d0a96a601c
Update run_multi_node_multi_gpu.sh
2024-08-21 12:42:06 +08:00
yifanyeung
d025ce11ff
use lr hours in librilight ssl
2024-08-19 23:14:26 +08:00
Yifan Yang
70a1713662
Merge branch 'k2-fsa:master' into dev/k2ssl
2024-08-19 23:09:03 +08:00
Xiaoyu Yang
5952972294
Keep the custom fields in libriheavy manifest ( #1719 )
2024-08-17 13:24:38 +08:00
Yifan Yang
8b1402aab5
Merge branch 'k2-fsa:master' into dev/k2ssl
2024-08-16 20:19:58 +08:00
Yifan Yang
6ac3343ce5
fix path in README.md ( #1722 )
2024-08-16 20:13:02 +08:00
Yifan Yang
cce86a3943
Merge branch 'k2-fsa:master' into dev/k2ssl
2024-08-14 15:20:26 +08:00
Karel Vesely
1730fce688
split save_results() -> save_asr_output() + save_wer_results() ( #1712 )
...
- the idea is to support `--skip-scoring` argument passed to a decoding
script
- created for Transducer decoding (non-streaming, streaming)
- it can be done also for CTC decoding... (not yet)
- also added `--label` for extra label in `streaming_decode.py`
- and also added `set_caching_enabled(True)`, which has no effect on
librispeech, but it leads to faster runtime on DBs with long
recordings (assuming `librispeech/zipformer` scripts are the
example scripts for other setups)
2024-08-13 23:02:14 +08:00
Yifan Yeung
f26dd3ba17
support multinode multigpu
...
update
2024-08-10 22:44:32 +08:00
Your Name
8e296b7047
add librilight ssl recipe
...
update
Update ssl_datamodule.py
Update pretrain.py
Update pretrain.sh
Update pretrain.sh
Update hubert_ce.py
Update pretrain.py
2024-08-10 22:44:20 +08:00
Fangjun Kuang
3b257dd5ae
Add docker images for torch 2.4 ( #1704 )
2024-07-25 16:46:24 +08:00
Yuekai Zhang
4af81af5a6
Update Zipformer-xl 700M Results on multi-hans-zh ( #1694 )
...
* add blank penalty
* update zipformer-xl results
* fix typo
2024-07-18 21:05:59 +08:00
zzasdf
11151415f3
fix error in accum_grad ( #1693 )
2024-07-17 17:47:43 +08:00
Fangjun Kuang
2e13298717
Refactor ctc greedy search. ( #1691 )
...
Use torch.unique_consecutive() to avoid reinventing the wheel.
2024-07-15 12:01:47 +08:00
Zengwei Yao
d47c078286
add decoding method of ctc-greedy-search in zipformer recipe ( #1690 )
2024-07-14 17:30:13 +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
Ziwei Li
f6febd658e
"-" replace "_" fix writing error ( #1687 )
2024-07-12 14:42:00 +08:00
Teo Wen Shen
19048e155b
Cast grad_scale in whiten to float ( #1663 )
...
* cast grad_scale in whiten to float
* fix cast in zipformer_lora
2024-07-11 15:12:30 +08:00
Yifan Yang
d65187ec52
Small fix ( #1686 )
2024-07-11 14:45:35 +08:00
Zengwei Yao
785f3f0bcf
Update RESULTS.md, adding results and model links of zipformer-small/medium CTC/AED models ( #1683 )
2024-07-09 20:04:47 +08:00
Yuekai Zhang
1c3d992a39
Update results using Zipformer-large on multi-hans-zh ( #1679 )
2024-07-09 09:57:52 +08:00
zr_jin
2d64228efa
Update attention_decoder.py ( #1681 )
2024-07-06 09:01:34 +08:00
zr_jin
325a825841
Update requirements-ci.txt ( #1682 )
2024-07-06 09:01:19 +08:00
Zengwei Yao
f76afff741
Support CTC/AED option for Zipformer recipe ( #1389 )
...
* add attention-decoder loss option for zipformer recipe
* add attention-decoder-rescoring
* update export.py and pretrained_ctc.py
* update RESULTS.md
2024-07-05 20:19:18 +08:00
Yifan Yang
cbcac23d26
Fix typos, remove unused packages, normalize comments ( #1678 )
2024-07-04 14:19:45 +08:00
Yuekai Zhang
ebbd396c2b
update multi-hans-zh whisper-qwen-7b results ( #1677 )
...
* update qwen-7b whisper encoder results
* update qwen-7b whisper encoder results
* fix typo
2024-07-03 19:55:12 +08:00
Manix
eaab2c819f
Zipformer Onnx FP16 ( #1671 )
...
Signed-off-by: manickavela29 <manickavela1998@gmail.com>
2024-06-27 16:08:24 +08:00
Fangjun Kuang
b594a3875b
Add CI for non-streaming zipformer about ksponspeech ( #1667 )
2024-06-24 16:20:46 +08:00
Seung Hyun Lee
031f892796
Reformat by black non-streaming zipformer recipe for ksponspeech ( #1665 )
2024-06-24 15:28:09 +08:00
Seung Hyun Lee
6f102d3470
Add non-streaming Zipformer recipe for KsponSpeech ( #1664 )
2024-06-24 14:07:37 +08:00
Fangjun Kuang
3059eb4511
Fix doc URLs ( #1660 )
2024-06-21 11:10:14 +08:00
Yuekai Zhang
ff2bef9e50
update multi-hans whisper-qwen-1.5b results ( #1657 )
2024-06-19 11:10:31 +08:00
Seung Hyun Lee
2e05663fbb
Add prepare.sh for KsponSpeech recipe. ( #1656 )
2024-06-18 16:54:39 +08:00
Fangjun Kuang
1f5c0a87b9
Add CI for ksponspeech ( #1655 )
2024-06-16 19:15:09 +08:00
Seung Hyun Lee
c13c7aa30b
Add Streaming Zipformer-Transducer recipe for KsponSpeech ( #1651 )
2024-06-16 16:20:44 +08:00
Yuekai Zhang
890eeec82c
Add qwen-audio style model training: using whisper + qwen2 ( #1652 )
2024-06-16 12:14:44 +08:00
Triplecq
3b40d9bbb1
Zipformer recipe for ReazonSpeech ( #1611 )
...
* Add first cut at ReazonSpeech recipe
This recipe is mostly based on egs/csj, but tweaked to the point that
can be run with ReazonSpeech corpus.
Signed-off-by: Fujimoto Seiji <fujimoto@ceptord.net>
---------
Signed-off-by: Fujimoto Seiji <fujimoto@ceptord.net>
Co-authored-by: Fujimoto Seiji <fujimoto@ceptord.net>
Co-authored-by: Chen <qc@KDM00.cm.cluster>
Co-authored-by: root <root@KDA01.cm.cluster>
2024-06-13 14:19:03 +08:00
Yuekai Zhang
d5be739639
add distill whisper results ( #1648 )
2024-06-13 00:20:04 +08:00
Fangjun Kuang
13f55d0735
Add merge_tokens for ctc forced alignment ( #1649 )
2024-06-12 17:45:13 +08:00
Fangjun Kuang
ec0389a3c1
Add doc about FST-based CTC forced alignment. ( #1482 )
2024-06-12 17:36:57 +08:00
Daniel Povey
4d5c1f2e60
Remove inf from stored stats ( #1647 )
2024-06-10 22:41:54 +08:00
