Xiaoyu Yang
4b10b7cde3
Merge 1aa2a930b41b7fc51c7b9383c7c022a6592213b6 into 34fc1fdf0d8ff520e2bb18267d046ca207c78ef9
2025-08-04 12:21:44 +08:00
Teo Wen Shen
da87e7fc99
add weights_only=False to torch.load ( #1984 )
2025-07-10 15:27:08 +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
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
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
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
zr_jin
1814bbb0e7
typo fixed ( #1334 )
2023-10-25 00:03:33 +08:00
zr_jin
d2bd0933b1
Compatibility with the latest Lhotse ( #1314 )
2023-10-17 21:22:32 +08:00
zr_jin
ef658d691e
fixes for init value of diagnostics.TensorDiagnosticOptions
( #1269 )
...
* fixes for `diagnostics`
Replace `2 ** 22` with `512` as the default value of `diagnostics.TensorDiagnosticOptions`
also black formatted some scripts
* fixed formatting issues
2023-09-24 17:06:47 +08:00
docterstrange
fba1710622
modify tal_csasr recipe ( #1252 )
...
Co-authored-by: zss11 <zss11@d3-hpc-sjtu-test-001.cm.cluster>
2023-09-14 09:58:28 +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
Wei Kang
bccd20d978
Traning with byte level BPE (TAL_CSASR) ( #1033 )
...
* Add byte level bpe tal_csasr recipe
* Minor fixes to decoding and exporting
* Fix prepare.sh
* Update results
2023-05-16 12:44:52 +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
marcoyang
1aa2a930b4
fix codestyle
2023-02-14 16:23:42 +08:00
marcoyang
7d217e15ab
updates pretrained*.py
2023-02-14 16:11:05 +08:00
marcoyang
f6f29b9321
reformat
2023-02-14 15:52:54 +08:00
marcoyang
56c2474c0d
fix
2023-02-13 18:19:52 +08:00
marcoyang
a57c54124a
fix code style
2023-02-13 17:55:34 +08:00
marcoyang
dae3a310f4
fix code style
2023-02-13 17:49:32 +08:00
marcoyang
8fb81e27cb
lstm_transducer_stateless3/streaming-ncnn-decode.py
2023-02-13 17:48:46 +08:00
marcoyang
142ea421b0
small fix
2023-02-13 16:21:21 +08:00
marcoyang
6018f222df
update decoding files
2023-02-13 16:21:01 +08:00
marcoyang
b39ac0207e
add necessary files
2023-02-13 16:20:42 +08:00
marcoyang
461fe91dc3
copy file
2023-02-13 14:09:53 +08:00
marcoyang
b3fa59d68a
Merge branch 'master' of github.com:marcoyang1998/icefall into add_lstm_transducer
2023-02-13 12:47:34 +08:00
marcoyang
eb9a5267a9
add args in streaming-ncnn-decode.py
2023-02-13 12:45:47 +08:00
marcoyang
c689b018d7
add new files
2023-02-13 12:45:22 +08:00
marcoyang
bff0822ffa
small fix
2023-02-13 12:44:52 +08:00
marcoyang
04ce87e307
add export
2023-02-13 12:44:09 +08:00
marcoyang
8f5fcb2f52
add files
2023-02-13 12:18:58 +08:00
marcoyang
4d4a2c08f7
fix export for ncnn
2023-02-13 12:04:29 +08:00
marcoyang
72f5c5e17f
add file
2023-02-13 11:54:23 +08:00
marcoyang
5596da0704
add export ncnn
2023-02-13 10:46:18 +08:00
KajiMaCN
57604aac34
fix tal_csasr data pre-processing ( #898 )
2023-02-10 21:28:19 +08:00
marcoyang
7556811d64
modify train.py
2023-02-10 16:49:57 +08:00
marcoyang
d1a0668f68
add soft links
2023-02-10 16:41:59 +08:00
marcoyang
3558556906
copy file and soft links
2023-02-10 16:40:18 +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
d1f16a04bd
fix type hints for decode.py ( #623 )
2022-10-18 06:56:12 +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