jinzr
91044348bb
args fixed
2023-08-11 20:41:44 +08:00
zr_jin
2f4a0fd9fd
fixed a formatting issue
2023-07-25 09:21:41 +08:00
zr_jin
ab7688e556
Merge branch 'k2-fsa:master' into dev_export_diff_acoustic_units
2023-07-24 23:56:00 +08:00
jinzr
eccd4964b7
Merge branch 'dev_export_diff_acoustic_units' of https://github.com/JinZr/icefall into dev_export_diff_acoustic_units
2023-07-24 23:55:18 +08:00
jinzr
7e35a3b906
removed batch_name to fix a KeyError with "uttid" ( #1172 )
2023-07-24 23:55:16 +08:00
jinzr
0816be86ae
updates for the zipformer_mmi and transducer_stateless recipes
2023-07-24 23:54:35 +08:00
jinzr
e0e8db3c91
updates for the pruned_transducer_stateless recipes
2023-07-24 23:54:35 +08:00
zr_jin
c03c011230
applied PR #1152 to other recipes
2023-07-24 23:54:35 +08:00
zr_jin
3cfd75c4db
fixed CI tests
2023-07-24 23:54:35 +08:00
zr_jin
7e74c2d38b
fixed a formatting issue
2023-07-24 23:54:35 +08:00
jinzr
8dcb6da8c7
updated the pruned_stateless_emformer_rnnt2 recipe
2023-07-24 23:54:35 +08:00
jinzr
d6f4805226
updated the lstm_transducer_stateless recipes
...
also revoked previous changes in conformer_ctc3/jit_pretrained.py
2023-07-24 23:54:35 +08:00
jinzr
64393e798f
updated the conv_emformer_transducer_stateless recipes
2023-07-24 23:54:35 +08:00
jinzr
fb820982aa
updated CI test for conformer_ctc3 recipe
2023-07-24 23:54:35 +08:00
jinzr
13bcfda1e4
updated all conformer_ctc* recipes to use tokens.txt in export.py and pretrained.py
2023-07-24 23:54:35 +08:00
jinzr
54c023034e
Update pretrained.py
2023-07-24 23:54:35 +08:00
jinzr
9e79cf9f68
update the conformer_ctc recipe to replace lang-dir with tokens
2023-07-24 23:54:35 +08:00
jinzr
2edc3081d6
removed unused git lfs commands from librispeech zipformer recipe
2023-07-24 23:54:35 +08:00
zr_jin
5c0dfa52d2
Update egs/librispeech/ASR/pruned_transducer_stateless7/export-onnx.py
...
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
2023-07-24 23:54:35 +08:00
jinzr
2aaa7ff2af
fixed minor issues
...
1. removed `export2.py` from aishell recipe
2. removed `git lfs` commands for pulling `tokens.txt` from `test-onnx-export.sh`
3. applied #1152 to `export-onnx-streaming.py` and `export-onnx.py`
2023-07-24 23:54:35 +08:00
jinzr
d3f6a8a392
Update onnx_pretrained-streaming.py
2023-07-24 23:54:35 +08:00
jinzr
c37ca4dd66
added tests for zipformer streaming & non-streaming export
...
details are listed below:
1. updated `git lfs` command in `export-onnx.py` and `onnx_pretrained-streaming.py`;
2. added rounding code to `export.py` for case where `params.avg == 1`.
2023-07-24 23:54:35 +08:00
jinzr
9fe1125348
removed deprecated param onnx
2023-07-24 23:54:35 +08:00
jinzr
fa90d83bf0
fixed CI
2023-07-24 23:54:35 +08:00
jinzr
83e26a63e3
applied isort and removed unused imports
2023-07-24 23:54:35 +08:00
jinzr
a572f441eb
fixed a formatting issue
2023-07-24 23:54:35 +08:00
jinzr
ccb6031853
moved num_tokens to utils.py
...
moved `num_tokens` to `icefall/utils.py` to reduce code redundancy
2023-07-24 23:54:35 +08:00
jinzr
06cb1346ac
fixed file permission
2023-07-24 23:54:35 +08:00
jinzr
f1fe409dee
Update export-onnx.py
...
updated `export-onnx.py` to apply the same change as in [#1152 ](https://github.com/k2-fsa/icefall/pull/1152 )
2023-07-24 23:54:35 +08:00
jinzr
aa2fc799c6
Update export-onnx.py
...
updated `export-oonx.py` to accept `tokens.txt` for blank_id and vocab_size
2023-07-24 23:54:35 +08:00
jinzr
cca02ae861
update for the pruned_transducer_stateless7 for aishell and librispeech
2023-07-24 23:54:35 +08:00
jinzr
fe5ffca1c1
init commit
...
init commit for an unified version of `export.py` and `pretrained.py`
2023-07-24 23:54:35 +08:00
jinzr
71351291a8
updates for the zipformer_mmi and transducer_stateless recipes
2023-07-24 23:48:36 +08:00
jinzr
f13f0b990e
updates for the pruned_transducer_stateless recipes
2023-07-24 23:25:40 +08:00
zr_jin
bbeca5ccd4
applied PR #1152 to other recipes
2023-07-24 19:19:34 +08:00
zr_jin
8ad6ce4313
fixed CI tests
2023-07-24 19:12:07 +08:00
zr_jin
a4e3186e4f
fixed a formatting issue
2023-07-23 12:24:25 +08:00
jinzr
20d4031e9b
updated the pruned_stateless_emformer_rnnt2 recipe
2023-07-23 01:00:34 +08:00
jinzr
696024abab
updated the lstm_transducer_stateless recipes
...
also revoked previous changes in conformer_ctc3/jit_pretrained.py
2023-07-23 00:51:51 +08:00
jinzr
96f8904ce7
updated the conv_emformer_transducer_stateless recipes
2023-07-23 00:12:54 +08:00
zr_jin
4ab7d61008
removed batch_name to fix a KeyError with "uttid" ( #1172 )
2023-07-15 12:39:32 +08:00
jinzr
e515329d83
updated CI test for conformer_ctc3 recipe
2023-07-13 15:40:52 +08:00
jinzr
a8ace5bb61
updated all conformer_ctc* recipes to use tokens.txt in export.py and pretrained.py
2023-07-13 15:32:43 +08:00
jinzr
2459ea0c3e
Update pretrained.py
2023-07-13 14:19:22 +08:00
jinzr
40af5f2828
update the conformer_ctc recipe to replace lang-dir with tokens
2023-07-13 14:19:14 +08:00
marcoyang1998
5ed6fc0e6d
add sym link ( #1170 )
2023-07-12 15:37:14 +08:00
Desh Raj
41b16d7838
SURT recipe for AMI and ICSI ( #1133 )
...
* merge upstream
* add SURT model and training
* add libricss decoding
* add chunk width randomization
* decode SURT with libricss
* initial commit for zipformer_ctc
* remove unwanted changes
* remove changes to other recipe
* fix zipformer softlink
* fix for JIT export
* add missing file
* fix symbolic links
* update results
* clean commit for SURT recipe
* training libricss surt model
* remove unwanted files
* remove unwanted changes
* remove changes in librispeech
* change some files to symlinks
* remove unwanted changes in utils
* add export script
* add README
* minor fix in README
* add assets for README
* replace some files with symlinks
* remove unused decoding methods
* initial commit for SURT AMI recipe
* fix symlink
* add train + decode scripts
* add missing symlink
* change files to symlink
* change file type
2023-07-08 23:01:51 +08:00
jinzr
208c30c160
removed unused git lfs commands from librispeech zipformer recipe
2023-07-07 15:44:46 +08:00
zr_jin
7db7a7d36d
Update egs/librispeech/ASR/pruned_transducer_stateless7/export-onnx.py
...
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
2023-07-07 15:34:33 +08:00
jinzr
bd69685e03
fixed minor issues
...
1. removed `export2.py` from aishell recipe
2. removed `git lfs` commands for pulling `tokens.txt` from `test-onnx-export.sh`
3. applied #1152 to `export-onnx-streaming.py` and `export-onnx.py`
2023-07-07 15:31:57 +08:00
