yaozengwei
2d8b07ef3a
delete two dir
2022-05-15 17:10:47 +08:00
yaozengwei
9828b8f628
fix decode.py
2022-05-15 16:25:34 +08:00
yaozengwei
27558858a3
minor fix of doc
2022-05-15 14:20:17 +08:00
yaozengwei
2142fca8f8
add remaining files
2022-05-15 12:12:25 +08:00
yaozengwei
20a23d13ce
minor fix
2022-05-15 12:11:05 +08:00
yaozengwei
8b60d43ead
add Emformer module
2022-05-14 23:18:16 +08:00
yaozengwei
b265a5c875
add EmformerEncoderLayer module
2022-05-14 13:10:44 +08:00
yaozengwei
3360dc5afc
add conv module
2022-05-13 22:23:39 +08:00
yaozengwei
2cfb2f58f0
add emformer attention module
2022-05-13 17:07:40 +08:00
yaozengwei
d74e2e8e07
add relative position encoding
2022-05-12 21:27:32 +08:00
yaozengwei
deac02ee5e
Merge branch 'master' into emformer_pos_enc_conv
2022-05-12 18:07:32 +08:00
yaozengwei
6a7b69168c
minor fix
2022-05-12 17:14:04 +08:00
Fangjun Kuang
bc284e88e6
Run decode.py in GitHub actions. ( #356 )
2022-05-10 14:51:34 +08:00
yaozengwei
61ecd3764d
minor fix of doc of pos_emb
2022-05-10 12:15:14 +08:00
yaozengwei
5de9d0a19a
add tanh_on_mem option
2022-05-10 11:48:22 +08:00
yaozengwei
e3a29b17f3
minor refactor of emformer codes
2022-05-10 11:15:44 +08:00
yaozengwei
aff7c4ee3c
minor fix of conv-emformer
2022-05-09 16:46:51 +08:00
yaozengwei
6c5fd6f648
minor fix of train.py
2022-05-09 16:41:46 +08:00
yaozengwei
d0cea4f2f8
move encoder_pos
2022-05-09 16:27:56 +08:00
yaozengwei
8e6a51edaa
support positional encoding for conv-emformer
2022-05-09 15:39:27 +08:00
Zengwei Yao
20f092e709
Support decoding with averaged model when using --iter ( #353 )
...
* support decoding with averaged model when using --iter
* minor fix
* monir fix of copyright date
2022-05-07 13:09:11 +08:00
Zengwei Yao
c059ef3169
Keep model_avg on cpu ( #348 )
...
* keep model_avg on cpu
* explicitly convert model_avg to cpu
* minor fix
* remove device convertion for model_avg
* modify usage of the model device in train.py
* change model.device to next(model.parameters()).device for decoding
* assert params.start_epoch>0
* assert params.start_epoch>0, params.start_epoch
2022-05-07 10:42:34 +08:00
Fangjun Kuang
32f05c00e3
Save batch to disk on exception. ( #350 )
2022-05-06 17:49:40 +08:00
Zengwei Yao
00c48ec1f3
Model average ( #344 )
...
* First upload of model average codes.
* minor fix
* update decode file
* update .flake8
* rename pruned_transducer_stateless3 to pruned_transducer_stateless4
* change epoch number counter starting from 1 instead of 0
* minor fix of pruned_transducer_stateless4/train.py
* refactor the checkpoint.py
* minor fix, update docs, and modify the epoch number to count from 1 in the pruned_transducer_stateless4/decode.py
* update author info
* add docs of the scaling in function average_checkpoints_with_averaged_model
2022-05-05 21:20:04 +08:00
Fangjun Kuang
8635fb4334
Fix decoding for gigaspeech in the libri + giga setup. ( #345 )
2022-05-05 20:58:46 +08:00
Fangjun Kuang
e1c3e98980
Save batch to disk on OOM. ( #343 )
...
* Save batch to disk on OOM.
* minor fixes
* Fixes after review.
* Fix style issues.
2022-05-05 15:09:23 +08:00
yaozengwei
50fe100f50
support position encoding for emformer
2022-05-04 20:11:50 +08:00
Fangjun Kuang
6af15914fa
Validate generated manifest files. ( #338 )
2022-05-03 07:02:54 +08:00
Fangjun Kuang
6dc2e04462
Update results. ( #340 )
...
* Update results.
* Typo fixes.
2022-04-29 15:49:45 +08:00
Fangjun Kuang
ac84220de9
Modified conformer with multi datasets ( #312 )
...
* Copy files for editing.
* Use librispeech + gigaspeech with modified conformer.
* Support specifying number of workers for on-the-fly feature extraction.
* Feature extraction code for GigaSpeech.
* Combine XL splits lazily during training.
* Fix warnings in decoding.
* Add decoding code for GigaSpeech.
* Fix decoding the gigaspeech dataset.
We have to use the decoder/joiner networks for the GigaSpeech dataset.
* Disable speed perturbe for XL subset.
* Compute the Nbest oracle WER for RNN-T decoding.
* Minor fixes.
* Minor fixes.
* Add results.
* Update results.
* Update CI.
* Update results.
* Fix style issues.
* Update results.
* Fix style issues.
2022-04-29 15:40:30 +08:00
Fangjun Kuang
caab6cfd92
Support specifying iteration number of checkpoints for decoding. ( #336 )
...
See also #289
2022-04-28 14:09:22 +08:00
pehonnet
9a98e6ced6
fix fp16 option in example usage ( #332 )
2022-04-25 18:51:53 +08:00
yaozengwei
b612b3dc50
Merge branch 'streaming_decoding' into streaming_new
2022-04-22 17:04:17 +08:00
whsqkaak
d766dc5aee
Fix some typos. ( #329 )
2022-04-22 15:54:59 +08:00
yaozengwei
ece99a862b
Minor fix for transducer_emformer/streaming_feature_extractor.py
2022-04-22 11:23:23 +08:00
yaozengwei
e97c9fbdbf
Sorted imports for transducer_emformer/streaming_feature_extractor.py
2022-04-22 11:04:50 +08:00
yaozengwei
83a5052cf0
Merge remote-tracking branch 'k2-fsa/master' into streaming_decoding_new
2022-04-21 20:40:27 +08:00
yaozengwei
d20a852f61
Fixed docs.
2022-04-21 19:55:30 +08:00
yaozengwei
cf0ce8db32
Fixed streaming decoding codes for emformer model.
2022-04-21 19:48:35 +08:00
yaozengwei
24db3a1934
update emformer_pruned_transducer_stateless/emformer.py
2022-04-20 14:21:45 +08:00
Fangjun Kuang
3607c516d6
Update results for torchaudio RNN-T. ( #322 )
2022-04-20 11:15:10 +08:00
yaozengwei
42f8afd264
Merge branch 'streaming_decoding' into streaming
2022-04-20 11:10:53 +08:00
yaozengwei
e74654c2a2
Formatted imports.
2022-04-19 22:05:14 +08:00
yaozengwei
5228b44de7
Support modified beam search decoding for streaming inference with Emformer model.
2022-04-19 22:00:47 +08:00
Fangjun Kuang
fce7f3cd9a
Support computing RNN-T loss with torchaudio ( #316 )
2022-04-19 18:47:13 +08:00
yaozengwei
328ad280a4
Support state stacking and unstacking operations for emformer_pruned_transducer_stateless/emformer.py
2022-04-19 17:58:51 +08:00
Wei Kang
021c79824e
Add LG decoding ( #277 )
...
* Add LG decoding
* Add log weight pushing
* Minor fixes
2022-04-19 17:23:46 +08:00
yaozengwei
b343cb51dc
Merge remote-tracking branch 'k2-fsa/streaming' into streaming_new
2022-04-18 14:48:36 +08:00
Fangjun Kuang
0f45356ee6
Add streaming feature extractor. ( #302 )
...
* Add streaming feature extractor.
* Parallel streaming decode with greedy search.
* Fix typos.
* Use torch.stack() to replace torch.cat()
2022-04-18 10:38:56 +08:00
yaozengwei
df7919f4bf
update test functions for conv_emformer_transducer/emformer.py
2022-04-14 19:16:30 +08:00
