mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 18:12:19 +00:00
Code Issues Packages Projects Releases Wiki Activity
210 Commits 5 Branches 3 Tags
Commit Graph

91 Commits

Author SHA1 Message Date
Daniel Povey
a392cb9fbc Reduce initial scaling of modules 2022-03-12 16:53:03 +08:00
Daniel Povey
ca8cf2a73b Another rework, use scales on linear/conv 2022-03-12 15:38:13 +08:00
Daniel Povey
2d3a76292d Set scaling on SwishExpScale 2022-03-11 20:12:45 +08:00
Daniel Povey
98156711ef Introduce in_scale=0.5 for SwishExpScale 2022-03-11 19:07:34 +08:00
Daniel Povey
a0d5e2932c Reduce min_abs from 0.5 to 0.2 2022-03-11 18:17:49 +08:00
Daniel Povey
bec33e6855 init 1st conv module to smaller variance 2022-03-11 16:37:17 +08:00
Daniel Povey
bcf417fce2 Change max_factor in DerivBalancer from 0.025 to 0.01; fix scaling code. 2022-03-11 14:47:46 +08:00
Daniel Povey
137eae0b95 Reduce max_factor to 0.01 2022-03-11 14:42:17 +08:00
Daniel Povey
e3e14cf7a4 Change min-abs threshold from 0.2 to 0.5 2022-03-11 14:16:33 +08:00
Daniel Povey
76560f255c Add min-abs-value 0.2 2022-03-10 23:48:46 +08:00
Daniel Povey
2fa9c636a4 use nonzero threshold in DerivBalancer 2022-03-10 23:24:55 +08:00
Daniel Povey
b55472bb42 Replace most normalizations with scales (still have norm in conv) 2022-03-10 14:43:54 +08:00
Daniel Povey
059b57ad37 Add BasicNorm module 2022-03-10 14:32:05 +08:00
Daniel Povey
e2ace9d545 Replace norm on input layer with scale of 0.1. 2022-03-07 11:24:04 +08:00
Daniel Povey
a37d98463a Restore ConvolutionModule to state before changes; change all Swish,Swish(Swish) to SwishOffset. 2022-03-06 11:55:02 +08:00
Daniel Povey
8a8b81cd18 Replace relu with swish-squared. 2022-03-05 22:21:42 +08:00
Daniel Povey
5f2c0a09b7 Convert swish nonlinearities to ReLU 2022-03-05 16:28:24 +08:00
Daniel Povey
65b09dd5f2 Double the threshold in brelu; slightly increase max_factor. 2022-03-05 00:07:14 +08:00
Daniel Povey
6252282fd0 Add deriv-balancing code 2022-03-04 20:19:11 +08:00
Daniel Povey
eb3ed54202 Reduce scale from 50 to 20 2022-03-04 15:56:45 +08:00
Daniel Povey
7e88999641 Increase scale from 20 to 50. 2022-03-04 14:31:29 +08:00
Daniel Povey
3207bd98a9 Increase scale on Scale from 4 to 20 2022-03-04 13:16:40 +08:00
Daniel Povey
3d9ddc2016 Fix backprop bug 2022-03-04 12:29:44 +08:00
Daniel Povey
bc6c720e25 Combine ExpScale and swish for memory reduction 2022-03-04 10:52:05 +08:00
Daniel Povey
23b3aa233c Double learning rate of exp-scale units 2022-03-04 00:42:37 +08:00
Daniel Povey
5c177fc52b pelu_base->expscale, add 2xExpScale in subsampling, and in feedforward units. 2022-03-03 23:52:03 +08:00
Daniel Povey
3fb559d2f0 Add baseline for the PeLU expt, keeping only the small normalization-related changes. 2022-03-02 18:27:08 +08:00
Daniel Povey
9ed7d55a84 Small bug fixes/imports 2022-03-02 16:34:55 +08:00
Daniel Povey
9d1b4ae046 Add pelu to this good-performing setup.. 2022-03-02 16:33:27 +08:00
Piotr Żelasko
1731cc37bb Black 2022-01-24 10:20:22 -05:00
Piotr Żelasko
f92c24a73a
Merge branch 'master' into feature/libri-conformer-phone-ctc 2022-01-24 10:18:56 -05:00
Piotr Żelasko
565c1d8413 Address code review 2022-01-24 10:17:47 -05:00
Piotr Żelasko
1d5fe8afa4 flake8 2022-01-21 17:27:02 -05:00
Piotr Żelasko
f0f35e6671 black 2022-01-21 17:22:41 -05:00
Piotr Żelasko
f28951f2b6 Add an assertion 2022-01-21 17:16:49 -05:00
Piotr Żelasko
3d109b121d Remove train_phones.py and modify train.py instead 2022-01-21 17:08:53 -05:00
Fangjun Kuang
1d44da845b
RNN-T Conformer training for LibriSpeech (#143) 
* Begin to add RNN-T training for librispeech.

* Copy files from conformer_ctc.

Will edit it.

* Use conformer/transformer model as encoder.

* Begin to add training script.

* Add training code.

* Remove long utterances to avoid OOM when a large max_duraiton is used.

* Begin to add decoding script.

* Add decoding script.

* Minor fixes.

* Add beam search.

* Use LSTM layers for the encoder.

Need more tunings.

* Use stateless decoder.

* Minor fixes to make it ready for merge.

* Fix README.

* Update RESULT.md to include RNN-T Conformer.

* Minor fixes.

* Fix tests.

* Minor fixes.

* Minor fixes.

* Fix tests.
 2021-12-18 07:42:51 +08:00
Wei Kang
a183d5bfd7
Remove batchnorm (#147) 
* Remove batch normalization

* Minor fixes

* Fix typo

* Fix comments

* Add assertion for use_feat_batchnorm
 2021-12-14 08:20:03 +08:00
Fangjun Kuang
ec591698b0
Associate a cut with token alignment (without repeats) (#125) 
* WIP: Associate a cut with token alignment (without repeats)

* Save framewise alignments with/without repeats.

* Minor fixes.
 2021-11-29 18:50:54 +08:00
Fangjun Kuang
243fb9723c
Fix an error introduced while supporting torchscript. (#134) 
Should be `G.dummy = 1`, not `G["dummy"] = 1`.
 2021-11-27 09:07:04 +08:00
Fangjun Kuang
0e541f5b5d
Print hostname and IP address to the log. (#131) 
We are using multiple machines to do various experiments. It makes
life easier to know which experiment is running on which machine
if we also log the IP and hostname of the machine.
 2021-11-26 11:25:59 +08:00
Piotr Żelasko
8eb94fa4a0 CTC-only phone conformer recipe for LibriSpeech 2021-11-23 15:34:46 -05:00
Wei Kang
4151cca147
Add torch script support for Aishell and update documents (#124) 
* Add aishell recipe

* Remove unnecessary code and update docs

* adapt to k2 v1.7, add docs and results

* Update conformer ctc model

* Update docs, pretrained.py & results

* Fix code style

* Fix code style

* Fix code style

* Minor fix

* Minor fix

* Fix pretrained.py

* Update pretrained model & corresponding docs

* Export torch script model for Aishell

* Add C++ deployment docs

* Minor fixes

* Fix unit test

* Update Readme
 2021-11-19 16:37:05 +08:00
Fangjun Kuang
0660d12e4e
Fix computing WERs for empty hypotheses (#118) 
* Fix computing WERs when empty lattices are generated.

* Minor fixes.
 2021-11-17 19:25:47 +08:00
Fangjun Kuang
336283f872
New label smoothing (#109) 
* Modify label smoothing to match the one implemented in PyTorch.

* Enable CI for torch 1.10

* Fix CI errors.

* Fix CI installation errors.

* Fix CI installation errors.

* Minor fixes.

* Minor fixes.

* Minor fixes.

* Minor fixes.

* Minor fixes.

* Fix CI errors.
 2021-11-17 19:24:07 +08:00
Fangjun Kuang
68506609ad
Set fsa.properties to None after changing its labels in-place. (#121) 2021-11-16 23:11:30 +08:00
Fangjun Kuang
8d679c3e74
Fix typos. (#115) 2021-11-10 14:45:30 +08:00
Fangjun Kuang
21096e99d8
Update result for the librispeech recipe using vocab size 500 and att rate 0.8 (#113) 
* Update RESULTS using vocab size 500, att rate 0.8

* Update README.

* Refactoring.

Since FSAs in an Nbest object are linear in structure, we can
add the scores of a path to compute the total scores.

* Update documentation.

* Change default vocab size from 5000 to 500.
 2021-11-10 14:32:52 +08:00
Fangjun Kuang
42b437bea6
Use pre-sorted text to generate token ids for attention decoder. (#98) 
* Use pre-sorted text to generate token ids for attention decoder.

See https://github.com/k2-fsa/icefall/issues/97
for more details.

* Fix typos.
 2021-10-29 13:46:41 +08:00
Fangjun Kuang
8cb7f712e4
Use GPU for averaging checkpoints if possible. (#84) 2021-10-26 17:10:04 +08:00