mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 10:02:22 +00:00
Code Issues Packages Projects Releases Wiki Activity
107 Commits 5 Branches 3 Tags
Commit Graph

107 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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
Piotr Żelasko
8eb94fa4a0 CTC-only phone conformer recipe for LibriSpeech 2021-11-23 15:34:46 -05:00
Lucky Wong
769a9791ec
Fix no attribute 'data' error. (#129) 2021-11-22 18:31:04 +08:00
Wei Kang
e2c9c728d9
Update aishell tensorboard log for new LabelSmoothing loss (#128) 
* Update aishell tensorboard log for new LabelSmoothing loss

* Minor fixes
 2021-11-22 12:26:44 +08:00
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
Wei Kang
30c43b7f69
Add aishell recipe (#30) 
* 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
 2021-11-18 10:00:47 +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
Mingshuang Luo
10e46f3e1d
A little changes for timit recipe (#122) 
* Update train.py

* Update train.py

* Update train.py

* Update tdnn_ligru_ctc.rst
 2021-11-17 16:13:51 +08:00
Mingshuang Luo
2e0f255ada
Add timit recipe (including the code scripts and the docs) for icefall (#114) 
* add timit recipe for icefall

* add shared file

* update the docs for timit recipe

* Delete shared

* update the timit recipe and check style

* Update model.py

* Do some changes

* Update model.py

* Update model.py

* Add README.md and RESULTS.md

* Update RESULTS.md

* Update README.md

* update the docs for timit recipe
 2021-11-17 11:23:45 +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
Daniel Povey
b9452235d5
Merge pull request #117 from csukuangfj/fix-empty-lattice 
Handle empty lattices in attention decoder rescoring.
 2021-11-11 16:26:02 +08:00
Fangjun Kuang
5b10310bd1 Handle empty lattices in attention decoder rescoring. 2021-11-11 15:42:30 +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
04029871b6
Fix a bug in Nbest.compute_am_scores and Nbest.compute_lm_scores. (#111) 2021-11-09 13:44:51 +08:00
Fangjun Kuang
91cfecebf2
Remove duplicated token seq in rescoring. (#108) 
* Remove duplicated token seq in rescoring.

* Use a larger range for ngram_lm_scale and attention_scale
 2021-11-06 08:54:45 +08:00
Fangjun Kuang
810b193dcc
Clarify the doc about ctc-decoding. (#104) 2021-11-03 07:16:49 +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
12d647d899
Add a note about the CUDA OOM error. (#94) 
* Add a note about the CUDA OOM error.

Some users consider this kind of OOM as an error during decoding,
but actually it is not. This pull request clarifies that.

* Fix style issues.
 2021-10-29 12:17:56 +08:00
Fangjun Kuang
8cb7f712e4
Use GPU for averaging checkpoints if possible. (#84) 2021-10-26 17:10:04 +08:00
Fangjun Kuang
712ead8207
Fix an error when attention decoder rescoring returns None. (#90) 2021-10-22 19:52:25 +08:00
Piotr Żelasko
902e0b238d
Merge pull request #82 from pzelasko/feature/find-pessimistic-batches 
Find CUDA OOM batches before starting training
 2021-10-19 11:26:13 -04:00
Piotr Żelasko
3cc99d2af2 make flake8 happy 2021-10-19 11:24:54 -04:00
cdxie
d30244e28f
add a docker file for some users (#87) 
* add a docker file for some users

Ubuntu18.04-pytorch1.7.1-cuda11.0-cudnn8-python3.8

* add a describing file of how to use dockerfile

give some steps to use dockerfile
 2021-10-19 13:00:59 +08:00
Piotr Żelasko
86f3e0ef37 Make flake8 happy 2021-10-18 09:54:40 -04:00
Piotr Żelasko
6fbd7a287c Refactor OOM batch scanning into a local function 2021-10-18 09:53:04 -04:00
Piotr Żelasko
d509d58f30 Merge branch 'master' into feature/find-pessimistic-batches 2021-10-18 09:47:21 -04:00
Fangjun Kuang
3effcb4225
Fix typos. (#85) 2021-10-18 16:17:14 +08:00
Fangjun Kuang
53b79fafa7
Add MMI training with word pieces as modelling unit. (#6) 
* Fix an error in TDNN-LSTM training.

* WIP: Refactoring

* Refactor transformer.py

* Remove unused code.

* Minor fixes.

* Fix decoder padding mask.

* Add MMI training with word pieces.

* Remove unused files.

* Minor fixes.

* Refactoring.

* Minor fixes.

* Use pre-computed alignments in LF-MMI training.

* Minor fixes.

* Update decoding script.

* Add doc about how to check and use extracted alignments.

* Fix style issues.

* Fix typos.

* Fix style issues.

* Disable macOS tests for now.
 2021-10-18 15:20:32 +08:00
Fangjun Kuang
4890e27b45
Extract framewise alignment information using CTC decoding (#39) 
* Use new APIs with k2.RaggedTensor

* Fix style issues.

* Update the installation doc, saying it requires at least k2 v1.7

* Extract framewise alignment information using CTC decoding.

* Print environment information.

Print information about k2, lhotse, PyTorch, and icefall.

* Fix CI.

* Fix CI.

* Compute framewise alignment information of the LibriSpeech dataset.

* Update comments for the time to compute alignments of train-960.

* Preserve cut id in mix cut transformer.

* Minor fixes.

* Add doc about how to extract framewise alignments.
 2021-10-18 14:24:33 +08:00
Jan "yenda" Trmal
bd7c2f7645
fix conformer typo in docs (#83) 2021-10-16 07:46:17 +08:00
Piotr Żelasko
403d1744ff Introduce backprop in finding OOM batches 2021-10-15 10:05:13 -04:00
Piotr Żelasko
060117a9ff Reformatting 2021-10-14 21:40:14 -04:00
Piotr Żelasko
1c7c79f2fc Find CUDA OOM batches before starting training 2021-10-14 21:28:11 -04:00
Fangjun Kuang
fee1f84b20
Test pre-trained model in CI (#80) 
* Add CI to run pre-trained models.

* Minor fixes.

* Install kaldifeat

* Install a CPU version of PyTorch.

* Fix CI errors.

* Disable decoder layers in pretrained.py if it is not used.

* Clone pre-trained model from GitHub.

* Minor fixes.

* Minor fixes.

* Minor fixes.
 2021-10-15 00:41:33 +08:00
Mingshuang Luo
5401ce199d
Update ctc-decoding on pretrained.py and conformer_ctc.rst (#78) 2021-10-14 23:29:06 +08:00
Fangjun Kuang
f2387fe523
Fix a bug introduced while supporting torch script. (#79) 2021-10-14 20:09:38 +08:00
Fangjun Kuang
5016ee3c95
Give an informative message when users provide an unsupported decoding method (#77) 2021-10-14 16:20:35 +08:00
Mingshuang Luo
39bc8cae94
Add ctc decoding to pretrained.py on conformer_ctc (#75) 
* Add ctc-decoding to pretrained.py

* update pretrained.py and conformer_ctc.rst

* update ctc-decoding for pretrained.py on conformer_ctc

* Update pretrained.py

* fix the style issue

* Update conformer_ctc.rst

* Update the running logs
 2021-10-13 12:20:16 +08:00
Mingshuang Luo
391432b356
Update train.py ("10"--->"params.log_interval") (#76) 
* Update train.py

* Update train.py

* Update train.py
 2021-10-12 21:30:31 +08:00
Mingshuang Luo
597c5efdb1
Use LossRecord to record and print the loss for the training process (#62) 
* Update index.rst (AS->ASR)

* Update conformer_ctc.rst (pretraind->pretrained)

* Fix some spelling errors.

* Fix some spelling errors.

* Use LossRecord to record and print loss in the training process

* Change the name "LossRecord" to "MetricsTracker"
 2021-10-12 15:58:03 +08:00
Fangjun Kuang
beb54ddb61
Support torch script. (#65) 
* WIP: Support torchscript.

* Minor fixes.

* Fix style issues.

* Add documentation about how to deploy a trained model.
 2021-10-12 14:55:05 +08:00
Piotr Żelasko
d54828e73a
Merge pull request #73 from pzelasko/feature/bucketing-in-test 
Use BucketingSampler for dev and test data
 2021-10-09 10:58:29 -04:00
Piotr Żelasko
069ebaf9ba Reformatting 2021-10-09 14:45:46 +00:00
Mingshuang Luo
6e43905d12
Update the documentation to include "ctc-decoding" (#71) 
* Update conformer_ctc.rst
 2021-10-09 11:56:25 +08:00
Piotr Żelasko
b682467e4d Use BucketingSampler for dev and test data 2021-10-08 22:32:13 -04:00
Piotr Żelasko
adb068eb82
setup.py (#64) 2021-10-01 16:43:08 +08:00