-
Notifications
You must be signed in to change notification settings - Fork 5.3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[WIP] MATERIAL scripts #2165
Merged
Merged
[WIP] MATERIAL scripts #2165
Changes from 1 commit
Commits
Show all changes
113 commits
Select commit
Hold shift + click to select a range
3b4428b
basic directory structure
jtrmal 467cdeb
basic data setup ready
jtrmal ae370ad
adding scoring script
jtrmal 92bd9eb
resolve utf-8 encoding and some other details
jtrmal 33d5f36
do fix_data_dir after parametrixation
jtrmal 0a0436a
make 1A language default again
jtrmal e826675
material:add text filter for scoring
jtrmal 34ff3c1
material: fix path.sh
jtrmal 8e3481a
script changes up to triphone training
freewym 04dc97e
tuning of triphone systems
freewym 7a2114c
added recipe for tagalog
freewym 51768ed
added more
freewym 4755373
RNNLM for material
hainan-xv 389dcde
change chain model path
hainan-xv 258f7ba
minor change
hainan-xv 0061f07
minor change
hainan-xv daf8e56
reoriganized the scripts structures to allow to specifying language n…
freewym 8b3e34c
create one single rnnlm script for all material languages
freewym c05b977
fix stage numbers in the tdnn-lstm recipe
freewym 78c821b
remove $language subdir in /exp and /data
freewym 2abbfa2
fix issues related to num of params checks for some scripts
freewym b5af256
added decoding scripts for ANALYSIS1
1a8d80e
added scripts to compute WER for decoding ANALYSIS1
60c6eed
removed exit 0
b0b098f
remove in exp/ and data/
0145421
minor fixes
64165fe
added audio_path to conf
10360e6
added scripts that produce the results for the site visit and cleanup
freewym c0ae6b1
added support to decode test dev/eval1
freewym 2016d8c
added sentence segmentation
2e5d018
bug fixes for the path to tagalog DEV data
freewym 1b17c1f
adds eval2 decoding; adds tdnn1b recipes
freewym 442e6bb
adds analysis2 decoding
eb225b1
material scripts
hainan-xv 711198e
clean up src a bit
hainan-xv 0ca089f
clean up src a bit2
hainan-xv 3e1c880
material: Temporarily fixed scoring
vimalmanohar 9cd33e6
material: Cleanup scoring scripts
vimalmanohar 399496a
material scripts
hainan-xv d705fe3
merge with latest base
hainan-xv a42b09f
t push origin material_basicMerge branch 'hainan-xv-material_basic' i…
b98b248
remove some of the _2 affixes
hainan-xv 1f9fa82
add decoding for eval3
hainan-xv 9ffb000
Update convert_lexicon.pl
jtrmal 4cd2ea5
added semisupervised training scripts (might need changes according t…
freewym 187b18c
removed files with _2 suffix
212a8f7
Merge branch 'master' of https://github.com/kaldi-asr/kaldi into mate…
hainan-xv cc3cd1d
add mono data
hainan-xv 250ba57
fix a bug for decoding; officially working
hainan-xv 28dc919
basic directory structure
jtrmal bf66894
basic data setup ready
jtrmal e3db74e
adding scoring script
jtrmal b06655e
resolve utf-8 encoding and some other details
jtrmal 0599652
do fix_data_dir after parametrixation
jtrmal fa75313
make 1A language default again
jtrmal de1b53d
material:add text filter for scoring
jtrmal 93ebc80
material: fix path.sh
jtrmal bdc70ec
script changes up to triphone training
freewym 2c46288
tuning of triphone systems
freewym d281ede
added recipe for tagalog
freewym dbc0723
added more
freewym eab09c7
RNNLM for material
hainan-xv a7f73a3
change chain model path
hainan-xv 77ce4dc
minor change
hainan-xv 0b0e47d
minor change
hainan-xv c9b3e75
reoriganized the scripts structures to allow to specifying language n…
freewym a8d77fc
create one single rnnlm script for all material languages
freewym ffba239
fix stage numbers in the tdnn-lstm recipe
freewym 9ee662d
remove $language subdir in /exp and /data
freewym a80382b
fix issues related to num of params checks for some scripts
freewym 6cd4049
added decoding scripts for ANALYSIS1
809e3f3
added scripts to compute WER for decoding ANALYSIS1
5e06fe4
removed exit 0
d7cf604
remove in exp/ and data/
63c2b93
minor fixes
bb97a3f
added audio_path to conf
38d3445
added scripts that produce the results for the site visit and cleanup
freewym 1601312
added support to decode test dev/eval1
freewym cc32463
added sentence segmentation
c85ddf3
bug fixes for the path to tagalog DEV data
freewym 22109d7
adds eval2 decoding; adds tdnn1b recipes
freewym 6452a5f
adds analysis2 decoding
ec7ec63
material scripts
hainan-xv b37c754
clean up src a bit
hainan-xv f1e44da
clean up src a bit2
hainan-xv 170da49
material: Temporarily fixed scoring
vimalmanohar 9c61ab2
material: Cleanup scoring scripts
vimalmanohar 63022e6
material scripts
hainan-xv 46f34a4
remove some of the _2 affixes
hainan-xv e6e21bb
add decoding for eval3
hainan-xv bb06a69
Update convert_lexicon.pl
jtrmal d380c46
added semisupervised training scripts (might need changes according t…
freewym c5b58f8
removed files with _2 suffix
e80d7b1
adding monodata to material
hainan-xv d80f022
Merge branch 'material_basic' into material_fix2
mahsa7823 902fd89
Merge branch 'hainan-xv-material_fix4' into material_basic
865b507
updated run.sh with the instrictions
b1d9ef0
changing how LM preparation was done for material
hainan-xv 8014b51
changing how LM preparation was done for material, merge with latest …
hainan-xv aef4bf3
added Somali config
3d07b4e
Merge branch 'hainan-xv-material_new_lm2' into material_basic
df46dc9
updated somali.cong with mono and number_mapping paths
22d03b5
added local/normalize_numbers.py
7a83d7e
support for mono2, create output_nbest directory
mahsa7823 e4b77fe
updated WER results in local/chain/tuning/run_tdnn_1b.sh and local/rn…
mahsa7823 54840c8
clean-up semisupervised training scripts for material
freewym 042c974
clean up
mahsa7823 682d483
clean up semisup
mahsa7823 0f428ba
change configs
mahsa7823 7f07182
anonymize paths
mahsa7823 f92372b
Merge branch 'master' into material_basic
mahsa7823 2de2e42
added README and RESULTS. De-anonymization.
mahsa7823 aac8c9a
Merge branch 'material_basic' of https://github.com/mahsa7823/kaldi i…
mahsa7823 File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
removed files with _2 suffix
- Loading branch information
There are no files selected for viewing
This file was deleted.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@mahsa7823 , Are the results above up-to-date?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think so. Unless Hainan will have a new update after resolving a possible bug in rnnlm. @hainan-xv