-
Notifications
You must be signed in to change notification settings - Fork 5.3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[egs] fixes to babel pipeline; thanks to Fred Richardson (#1509)
- Loading branch information
Showing
57 changed files
with
4,359 additions
and
190 deletions.
There are no files selected for viewing
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
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
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
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
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
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
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
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
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
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,78 @@ | ||
| # include common settings for fullLP systems. | ||
| . conf/common.fullLP || exit 1; | ||
|
|
||
|
|
||
| #speech corpora files location | ||
| train_data_dir=/export/babel/data//404-georgian/IARPA-babel404b-v1.0a-build/BABEL_OP3_404/conversational/training | ||
| train_data_list=./conf/lists/404-georgian//training.list | ||
| train_nj=32 | ||
|
|
||
|
|
||
| #Radical reduced DEV corpora files location | ||
| dev2h_data_dir=/export/babel/data//404-georgian/IARPA-babel404b-v1.0a-build/BABEL_OP3_404/conversational/dev | ||
| dev2h_data_list=./conf/lists/404-georgian//dev.2h.list | ||
| dev2h_rttm_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.mitllfa3.rttm | ||
| dev2h_ecf_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.scoring.ecf.xml | ||
| dev2h_stm_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.stm | ||
| dev2h_kwlists=( | ||
| [dev]=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.annot.kwlist.xml | ||
| [eval]=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev.kwlist3.xml | ||
| ) # dev2h_kwlists | ||
| dev2h_nj=16 | ||
| dev2h_subset_ecf=true | ||
|
|
||
|
|
||
| #Official DEV corpora files location | ||
| dev10h_data_dir=/export/babel/data//404-georgian/IARPA-babel404b-v1.0a-build/BABEL_OP3_404/conversational/dev | ||
| dev10h_data_list=./conf/lists/404-georgian//dev.list | ||
| dev10h_rttm_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.mitllfa3.rttm | ||
| dev10h_ecf_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.scoring.ecf.xml | ||
| dev10h_stm_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.stm | ||
| dev10h_kwlists=( | ||
| [dev]=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.annot.kwlist.xml | ||
| [eval]=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev.kwlist3.xml | ||
| ) # dev10h_kwlists | ||
| dev10h_nj=32 | ||
|
|
||
|
|
||
| #Official EVAL period evaluation data files | ||
| eval_data_dir=/export/babel/data//404-georgian/IARPA-babel404b-v1.0a-build/BABEL_OP3_404/conversational/eval | ||
| eval_data_list=./conf/lists/404-georgian//eval.list | ||
| eval_ecf_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-eval.ecf.xml | ||
| eval_kwlists=( | ||
| [dev]=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.annot.kwlist.xml | ||
| [eval]=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev.kwlist3.xml | ||
| ) # eval_kwlists | ||
| eval_nj=32 | ||
|
|
||
|
|
||
| #Shadow data files | ||
| shadow_data_dir=( | ||
| /export/babel/data//404-georgian/IARPA-babel404b-v1.0a-build/BABEL_OP3_404/conversational/dev | ||
| /export/babel/data//404-georgian/IARPA-babel404b-v1.0a-build/BABEL_OP3_404/conversational/eval | ||
| ) # shadow_data_dir | ||
| shadow_data_list=( | ||
| ./conf/lists/404-georgian//dev.list | ||
| ./conf/lists/404-georgian//eval.list | ||
| ) # shadow_data_dir | ||
| shadow_ecf_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.scoring.ecf.xml | ||
| shadow_rttm_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.mitllfa3.rttm | ||
| shadow_stm_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.stm | ||
| shadow_kwlists=( | ||
| [dev]=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.annot.kwlist.xml | ||
| [eval]=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev.kwlist3.xml | ||
| ) # shadow_kwlists | ||
| shadow_nj=32 | ||
|
|
||
|
|
||
| #Unsupervised dataset for FullLP condition | ||
| unsup_data_dir=/export/babel/data//404-georgian/IARPA-babel404b-v1.0a-build/BABEL_OP3_404/conversational/untranscribed-training | ||
| unsup_data_list=./conf/lists/404-georgian//untranscribed-training.list | ||
| unsup_nj=32 | ||
|
|
||
|
|
||
| lexicon_file= | ||
| lexiconFlags="--romanized --oov <unk>" | ||
|
|
||
|
|
||
|
|
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,54 @@ | ||
| # include common settings for fullLP systems. | ||
| . conf/common.limitedLP || exit 1; | ||
|
|
||
|
|
||
| #speech corpora files location | ||
| train_data_dir=/export/babel/data//404-georgian/IARPA-babel404b-v1.0a-build/BABEL_OP3_404/conversational/training | ||
| train_data_list=./conf/lists/404-georgian//sub-train.list | ||
| train_nj=32 | ||
|
|
||
|
|
||
| #Radical reduced DEV corpora files location | ||
| dev2h_data_dir=/export/babel/data//404-georgian/IARPA-babel404b-v1.0a-build/BABEL_OP3_404/conversational/dev | ||
| dev2h_data_list=./conf/lists/404-georgian//dev.2h.list | ||
| dev2h_rttm_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.mitllfa3.rttm | ||
| dev2h_ecf_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.scoring.ecf.xml | ||
| dev2h_stm_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.stm | ||
| dev2h_kwlists=( | ||
| [dev]=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.annot.kwlist.xml | ||
| [eval]=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.annot.kwlist3.xml | ||
| ) # dev2h_kwlists | ||
| dev2h_nj=16 | ||
| dev2h_subset_ecf=true | ||
|
|
||
|
|
||
| #Official DEV corpora files location | ||
| dev10h_data_dir=/export/babel/data//404-georgian/IARPA-babel404b-v1.0a-build/BABEL_OP3_404/conversational/dev | ||
| dev10h_data_list=./conf/lists/404-georgian//dev.list | ||
| dev10h_rttm_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.mitllfa3.rttm | ||
| dev10h_ecf_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.scoring.ecf.xml | ||
| dev10h_stm_file=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.stm | ||
| dev10h_kwlists=( | ||
| [dev]=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.annot.kwlist.xml | ||
| [eval]=/export/babel/data/scoring/IndusDB/IARPA-babel404b-v1.0a_conv-dev/IARPA-babel404b-v1.0a_conv-dev.annot.kwlist3.xml | ||
| ) # dev10h_kwlists | ||
| dev10h_nj=32 | ||
|
|
||
|
|
||
| #Unsupervised dataset for LimitedLP condition | ||
| unsup_data_list=( | ||
| ./conf/lists/404-georgian//untranscribed-training.list | ||
| ./conf/lists/404-georgian//sub-train.untranscribed.list | ||
| ) # unsup_data_list | ||
| unsup_data_dir=( | ||
| /export/babel/data//404-georgian/IARPA-babel404b-v1.0a-build/BABEL_OP3_404/conversational/untranscribed-training | ||
| /export/babel/data//404-georgian/IARPA-babel404b-v1.0a-build/BABEL_OP3_404/conversational/training | ||
| ) # unsup_data_dir | ||
| unsup_nj=32 | ||
|
|
||
|
|
||
| lexicon_file= | ||
| lexiconFlags="--romanized --oov <unk>" | ||
|
|
||
|
|
||
|
|
Oops, something went wrong.