kaldi/egs
Daniel Povey 0d4f1b2483 Merge pull request #786 from freewym/librispeech_nnet2
add new results for Multi-splice version of online recipe of Librispeech, including those on test set.
2016-05-18 19:56:26 -04:00
..
ami Merge pull request #631 from jtrmal/path_sh_fix2 2016-04-11 11:20:11 -04:00
apiai_decode/s5 Merge remote-tracking branch 'upstream/chain' 2016-04-26 22:20:02 -04:00
aspire Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
aurora4 Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
babel Update arpa2fst invocations in individual egs/*/local scripts 2016-04-10 20:15:08 -07:00
bn_music_speech/v1 bn-music-speech-fix: Update to run.sh to use the LDC distribution of the HUB4 corpus, update to local/make_bn.py so that it is more flexible with regard to differences in source directory format 2016-04-12 18:25:31 -04:00
callhome_egyptian Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
chime1 moving the src/path.sh into tools/config/common_path.sh 2016-03-30 09:57:03 -04:00
chime2 Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
chime3 remove "set -x" in CHiME3 scripts 2016-04-25 13:35:11 -04:00
chime4 chime4: minor bug-fixes 2016-05-07 16:35:41 -04:00
csj moving the src/path.sh into tools/config/common_path.sh 2016-03-30 09:57:03 -04:00
farsdat Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
fisher_callhome_spanish Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
fisher_english Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
fisher_swbd/s5 add fisher_swbd tdnn+smbr results 2016-04-28 13:30:40 +08:00
gale_arabic Update run_lstm.sh 2016-04-15 09:04:43 +01:00
gale_mandarin Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
gp Update arpa2fst invocations in individual egs/*/local scripts 2016-04-10 20:15:08 -07:00
hkust nnet1: integrating comments from Dan. 2016-05-12 02:12:01 +02:00
iban fixing path.sh 2016-05-03 15:38:24 -04:00
librispeech add new results for Multi-splice version of online recipe (5/16/2016). 2016-05-17 19:31:35 -04:00
lre moving the src/path.sh into tools/config/common_path.sh 2016-03-30 09:57:03 -04:00
lre07 Merge pull request #631 from jtrmal/path_sh_fix2 2016-04-11 11:20:11 -04:00
reverb Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
rm nnet1: integrating comments from Dan. 2016-05-12 02:12:01 +02:00
sprakbanken fix name of decoding script in some old nnet2 recipes (thanks: miguelcm86@gmail.com) 2016-05-18 15:24:44 -04:00
sre08 moving the src/path.sh into tools/config/common_path.sh 2016-03-30 09:57:03 -04:00
sre10 Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
swahili Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
swbd Merge branch 'master' into chain-left-biphone 2016-05-16 10:17:22 +08:00
tedlium/s5 Update run_lstm.sh 2016-04-15 09:24:29 +01:00
thchs30 moving the src/path.sh into tools/config/common_path.sh 2016-03-30 09:57:03 -04:00
tidigits moving the src/path.sh into tools/config/common_path.sh 2016-03-30 09:57:03 -04:00
timit Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
voxforge Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
vystadial_cz Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
vystadial_en Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
wsj fix name of decoding script in some old nnet2 recipes (thanks: miguelcm86@gmail.com) 2016-05-18 15:24:44 -04:00
yesno Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
README.txt trunk: minor, cosmetic changes 2014-03-30 17:53:53 +00:00

README.txt

This directory contains example scripts that demonstrate how to 
use Kaldi.  Each subdirectory corresponds to a corpus that we have
example scripts for.

Note: we now have some scripts using free data, including voxforge,
vystadial_{cz,en} and yesno.  Most of the others are available from
the Linguistic Data Consortium (LDC), which requires money (unless you
have a membership).

If you have an LDC membership, probably rm/s5 or wsj/s5 should be your first
choice to try out the scripts.