mirrors/DeepSpeech
2
0
Fork 0
mirror of https://github.com/mozilla/DeepSpeech.git synced 2025-10-26 11:19:39 +00:00
Code Issues Packages Projects Releases Wiki Activity
bb1fcc0542
DeepSpeech/bin
History
Alexandre Lissy d7653d749b Use LDC93S1 small language model 
How to regenerate:
 - Get a KenLM build
 - $ (tr -d '[:digit:]|[:punct:]' < LDC93S1.txt | tr '[:upper:]' '[:lower:]'; head -n 500 ../lm/vocab.txt) > vocab.txt
 - $ bin/lmplz --prune 0 0 1 --order 5 --text vocab.txt --arpa vocab.pruned.arpa
 - $ bin/build_binary  -s vocab.pruned.arpa vocab.pruned.lm
 - $ generate_trie ../alphabet.txt vocab.pruned.lm vocab.txt vocab.trie

Fixes #1245
2018-02-15 14:56:02 +01:00
..
benchmark_nc.py reorder arguments in client.cc, client.py and client.js also update call sites in tc-test-utils.sh 2018-02-14 09:29:35 +05:30
benchmark_plotter.py Rename util/tc.py to util/taskcluster.py 2017-11-08 14:34:05 -02:00
enqueue.sh Fix #678; copying keep directory into right target directory 2017-07-05 10:30:19 +02:00
gpu_usage_chart Tracking GPU Usage 2016-11-17 11:49:20 +01:00
gpu_usage_plot Tracking GPU Usage 2016-11-17 11:49:20 +01:00
import_cv.py Better resuming; additional README content; small improvements 2017-11-29 13:04:10 +01:00
import_fisher.py Remove audio file too large for its transcript 2017-11-01 18:14:34 -02:00
import_ldc93s1.py Fix #715; removed wrong and unused import 2017-07-13 14:28:59 +02:00
import_librivox.py Save absolute paths in dataset definition files 2017-04-25 23:58:13 -03:00
import_swb.py Fixed #789 2017-08-25 10:06:58 +02:00
import_ted.py Keep unsplit WAV files in the TED corpus 2017-05-10 12:04:45 -03:00
import_timit.py removed blank 2017-09-12 15:09:02 +01:00
import_voxforge.py parallelized import_voxforge.py 2017-10-22 23:43:36 -07:00
job-template.sbatch Fix #590; Fix #551; Fix #615; Better process exit and exception handlin 2017-06-07 08:10:57 -07:00
README.md Fix #328; distributed TensorFlow 2017-03-31 17:10:34 +02:00
run-cluster.sh Fix #328; distributed TensorFlow 2017-03-31 17:10:34 +02:00
run-fisher.sh Fix #493; DeepSpeech part of SLURM cluster support 2017-05-18 03:20:24 -07:00
run-ldc93s1.sh Fix #493; DeepSpeech part of SLURM cluster support 2017-05-18 03:20:24 -07:00
run-librivox.sh Fix #493; DeepSpeech part of SLURM cluster support 2017-05-18 03:20:24 -07:00
run-swb.sh Removed log level parameter 2017-08-25 13:15:25 +02:00
run-tc-ldc93s1.sh Use LDC93S1 small language model 2018-02-15 14:56:02 +01:00
run-ted.sh Fixed issue #608 2017-05-28 07:34:26 +02:00
run-timit.sh added timit import scripts 2017-09-11 16:14:01 +01:00
run-wer-automation.sh Fixed issue #608 2017-05-28 07:34:26 +02:00
update-website.sh Handling of website publication 2016-10-24 16:35:45 +02:00

README.md

Utility scripts

This folder contains scripts that can be used to do training on the various included importers from the command line. This is useful to be able to run training without a browser open, or unattended on a remote machine. They should be run from the base directory of the repository. Note that the default settings assume a very well-specified machine. In the situation that out-of-memory errors occur, you may find decreasing the values of --train_batch_size, --dev_batch_size and --test_batch_size will allow you to continue, at the expense of speed.