Added voice control
Former-commit-id: 6f69079bf44f0d8f9ae40de6b0f1638d103464c2
This commit is contained in:
parent
35c92407a3
commit
53da641909
863 changed files with 192681 additions and 0 deletions
|
|
@ -0,0 +1,40 @@
|
|||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
|
||||
<project basedir="." default="test" name="Voxforge Tests">
|
||||
<description>
|
||||
This file is used to run the voxforge performance tests.
|
||||
|
||||
NOTE: Before running the tests, you must have already built
|
||||
the sphinx-4 sources by typing "ant" in the top level
|
||||
sphinx4 directory.
|
||||
|
||||
Run ant with -Dskip=5 to do the standard 'quick' version of a test.
|
||||
</description>
|
||||
|
||||
<property name="classpath" value="../../../sphinx4-core/target/classes"/>
|
||||
|
||||
<property name="skip" value="40"/>
|
||||
<property name="logger_props" value=""/>
|
||||
|
||||
<property name="initial_heap_size" value="512m"/>
|
||||
<property name="maximum_heap_size" value="2048m"/>
|
||||
<property name="jit" value="server"/>
|
||||
<property name="gc_log_file" value="gc.txt"/>
|
||||
|
||||
<target name="compile" />
|
||||
|
||||
<target name="test"
|
||||
description="trigram decoding of Voxforge test data">
|
||||
<java classpath="${classpath}"
|
||||
classname="edu.cmu.sphinx.tools.batch.BatchModeRecognizer"
|
||||
fork="true">
|
||||
<jvmarg value="-${jit}"/>
|
||||
<jvmarg value="-ms${initial_heap_size}"/>
|
||||
<jvmarg value="-mx${maximum_heap_size}"/>
|
||||
<arg value="voxforge.config.xml"/>
|
||||
<arg value="voxforge_en_test.batch"/>
|
||||
<sysproperty key="batch[skip]" value="${skip}"/>
|
||||
</java>
|
||||
</target>
|
||||
|
||||
</project>
|
||||
|
|
@ -0,0 +1,255 @@
|
|||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
|
||||
<!-- ************************************************** -->
|
||||
<!-- Sphinx-4 Configuration File -->
|
||||
<!-- ************************************************** -->
|
||||
|
||||
|
||||
<config>
|
||||
|
||||
<!-- ************************************************** -->
|
||||
<!-- Global Properties -->
|
||||
<!-- ************************************************** -->
|
||||
|
||||
<property name="absoluteBeamWidth" value="30000"/>
|
||||
<property name="relativeBeamWidth" value="1E-80"/>
|
||||
<property name="absoluteWordBeamWidth" value="40"/>
|
||||
<property name="relativeWordBeamWidth" value="1E-40"/>
|
||||
<property name="wordInsertionProbability" value="0.5"/>
|
||||
<property name="languageWeight" value="10.5"/>
|
||||
<property name="silenceInsertionProbability" value=".1"/>
|
||||
<property name="fillerInsertionProbability" value="1e-6"/>
|
||||
<property name="acousticLookahead" value="1.7"/>
|
||||
<property name="lookaheadBeam" value="1e-80"/>
|
||||
<property name="frontend" value="mfcFrontEnd"/>
|
||||
<property name="recognizer" value="wordRecognizer"/>
|
||||
|
||||
<!-- ************************************************** -->
|
||||
<!-- Components -->
|
||||
<!-- ************************************************** -->
|
||||
|
||||
<component name="batch"
|
||||
type="edu.cmu.sphinx.tools.batch.BatchModeRecognizer">
|
||||
<propertylist name="inputDataProcessors">
|
||||
<item>streamDataSource</item>
|
||||
</propertylist>
|
||||
<property name="skip" value="0"/>
|
||||
<property name="recognizer" value="${recognizer}"/>
|
||||
</component>
|
||||
|
||||
<component name="wordRecognizer"
|
||||
type="edu.cmu.sphinx.recognizer.Recognizer">
|
||||
<propertylist name="monitors">
|
||||
<item>accuracyTracker</item>
|
||||
<item>speedTracker</item>
|
||||
<item>memoryTracker</item>
|
||||
</propertylist>
|
||||
<property name="decoder" value="decoder"/>
|
||||
</component>
|
||||
|
||||
<component name="decoder"
|
||||
type="edu.cmu.sphinx.decoder.Decoder">
|
||||
<property name="searchManager" value="wordPruningSearchManager"/>
|
||||
</component>
|
||||
|
||||
<component name="wordPruningSearchManager"
|
||||
type="edu.cmu.sphinx.decoder.search.WordPruningBreadthFirstSearchManager">
|
||||
<property name="scorer" value="threadedScorer"/>
|
||||
<property name="pruner" value="trivialPruner"/>
|
||||
<property name="activeListManager" value="activeListManager"/>
|
||||
<property name="logMath" value="logMath"/>
|
||||
|
||||
<property name="buildWordLattice" value="false"/>
|
||||
<property name="growSkipInterval" value="0"/>
|
||||
<property name="linguist" value="lexTreeLinguist"/>
|
||||
<property name="checkStateOrder" value="false"/>
|
||||
|
||||
<property name="acousticLookaheadFrames" value="${acousticLookahead}"/>
|
||||
<property name="relativeBeamWidth" value="${lookaheadBeam}"/>
|
||||
</component>
|
||||
|
||||
<component name="activeListManager"
|
||||
type="edu.cmu.sphinx.decoder.search.SimpleActiveListManager">
|
||||
<propertylist name="activeListFactories">
|
||||
<item>unitExitActiveList</item>
|
||||
<item>wordActiveList</item>
|
||||
<item>wordActiveList</item>
|
||||
<item>activeList</item>
|
||||
<item>activeList</item>
|
||||
<item>activeList</item>
|
||||
</propertylist>
|
||||
</component>
|
||||
|
||||
<component name="unitExitActiveList"
|
||||
type="edu.cmu.sphinx.decoder.search.PartitionActiveListFactory">
|
||||
<property name="logMath" value="logMath"/>
|
||||
<property name="absoluteBeamWidth" value="${absoluteBeamWidth}"/>
|
||||
<property name="relativeBeamWidth" value="${relativeBeamWidth}"/>
|
||||
</component>
|
||||
|
||||
<component name="wordActiveList"
|
||||
type="edu.cmu.sphinx.decoder.search.PartitionActiveListFactory">
|
||||
<property name="logMath" value="logMath"/>
|
||||
<property name="absoluteBeamWidth" value="${absoluteWordBeamWidth}"/>
|
||||
<property name="relativeBeamWidth" value="${relativeWordBeamWidth}"/>
|
||||
</component>
|
||||
|
||||
<component name="activeList"
|
||||
type="edu.cmu.sphinx.decoder.search.PartitionActiveListFactory">
|
||||
<property name="logMath" value="logMath"/>
|
||||
<property name="absoluteBeamWidth" value="${absoluteBeamWidth}"/>
|
||||
<property name="relativeBeamWidth" value="${relativeBeamWidth}"/>
|
||||
</component>
|
||||
|
||||
<component name="lexTreeLinguist"
|
||||
type="edu.cmu.sphinx.linguist.lextree.LexTreeLinguist">
|
||||
<property name="logMath" value="logMath"/>
|
||||
<property name="dictionary" value="dictionary"/>
|
||||
<property name="addFillerWords" value="false"/>
|
||||
<property name="acousticModel" value="voxforge"/>
|
||||
<property name="languageModel" value="trigramModel"/>
|
||||
<property name="unitManager" value="unitManager"/>
|
||||
|
||||
<property name="languageWeight" value="${languageWeight}"/>
|
||||
<property name="silenceInsertionProbability" value="${silenceInsertionProbability}"/>
|
||||
<property name="wordInsertionProbability" value="${wordInsertionProbability}"/>
|
||||
<property name="fillerInsertionProbability" value="${fillerInsertionProbability}"/>
|
||||
|
||||
<property name="wantUnigramSmear" value="true"/>
|
||||
<property name="unigramSmearWeight" value="1"/>
|
||||
<property name="cacheSize" value="0"/>
|
||||
</component>
|
||||
|
||||
<component name="trigramModel"
|
||||
type="edu.cmu.sphinx.linguist.language.ngram.large.LargeTrigramModel">
|
||||
<property name="unigramWeight" value=".7"/>
|
||||
<property name="maxDepth" value="3"/>
|
||||
<property name="logMath" value="logMath"/>
|
||||
<property name="dictionary" value="dictionary"/>
|
||||
<property name="location"
|
||||
value="etc/voxforge_en_sphinx.transcription.test.txt.lm.DMP"/>
|
||||
</component>
|
||||
|
||||
<component name="dictionary"
|
||||
type="edu.cmu.sphinx.linguist.dictionary.FullDictionary">
|
||||
<property name="dictionaryPath" value="etc/cmudict.0.7a"/>
|
||||
<property name="fillerPath" value="etc/voxforge_en_sphinx.filler"/>
|
||||
<property name="unitManager" value="unitManager"/>
|
||||
</component>
|
||||
|
||||
<component name="voxforge"
|
||||
type="edu.cmu.sphinx.linguist.acoustic.tiedstate.TiedStateAcousticModel">
|
||||
<property name="loader" value="modelLoader"/>
|
||||
<property name="unitManager" value="unitManager"/>
|
||||
</component>
|
||||
|
||||
<component name="modelLoader" type="edu.cmu.sphinx.linguist.acoustic.tiedstate.Sphinx3Loader">
|
||||
<property name="logMath" value="logMath"/>
|
||||
<property name="unitManager" value="unitManager"/>
|
||||
<property name="location" value="voxforge_en_sphinx.cd_cont_3000"/>
|
||||
<property name="vectorLength" value="29"/>
|
||||
</component>
|
||||
|
||||
<component name="trivialPruner"
|
||||
type="edu.cmu.sphinx.decoder.pruner.SimplePruner">
|
||||
</component>
|
||||
|
||||
<component name="threadedScorer"
|
||||
type="edu.cmu.sphinx.decoder.scorer.ThreadedAcousticScorer">
|
||||
<property name="frontend" value="${frontend}"/>
|
||||
</component>
|
||||
|
||||
<component name="logMath"
|
||||
type="edu.cmu.sphinx.util.LogMath">
|
||||
<property name="logBase" value="1.0001"/>
|
||||
<property name="useAddTable" value="true"/>
|
||||
</component>
|
||||
|
||||
<component name="unitManager"
|
||||
type="edu.cmu.sphinx.linguist.acoustic.UnitManager"/>
|
||||
|
||||
<component name="mfcFrontEnd"
|
||||
type="edu.cmu.sphinx.frontend.FrontEnd">
|
||||
<propertylist name="pipeline">
|
||||
<item>streamDataSource</item>
|
||||
<item>dither</item>
|
||||
<item>preemphasizer</item>
|
||||
<item>windower</item>
|
||||
<item>fft</item>
|
||||
<item>melFilterBank</item>
|
||||
<item>dct</item>
|
||||
<item>batchCMN</item>
|
||||
<item>featureExtraction</item>
|
||||
<item>featureTransform</item>
|
||||
</propertylist>
|
||||
</component>
|
||||
|
||||
<component name="streamDataSource"
|
||||
type="edu.cmu.sphinx.frontend.util.StreamDataSource">
|
||||
<property name="sampleRate" value="16000"/>
|
||||
</component>
|
||||
|
||||
<component name="preemphasizer"
|
||||
type="edu.cmu.sphinx.frontend.filter.Preemphasizer">
|
||||
</component>
|
||||
|
||||
<component name="dither"
|
||||
type="edu.cmu.sphinx.frontend.filter.Dither">
|
||||
</component>
|
||||
|
||||
<component name="windower"
|
||||
type="edu.cmu.sphinx.frontend.window.RaisedCosineWindower">
|
||||
</component>
|
||||
|
||||
<component name="fft"
|
||||
type="edu.cmu.sphinx.frontend.transform.DiscreteFourierTransform">
|
||||
</component>
|
||||
|
||||
<component name="melFilterBank"
|
||||
type="edu.cmu.sphinx.frontend.frequencywarp.MelFrequencyFilterBank">
|
||||
<property name="numberFilters" value="31"/>
|
||||
<property name="minimumFrequency" value="200"/>
|
||||
<property name="maximumFrequency" value="3500"/>
|
||||
</component>
|
||||
|
||||
<component name="dct"
|
||||
type="edu.cmu.sphinx.frontend.transform.DiscreteCosineTransform">
|
||||
</component>
|
||||
|
||||
<component name="batchCMN"
|
||||
type="edu.cmu.sphinx.frontend.feature.BatchCMN">
|
||||
</component>
|
||||
|
||||
<component name="featureExtraction"
|
||||
type="edu.cmu.sphinx.frontend.feature.DeltasFeatureExtractor">
|
||||
</component>
|
||||
|
||||
<component name="featureTransform"
|
||||
type="edu.cmu.sphinx.frontend.feature.FeatureTransform">
|
||||
<property name="loader" value="modelLoader"/>
|
||||
</component>
|
||||
|
||||
<!-- ************************************************** -->
|
||||
<!-- Instrumentation -->
|
||||
<!-- ************************************************** -->
|
||||
|
||||
<component name="accuracyTracker"
|
||||
type="edu.cmu.sphinx.instrumentation.BestPathAccuracyTracker">
|
||||
<property name="showRawResults" value="false"/>
|
||||
<property name="recognizer" value="${recognizer}"/>
|
||||
<property name="showAlignedResults" value="false"/>
|
||||
</component>
|
||||
|
||||
<component name="speedTracker"
|
||||
type="edu.cmu.sphinx.instrumentation.SpeedTracker">
|
||||
<property name="showTimers" value="true"/>
|
||||
<property name="frontend" value="${frontend}"/>
|
||||
<property name="recognizer" value="${recognizer}"/>
|
||||
</component>
|
||||
|
||||
<component name="memoryTracker"
|
||||
type="edu.cmu.sphinx.instrumentation.MemoryTracker">
|
||||
<property name="recognizer" value="${recognizer}"/>
|
||||
</component>
|
||||
|
||||
</config>
|
||||
File diff suppressed because it is too large
Load diff
Loading…
Add table
Add a link
Reference in a new issue