Menu ▾ ▴

HUB4 help

Help
Einstein Mic
2008-02-22
2012-09-22

  • Einstein Mic

    Einstein Mic - 2008-02-22

    Hi,

    I'm new to sphinx world. I want to create a transcriber for Italian language.
    Before approaching the problem of Italian I'm trying to create an English transcriber in order to understand all necessary concepts.
    Starting from the transcriber demo provided with sphinx-4 I was trying to use the HUB4 acoustic and language model.
    I've configured config file but when I start the program I receive these messages:

    12:01.204 INFO logMath Log base is 1.0001
    12:01.207 INFO logMath Using AddTable when adding logs
    12:01.207 INFO logMath LogAdd table has 99022 entries.
    Exception in thread "main" java.lang.IncompatibleClassChangeError: Found class edu.cmu.sphinx.util.props.PropertySheet, but interface was expected
    at edu.cmu.sphinx.model.acoustic.HUB4_8gau_13dCep_16k_40mel_133Hz_6855Hz.Model.newProperties(Model.java:158)
    at edu.cmu.sphinx.util.props.PropertySheet.getOwner(PropertySheet.java:420)
    at edu.cmu.sphinx.util.props.PropertySheet.getComponent(PropertySheet.java:270)
    at edu.cmu.sphinx.linguist.lextree.LexTreeLinguist.newProperties(LexTreeLinguist.java:241)
    at edu.cmu.sphinx.util.props.PropertySheet.getOwner(PropertySheet.java:420)
    at edu.cmu.sphinx.util.props.PropertySheet.getComponent(PropertySheet.java:270)
    at edu.cmu.sphinx.decoder.search.WordPruningBreadthFirstSearchManager.newProperties(WordPruningBreadthFirstSearchManager.java:173)
    at edu.cmu.sphinx.util.props.PropertySheet.getOwner(PropertySheet.java:420)
    at edu.cmu.sphinx.util.props.PropertySheet.getComponent(PropertySheet.java:270)
    at edu.cmu.sphinx.decoder.AbstractDecoder.newProperties(AbstractDecoder.java:42)
    at edu.cmu.sphinx.decoder.Decoder.newProperties(Decoder.java:31)
    at edu.cmu.sphinx.util.props.PropertySheet.getOwner(PropertySheet.java:420)
    at edu.cmu.sphinx.util.props.PropertySheet.getComponent(PropertySheet.java:270)
    at edu.cmu.sphinx.recognizer.Recognizer.newProperties(Recognizer.java:79)
    at edu.cmu.sphinx.util.props.PropertySheet.getOwner(PropertySheet.java:420)
    at edu.cmu.sphinx.util.props.ConfigurationManager.lookup(ConfigurationManager.java:144)
    at demo.sphinx.trascrittore.Transcriber.main(Transcriber.java:46)

    This is the configuration file:

    Thanks for your help.

    Mic

    <?xml version="1.0" encoding="UTF-8"?>
    <config>
    <property name="relativeBeamWidth" value="1E-60"/>
    <property name="absoluteWordBeamWidth" value="22"/>
    <property name="relativeWordBeamWidth" value="1E-30"/>
    <property name="wordInsertionProbability" value=".2"/>
    <property name="languageWeight" value="10.5"/>
    <property name="silenceInsertionProbability" value=".1"/>
    <property name="acousticLookahead" value="1.7"/>
    <property name="frontend" value="mfcFrontEnd"/>
    <property name="recognizer" value="recognizer"/>
    <property name="showCreations" value="false"/>

    &lt;component name=&quot;batch&quot;
      type=&quot;edu.cmu.sphinx.tools.batch.BatchModeRecognizer&quot;&gt;
    &lt;propertylist name=&quot;inputDataProcessors&quot;&gt;
        &lt;item&gt;streamDataSource&lt;/item&gt;
    &lt;/propertylist&gt;
    &lt;property name=&quot;skip&quot; value=&quot;0&quot;/&gt;
    &lt;property name=&quot;recognizer&quot; value=&quot;${recognizer}&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;live&quot;
            type=&quot;edu.cmu.sphinx.tools.live.LiveModeRecognizer&quot;&gt;
    &lt;property name=&quot;recognizer&quot; value=&quot;${recognizer}&quot;/&gt;
    &lt;property name=&quot;inputSource&quot; value=&quot;concatDataSource&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;recognizer&quot;
      type=&quot;edu.cmu.sphinx.recognizer.Recognizer&quot;&gt;
    &lt;propertylist name=&quot;monitors&quot;&gt;
        &lt;item&gt;accuracyTracker&lt;/item&gt;
        &lt;item&gt;speedTracker&lt;/item&gt;
        &lt;item&gt;memoryTracker&lt;/item&gt;
        &lt;item&gt;recognizerMonitor&lt;/item&gt;
        &lt;item&gt;beamFinder&lt;/item&gt;
    &lt;/propertylist&gt;
    &lt;property name=&quot;decoder&quot; value=&quot;decoder&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;decoder&quot;
      type=&quot;edu.cmu.sphinx.decoder.Decoder&quot;&gt;
    &lt;property name=&quot;searchManager&quot; value=&quot;wordPruningSearchManager&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;wordPruningSearchManager&quot;
      type=&quot;edu.cmu.sphinx.decoder.search.WordPruningBreadthFirstSearchManager&quot;&gt;
    &lt;property name=&quot;scorer&quot; value=&quot;threadedScorer&quot;/&gt;
    &lt;property name=&quot;pruner&quot; value=&quot;trivialPruner&quot;/&gt;
    &lt;property name=&quot;acousticLookaheadFrames&quot; value=&quot;2.0&quot;/&gt;
    &lt;property name=&quot;logMath&quot; value=&quot;logMath&quot;/&gt;
    &lt;property name=&quot;activeListManager&quot; value=&quot;activeListManager&quot;/&gt;
    &lt;property name=&quot;buildWordLattice&quot; value=&quot;false&quot;/&gt;
    &lt;property name=&quot;relativeBeamWidth&quot; value=&quot;1E-60&quot;/&gt;
    &lt;property name=&quot;growSkipInterval&quot; value=&quot;8&quot;/&gt;
    &lt;property name=&quot;linguist&quot; value=&quot;lexTreeLinguist&quot;/&gt;
    &lt;property name=&quot;checkStateOrder&quot; value=&quot;false&quot;/&gt;
    &lt;property name=&quot;keepAllTokens&quot; value=&quot;true&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;logMath&quot;
      type=&quot;edu.cmu.sphinx.util.LogMath&quot;&gt;
    &lt;property name=&quot;logBase&quot; value=&quot;1.0001&quot;/&gt;
    &lt;property name=&quot;useAddTable&quot; value=&quot;true&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;lexTreeLinguist&quot;
      type=&quot;edu.cmu.sphinx.linguist.lextree.LexTreeLinguist&quot;&gt;
    &lt;property name=&quot;silenceInsertionProbability&quot;
     value=&quot;${silenceInsertionProbability}&quot;/&gt;
    &lt;property name=&quot;wantUnigramSmear&quot; value=&quot;true&quot;/&gt;
    &lt;property name=&quot;fillerInsertionProbability&quot; value=&quot;.02&quot;/&gt;
    &lt;property name=&quot;addFillerWords&quot; value=&quot;true&quot;/&gt;
    &lt;property name=&quot;acousticModel&quot; value=&quot;hub4&quot;/&gt;
    &lt;property name=&quot;languageModel&quot; value=&quot;trigramModel&quot;/&gt;
    &lt;property name=&quot;wordInsertionProbability&quot;
     value=&quot;${wordInsertionProbability}&quot;/&gt;
    &lt;property name=&quot;languageWeight&quot; value=&quot;11&quot;/&gt;
    &lt;property name=&quot;logMath&quot; value=&quot;logMath&quot;/&gt;
    &lt;property name=&quot;dictionary&quot; value=&quot;dictionary&quot;/&gt;
    &lt;property name=&quot;unigramSmearWeight&quot; value=&quot;1&quot;/&gt;
    &lt;property name=&quot;cacheSize&quot; value=&quot;0&quot;/&gt;
    &lt;property name=&quot;generateUnitStates&quot; value=&quot;false&quot;/&gt;
    &lt;property name=&quot;unitManager&quot; value=&quot;unitManager&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;hub4&quot;
    type=&quot;edu.cmu.sphinx.model.acoustic.HUB4_8gau_13dCep_16k_40mel_133Hz_6855Hz.Model&quot;&gt;
    &lt;property name=&quot;loader&quot; value=&quot;sphinx3Loader&quot;/&gt;
    &lt;property name=&quot;unitManager&quot; value=&quot;unitManager&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;sphinx3Loader&quot;
           type=&quot;edu.cmu.sphinx.model.acoustic.HUB4_8gau_13dCep_16k_40mel_133Hz_6855Hz.ModelLoader&quot;&gt;
    &lt;property name=&quot;logMath&quot; value=&quot;logMath&quot;/&gt;
    &lt;property name=&quot;unitManager&quot; value=&quot;unitManager&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;trigramModel&quot;
      type=&quot;edu.cmu.sphinx.linguist.language.ngram.large.LargeTrigramModel&quot;&gt;
    &lt;property name=&quot;unigramWeight&quot; value=&quot;.5&quot;/&gt;
    &lt;property name=&quot;maxDepth&quot; value=&quot;3&quot;/&gt;
    &lt;property name=&quot;logMath&quot; value=&quot;logMath&quot;/&gt;
    &lt;property name=&quot;dictionary&quot; value=&quot;dictionary&quot;/&gt;
    &lt;property name=&quot;location&quot;
              value=&quot;/lab/speech/sphinx4/data/hub4_model/language_model.arpaformat.DMP&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;flatUnigramModel&quot;
            type=&quot;edu.cmu.sphinx.linguist.language.ngram.SimpleNGramModel&quot;&gt;
    &lt;property name=&quot;location&quot;
               value=&quot;hub4.flat_unigram.lm&quot;/&gt;
    &lt;property name=&quot;logMath&quot; value=&quot;logMath&quot;/&gt;
    &lt;property name=&quot;dictionary&quot; value=&quot;dictionary&quot;/&gt;
    &lt;property name=&quot;maxDepth&quot; value=&quot;1&quot;/&gt;
    &lt;property name=&quot;unigramWeight&quot; value=&quot;.7&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;dictionary&quot;
      type=&quot;edu.cmu.sphinx.linguist.dictionary.FastDictionary&quot;&gt;
    &lt;property name=&quot;dictionaryPath&quot; value=&quot;resource:/edu.cmu.sphinx.model.acoustic.HUB4_8gau_13dCep_16k_40mel_133Hz_6855Hz.Model!/edu/cmu/sphinx/model/acoustic/HUB4_8gau_13dCep_16k_40mel_133Hz_6855Hz/cmudict.06d&quot;/&gt;
    &lt;property name=&quot;fillerPath&quot; value=&quot;resource:/edu.cmu.sphinx.model.acoustic.HUB4_8gau_13dCep_16k_40mel_133Hz_6855Hz.Model!/edu/cmu/sphinx/model/acoustic/HUB4_8gau_13dCep_16k_40mel_133Hz_6855Hz/fillerdict&quot;/&gt;
    &lt;property name=&quot;addSilEndingPronunciation&quot; value=&quot;false&quot;/&gt;
    &lt;property name=&quot;allowMissingWords&quot; value=&quot;false&quot;/&gt;
    &lt;property name=&quot;unitManager&quot; value=&quot;unitManager&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;trivialPruner&quot;
      type=&quot;edu.cmu.sphinx.decoder.pruner.SimplePruner&quot;&gt;
&lt;/component&gt;

&lt;component name=&quot;threadedScorer&quot;
      type=&quot;edu.cmu.sphinx.decoder.scorer.ThreadedAcousticScorer&quot;&gt;
    &lt;property name=&quot;numThreads&quot; value=&quot;0&quot;/&gt;
    &lt;property name=&quot;scoreablesKeepFeature&quot; value=&quot;true&quot;/&gt;
    &lt;property name=&quot;frontend&quot; value=&quot;${frontend}&quot;/&gt;
    &lt;property name=&quot;isCpuRelative&quot; value=&quot;true&quot;/&gt;
    &lt;property name=&quot;minScoreablesPerThread&quot; value=&quot;10&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;unitManager&quot;
    type=&quot;edu.cmu.sphinx.linguist.acoustic.UnitManager&quot;/&gt;

&lt;component name=&quot;mfcFrontEnd&quot;
      type=&quot;edu.cmu.sphinx.frontend.FrontEnd&quot;&gt;
    &lt;propertylist name=&quot;pipeline&quot;&gt;
        &lt;item&gt;streamDataSource&lt;/item&gt;
        &lt;item&gt;premphasizer&lt;/item&gt;
        &lt;item&gt;windower&lt;/item&gt;
        &lt;item&gt;fft&lt;/item&gt;
        &lt;item&gt;melFilterBank&lt;/item&gt;
        &lt;item&gt;dct&lt;/item&gt;
        &lt;item&gt;batchCMN&lt;/item&gt;
        &lt;item&gt;featureExtraction&lt;/item&gt;
    &lt;/propertylist&gt;
&lt;/component&gt;

&lt;component name=&quot;mfcLiveFrontEnd&quot; type=&quot;edu.cmu.sphinx.frontend.FrontEnd&quot;&gt;
    &lt;propertylist name=&quot;pipeline&quot;&gt;
        &lt;item&gt;concatDataSource &lt;/item&gt;
        &lt;item&gt;speechClassifier &lt;/item&gt;
        &lt;item&gt;speechMarker &lt;/item&gt;
        &lt;item&gt;nonSpeechDataFilter &lt;/item&gt;
        &lt;item&gt;premphasizer &lt;/item&gt;
        &lt;item&gt;windower &lt;/item&gt;
        &lt;item&gt;fft &lt;/item&gt;
        &lt;item&gt;melFilterBank &lt;/item&gt;
        &lt;item&gt;dct &lt;/item&gt;
        &lt;item&gt;liveCMN &lt;/item&gt;
        &lt;item&gt;featureExtraction &lt;/item&gt;
    &lt;/propertylist&gt;
&lt;/component&gt;

&lt;component name=&quot;frameDropper&quot;
type=&quot;edu.cmu.sphinx.frontend.feature.FrameDropper&quot;&gt;
    &lt;property name=&quot;dropEveryNthFrame&quot; value=&quot;2&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;concatDataSource&quot;
            type=&quot;edu.cmu.sphinx.frontend.util.ConcatFileDataSource&quot;&gt;
    &lt;property name=&quot;sampleRate&quot; value=&quot;16000&quot;/&gt;
    &lt;property name=&quot;skip&quot; value=&quot;${skip}&quot;/&gt;
    &lt;property name=&quot;transcriptFile&quot; value=&quot;reference.txt&quot;/&gt;
    &lt;property name=&quot;silenceFile&quot;
     value=&quot;/lab/speech/sphinx4/data/tidigits/test/raw16k/silence1sec.raw&quot;/&gt;
    &lt;property name=&quot;bytesPerRead&quot; value=&quot;320&quot;/&gt;
    &lt;property name=&quot;batchFile&quot;
 value=&quot;/lab/speech/sphinx4/data/hub4/eval99/unsupervised/bn99en_1.batch&quot;/&gt;
    &lt;property name=&quot;addRandomSilence&quot; value=&quot;true&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;speechClassifier&quot;
            type=&quot;edu.cmu.sphinx.frontend.endpoint.SpeechClassifier&quot;&gt;
    &lt;property name=&quot;threshold&quot; value=&quot;16&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;nonSpeechDataFilter&quot;
            type=&quot;edu.cmu.sphinx.frontend.endpoint.NonSpeechDataFilter&quot;/&gt;

&lt;component name=&quot;speechMarker&quot;
            type=&quot;edu.cmu.sphinx.frontend.endpoint.SpeechMarker&quot; &gt;
    &lt;property name=&quot;speechTrailer&quot; value=&quot;50&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;liveCMN&quot;
            type=&quot;edu.cmu.sphinx.frontend.feature.LiveCMN&quot;/&gt;

&lt;component name=&quot;streamDataSource&quot;
      type=&quot;edu.cmu.sphinx.frontend.util.StreamDataSource&quot;&gt;
    &lt;property name=&quot;sampleRate&quot; value=&quot;16000&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;premphasizer&quot;
      type=&quot;edu.cmu.sphinx.frontend.filter.Preemphasizer&quot;&gt;
&lt;/component&gt;

&lt;component name=&quot;windower&quot;
      type=&quot;edu.cmu.sphinx.frontend.window.RaisedCosineWindower&quot;&gt;
&lt;/component&gt;

&lt;component name=&quot;fft&quot;
      type=&quot;edu.cmu.sphinx.frontend.transform.DiscreteFourierTransform&quot;&gt;
&lt;/component&gt;

&lt;component name=&quot;melFilterBank&quot;
      type=&quot;edu.cmu.sphinx.frontend.frequencywarp.MelFrequencyFilterBank&quot;&gt;
&lt;/component&gt;

&lt;component name=&quot;dct&quot;
      type=&quot;edu.cmu.sphinx.frontend.transform.DiscreteCosineTransform&quot;&gt;
&lt;/component&gt;

&lt;component name=&quot;batchCMN&quot;
      type=&quot;edu.cmu.sphinx.frontend.feature.BatchCMN&quot;&gt;
&lt;/component&gt;

&lt;component name=&quot;featureExtraction&quot;
      type=&quot;edu.cmu.sphinx.frontend.feature.DeltasFeatureExtractor&quot;&gt;
&lt;/component&gt;

&lt;component name=&quot;activeListManager&quot;
      type=&quot;edu.cmu.sphinx.decoder.search.SimpleActiveListManager&quot;&gt;
    &lt;propertylist name=&quot;activeListFactories&quot;&gt;
        &lt;item&gt;unitExitActiveList&lt;/item&gt;
        &lt;item&gt;wordActiveList&lt;/item&gt;
        &lt;item&gt;wordActiveList&lt;/item&gt;
        &lt;item&gt;activeList&lt;/item&gt;
        &lt;item&gt;activeList&lt;/item&gt;
        &lt;item&gt;activeList&lt;/item&gt;
    &lt;/propertylist&gt;
&lt;/component&gt;

&lt;component name=&quot;unitExitActiveList&quot;
      type=&quot;edu.cmu.sphinx.decoder.search.PartitionActiveListFactory&quot;&gt;
    &lt;property name=&quot;absoluteBeamWidth&quot; value=&quot;-1&quot;/&gt;
    &lt;property name=&quot;logMath&quot; value=&quot;logMath&quot;/&gt;
    &lt;property name=&quot;relativeBeamWidth&quot; value=&quot;${relativeBeamWidth}&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;wordActiveList&quot;
      type=&quot;edu.cmu.sphinx.decoder.search.WordActiveListFactory&quot;&gt;
    &lt;property name=&quot;absoluteBeamWidth&quot; value=&quot;21&quot;/&gt;
    &lt;property name=&quot;logMath&quot; value=&quot;logMath&quot;/&gt;
    &lt;property name=&quot;relativeBeamWidth&quot; value=&quot;1E-25&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;activeList&quot;
      type=&quot;edu.cmu.sphinx.decoder.search.PartitionActiveListFactory&quot;&gt;
    &lt;property name=&quot;absoluteBeamWidth&quot; value=&quot;25000&quot;/&gt;
    &lt;property name=&quot;logMath&quot; value=&quot;logMath&quot;/&gt;
    &lt;property name=&quot;relativeBeamWidth&quot; value=&quot;1E-60&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;accuracyTracker&quot;
      type=&quot;edu.cmu.sphinx.instrumentation.BestPathAccuracyTracker&quot;&gt;
    &lt;property name=&quot;showRawResults&quot; value=&quot;false&quot;/&gt;
    &lt;property name=&quot;recognizer&quot; value=&quot;${recognizer}&quot;/&gt;
   &lt;property name=&quot;showAlignedResults&quot; value=&quot;false&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;speedTracker&quot;
      type=&quot;edu.cmu.sphinx.instrumentation.SpeedTracker&quot;&gt;
    &lt;property name=&quot;showTimers&quot; value=&quot;true&quot;/&gt;
    &lt;property name=&quot;frontend&quot; value=&quot;${frontend}&quot;/&gt;
    &lt;property name=&quot;recognizer&quot; value=&quot;${recognizer}&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;memoryTracker&quot;
      type=&quot;edu.cmu.sphinx.instrumentation.MemoryTracker&quot;&gt;
    &lt;property name=&quot;recognizer&quot; value=&quot;${recognizer}&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;recognizerMonitor&quot;
      type=&quot;edu.cmu.sphinx.instrumentation.RecognizerMonitor&quot;&gt;
    &lt;property name=&quot;recognizer&quot; value=&quot;${recognizer}&quot;/&gt;
    &lt;propertylist name=&quot;allocatedMonitors&quot;&gt;
        &lt;item&gt;configMonitor&lt;/item&gt;
    &lt;/propertylist&gt;
&lt;/component&gt;

&lt;component name=&quot;configMonitor&quot;
      type=&quot;edu.cmu.sphinx.instrumentation.ConfigMonitor&quot;&gt;
    &lt;property name=&quot;saveConfigAsXML&quot; value=&quot;true&quot;/&gt;
    &lt;property name=&quot;showConfig&quot; value=&quot;true&quot;/&gt;
&lt;/component&gt;

&lt;component name=&quot;beamFinder&quot;
      type=&quot;edu.cmu.sphinx.instrumentation.BeamFinder&quot;&gt;
    &lt;property name=&quot;showDetails&quot; value=&quot;true&quot;/&gt;
    &lt;property name=&quot;logMath&quot; value=&quot;logMath&quot;/&gt;
    &lt;property name=&quot;showSummary&quot; value=&quot;true&quot;/&gt;
    &lt;property name=&quot;recognizer&quot; value=&quot;${recognizer}&quot;/&gt;
    &lt;property name=&quot;enable&quot; value=&quot;false&quot;/&gt;
&lt;/component&gt;

    </config>

     

    • Einstein Mic

      Einstein Mic - 2008-02-22

      Thanks for your fast reply

       

    • Nickolay V. Shmyrev

      Nickolay V. Shmyrev - 2008-02-22

      You should rebuild the model. Search forum, this topic was discussed already. About Italian, join Voxforge, we already started model there.

       

Log in to post a comment.

Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.