Examples of edu.cmu.sphinx.linguist.dictionary.FullDictionary

Package edu.cmu.sphinx.linguist.dictionary

Examples of edu.cmu.sphinx.linguist.dictionary.FullDictionary

edu.cmu.sphinx.linguist.dictionary.FullDictionary
Creates a dictionary by reading in an ASCII-based Sphinx-3 format dictionary. Each line of the dictionary specifies the word, followed by spaces or tab, followed by the pronunciation (by way of the list of phones) of the word. Each word can have more than one pronunciations. For example, a digits dictionary will look like:
```
 ONE                  HH W AH N ONE(2)               W AH N TWO                  T UW THREE                TH R IY FOUR                 F AO R FIVE                 F AY V SIX                  S IH K S SEVEN                S EH V AH N EIGHT                EY T NINE                 N AY N ZERO                 Z IH R OW ZERO(2)              Z IY R OW OH                   OW 
```
In the above example, the words "one" and "zero" have two pronunciations each.
This dictionary will read in all the words and its pronunciation(s) at startup. Therefore, if the dictionary is big, it will take longer to load and will consume more memory.

    public void testNgram() throws IOException {
        URL dictUrl = getClass().getResource("100.dict");
        URL noisedictUrl = getClass()
                .getResource("/edu/cmu/sphinx/models/acoustic/wsj/noisedict");


        Dictionary dictionary = new FullDictionary(dictUrl,
                                                   noisedictUrl,
                                                   null,
                                                   false,
                                                   null,
                                                   false,
                                                   false,
                                                   new UnitManager());


        URL lm = getClass().getResource("100.arpa.dmp");
        LargeTrigramModel model = new LargeTrigramModel("",
                                                        lm,
                                                        null,
                                                        100,
                                                        100,
                                                        false,
                                                        3,
                                                        dictionary,
                                                        false,
                                                        1.0f,
                                                        1.0f,
                                                        1.0f,
                                                        false);
        dictionary.allocate();
        model.allocate();
        assertThat(model.getMaxDepth(), equalTo(3));


        Word[] words = {
            new Word("huggins", null, false),

View Full Code Here

        URL noiseDictUrl =
                getClass().getResource(
                        "/edu/cmu/sphinx/models/acoustic/wsj/noisedict");


        dictionary =
                new FullDictionary(dictUrl, noiseDictUrl, null, false, null,
                        false, false, new UnitManager());
        dictionary.allocate();
    }

View Full Code Here

        URL noiseDictUrl =
                getClass().getResource(
                        "/edu/cmu/sphinx/models/acoustic/wsj/noisedict");


        dictionary =
                new FullDictionary(dictUrl, noiseDictUrl, null, false, null,
                        false, false, new UnitManager());
        dictionary.allocate();
    }

View Full Code Here

TOP

Related Classes of edu.cmu.sphinx.linguist.dictionary.FullDictionary

edu.cmu.sphinx.linguist.g2p.G2PConverter

edu.cmu.sphinx.linguist.language.ngram.DynamicTrigramModelTest

edu.cmu.sphinx.linguist.language.ngram.large.LargeNgramTest

edu.cmu.sphinx.linguist.WordSequenceTest

edu.cmu.sphinx.util.ExtendedStreamTokenizer

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.