Attempted: Transcribing a small .wav file
Problem: Running into an error - details and code below. The code is a ditto of a sample at https://github.com/cmusphinx/sphinx4/blob/master/sphinx4-samples/src/main/java/edu/cmu/sphinx/demo/transcriber/TranscriberDemo.java
Not sure what is incorrect here. Totally stumped! Please help..
Error:
Exception in thread "main" java.lang.NullPointerException
at edu.cmu.sphinx.result.Lattice.<init>(Lattice.java:171)
at edu.cmu.sphinx.api.SpeechResult.<init>(SpeechResult.java:38)
at edu.cmu.sphinx.api.AbstractSpeechRecognizer.getResult(AbstractSpeechRecognizer.java:61)
at com.microsoft.SpeechRecognitionSamples.TranscriberDemo.main(TranscriberDemo.java:43)
Source code:
package com.microsoft.SpeechRecognitionSamples;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.logging.Level;
import java.util.logging.Logger;
import edu.cmu.sphinx.api.Configuration;
import edu.cmu.sphinx.api.SpeechResult;
import edu.cmu.sphinx.api.StreamSpeechRecognizer;
import edu.cmu.sphinx.result.WordResult;
public class TranscriberDemo {
public static void main(String[] args) throws Exception {
try {
System.out.println("Loading models...");
Configuration configuration = new Configuration();
// Load model from the jar
configuration.setAcousticModelPath("resource:/edu/cmu/sphinx/models/en-us/en-us");
// You can also load model from folder
// configuration.setAcousticModelPath("file:en-us");
configuration.setDictionaryPath("resource:/edu/cmu/sphinx/models/en-us/cmudict-en-us.dict");
configuration.setLanguageModelPath("resource:/edu/cmu/sphinx/models/en-us/en-us.lm.bin");
StreamSpeechRecognizer recognizer = new StreamSpeechRecognizer(configuration);
InputStream stream = new FileInputStream(new File("C:\\Users\\vajra\\Desktop\\Projects\\whatstheweatherlike.wav"));
stream.skip(44);
// Simple recognition with generic model
recognizer.startRecognition(stream);
SpeechResult result;
while ((result = recognizer.getResult()) != null) {
System.out.format("Hypothesis: %s\n", result.getHypothesis());
System.out.println("List of recognized words and their times:");
for (WordResult r : result.getWords()) {
System.out.println(r);
}
System.out.println("Best 3 hypothesis:");
for (String s : result.getNbest(3))
System.out.println(s);
}
recognizer.stopRecognition();
} catch (IOException ex) {
Logger.getLogger(TranscriberDemo.class.getName()).log(Level.SEVERE, null, ex);
System.out.println(ex);
}
}
}
Output:
Loading models...
18:22:39.036 INFO unitManager CI Unit: *+NSN+
18:22:39.040 INFO unitManager CI Unit: *+SPN+
18:22:39.040 INFO unitManager CI Unit: AA
18:22:39.040 INFO unitManager CI Unit: AE
18:22:39.040 INFO unitManager CI Unit: AH
18:22:39.040 INFO unitManager CI Unit: AO
18:22:39.040 INFO unitManager CI Unit: AW
18:22:39.041 INFO unitManager CI Unit: AY
18:22:39.041 INFO unitManager CI Unit: B
18:22:39.041 INFO unitManager CI Unit: CH
18:22:39.041 INFO unitManager CI Unit: D
18:22:39.042 INFO unitManager CI Unit: DH
18:22:39.042 INFO unitManager CI Unit: EH
18:22:39.042 INFO unitManager CI Unit: ER
18:22:39.042 INFO unitManager CI Unit: EY
18:22:39.042 INFO unitManager CI Unit: F
18:22:39.042 INFO unitManager CI Unit: G
18:22:39.043 INFO unitManager CI Unit: HH
18:22:39.043 INFO unitManager CI Unit: IH
18:22:39.043 INFO unitManager CI Unit: IY
18:22:39.043 INFO unitManager CI Unit: JH
18:22:39.043 INFO unitManager CI Unit: K
18:22:39.043 INFO unitManager CI Unit: L
18:22:39.044 INFO unitManager CI Unit: M
18:22:39.044 INFO unitManager CI Unit: N
18:22:39.044 INFO unitManager CI Unit: NG
18:22:39.044 INFO unitManager CI Unit: OW
18:22:39.044 INFO unitManager CI Unit: OY
18:22:39.044 INFO unitManager CI Unit: P
18:22:39.045 INFO unitManager CI Unit: R
18:22:39.045 INFO unitManager CI Unit: S
18:22:39.045 INFO unitManager CI Unit: SH
18:22:39.045 INFO unitManager CI Unit: T
18:22:39.045 INFO unitManager CI Unit: TH
18:22:39.045 INFO unitManager CI Unit: UH
18:22:39.046 INFO unitManager CI Unit: UW
18:22:39.046 INFO unitManager CI Unit: V
18:22:39.046 INFO unitManager CI Unit: W
18:22:39.046 INFO unitManager CI Unit: Y
18:22:39.046 INFO unitManager CI Unit: Z
18:22:39.046 INFO unitManager CI Unit: ZH
18:22:39.917 INFO autoCepstrum Cepstrum component auto-configured as follows: autoCepstrum {MelFrequencyFilterBank, Denoise, DiscreteCosineTransform2, Lifter}
18:22:39.941 INFO dictionary Loading dictionary from: jar:file:/C:/Users/vajra/.m2/repository/edu/cmu/sphinx/sphinx4-data/5prealpha-SNAPSHOT/sphinx4-data-5prealpha-SNAPSHOT.jar!/edu/cmu/sphinx/models/en-us/cmudict-en-us.dict
18:22:40.111 INFO dictionary Loading filler dictionary from: jar:file:/C:/Users/vajra/.m2/repository/edu/cmu/sphinx/sphinx4-data/5prealpha-SNAPSHOT/sphinx4-data-5prealpha-SNAPSHOT.jar!/edu/cmu/sphinx/models/en-us/en-us/noisedict
18:22:40.112 INFO acousticModelLoader Loading tied-state acoustic model from: jar:file:/C:/Users/vajra/.m2/repository/edu/cmu/sphinx/sphinx4-data/5prealpha-SNAPSHOT/sphinx4-data-5prealpha-SNAPSHOT.jar!/edu/cmu/sphinx/models/en-us/en-us
18:22:40.112 INFO acousticModelLoader Pool means Entries: 16128
18:22:40.112 INFO acousticModelLoader Pool variances Entries: 16128
18:22:40.112 INFO acousticModelLoader Pool transition_matrices Entries: 42
18:22:40.112 INFO acousticModelLoader Pool senones Entries: 5126
18:22:40.112 INFO acousticModelLoader Gaussian weights: mixture_weights. Entries: 15378
18:22:40.112 INFO acousticModelLoader Pool senones Entries: 5126
18:22:40.112 INFO acousticModelLoader Context Independent Unit Entries: 42
18:22:40.113 INFO acousticModelLoader HMM Manager: 137095 hmms
18:22:40.113 INFO acousticModel CompositeSenoneSequences: 0
18:22:40.114 INFO trieNgramModel Loading n-gram language model from: jar:file:/C:/Users/vajra/.m2/repository/edu/cmu/sphinx/sphinx4-data/5prealpha-SNAPSHOT/sphinx4-data-5prealpha-SNAPSHOT.jar!/edu/cmu/sphinx/models/en-us/en-us.lm.bin
18:22:41.581 INFO dictionary The dictionary is missing a phonetic transcription for the word '3-d'
18:22:41.582 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word '3-d'
18:22:41.602 INFO dictionary The dictionary is missing a phonetic transcription for the word 'adjustors'
18:22:41.602 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'adjustors'
18:22:41.604 INFO dictionary The dictionary is missing a phonetic transcription for the word 'adulyadej'
18:22:41.604 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'adulyadej'
18:22:41.786 INFO dictionary The dictionary is missing a phonetic transcription for the word 'chloroflourocarbons'
18:22:41.786 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'chloroflourocarbons'
18:22:41.869 INFO dictionary The dictionary is missing a phonetic transcription for the word 'd�j�'
18:22:41.870 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'd�j�'
18:22:41.937 INFO dictionary The dictionary is missing a phonetic transcription for the word 'iife'
18:22:41.938 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'iife'
18:22:41.961 INFO dictionary The dictionary is missing a phonetic transcription for the word 'mm-hm'
18:22:41.961 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'mm-hm'
18:22:41.961 INFO dictionary The dictionary is missing a phonetic transcription for the word 'mm-hmm'
18:22:41.961 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'mm-hmm'
18:22:41.961 INFO dictionary The dictionary is missing a phonetic transcription for the word 'mmmm'
18:22:41.961 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'mmmm'
18:22:41.966 INFO dictionary The dictionary is missing a phonetic transcription for the word 'ngo's'
18:22:41.966 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'ngo's'
18:22:41.968 INFO dictionary The dictionary is missing a phonetic transcription for the word 'occured'
18:22:41.968 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'occured'
18:22:41.968 INFO dictionary The dictionary is missing a phonetic transcription for the word 'offical'
18:22:41.968 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'offical'
18:22:41.968 INFO dictionary The dictionary is missing a phonetic transcription for the word 'officals'
18:22:41.968 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'officals'
18:22:41.988 INFO dictionary The dictionary is missing a phonetic transcription for the word 'port_au_prince'
18:22:41.988 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'port_au_prince'
18:22:41.989 INFO dictionary The dictionary is missing a phonetic transcription for the word 'possiblity'
18:22:41.989 WARNING trieNgramModel The dictionary is missing a phonetic transcription for the word 'possiblity'
18:22:42.032 WARNING trieNgramModel Dictionary is missing 15 words that are contained in the language model.
18:22:42.992 INFO dictionary The dictionary is missing a phonetic transcription for the word 'occured'
18:22:42.994 INFO dictionary The dictionary is missing a phonetic transcription for the word 'iife'
18:22:42.994 INFO dictionary The dictionary is missing a phonetic transcription for the word 'port_au_prince'
18:22:43.000 INFO dictionary The dictionary is missing a phonetic transcription for the word 'd�j�'
18:22:43.001 INFO dictionary The dictionary is missing a phonetic transcription for the word 'mmmm'
18:22:43.002 INFO dictionary The dictionary is missing a phonetic transcription for the word 'offical'
18:22:43.005 INFO dictionary The dictionary is missing a phonetic transcription for the word 'possiblity'
18:22:43.011 INFO dictionary The dictionary is missing a phonetic transcription for the word '3-d'
18:22:43.016 INFO dictionary The dictionary is missing a phonetic transcription for the word 'adulyadej'
18:22:43.029 INFO dictionary The dictionary is missing a phonetic transcription for the word 'ngo's'
18:22:43.029 INFO dictionary The dictionary is missing a phonetic transcription for the word 'mm-hm'
18:22:43.029 INFO dictionary The dictionary is missing a phonetic transcription for the word 'adjustors'
18:22:43.031 INFO dictionary The dictionary is missing a phonetic transcription for the word 'officals'
18:22:43.036 INFO dictionary The dictionary is missing a phonetic transcription for the word 'mm-hmm'
18:22:43.037 INFO dictionary The dictionary is missing a phonetic transcription for the word 'chloroflourocarbons'
18:22:43.875 INFO lexTreeLinguist Max CI Units 43
18:22:43.875 INFO lexTreeLinguist Unit table size 79507
18:22:43.878 INFO speedTracker # ----------------------------- Timers----------------------------------------
18:22:43.878 INFO speedTracker # Name Count CurTime MinTime MaxTime AvgTime TotTime
18:22:43.879 INFO speedTracker Compile 1 1.8430s 1.8430s 1.8430s 1.8430s 1.8430s
18:22:43.879 INFO speedTracker Load AM 1 2.0140s 2.0140s 2.0140s 2.0140s 2.0140s
18:22:43.879 INFO speedTracker Load LM 1 1.9190s 1.9190s 1.9190s 1.9190s 1.9190s
18:22:43.879 INFO speedTracker Load Dictionary 1 0.1700s 0.1700s 0.1700s 0.1700s 0.1700s
18:22:46.140 INFO speedTracker This Time Audio: 1.22s Proc: 2.20s Speed: 1.80 X real time
18:22:46.141 INFO speedTracker Total Time Audio: 1.22s Proc: 2.20s 1.80 X real time
18:22:46.141 INFO memoryTracker Mem Total: 630.50 Mb Free: 220.90 Mb
18:22:46.141 INFO memoryTracker Used: This: 409.60 Mb Avg: 409.60 Mb Max: 409.60 Mb
18:22:46.141 INFO trieNgramModel LM Cache Size: 1730 Hits: 153479 Misses: 1730
Exception in thread "main" java.lang.NullPointerException
at edu.cmu.sphinx.result.Lattice.<init>(Lattice.java:171)
at edu.cmu.sphinx.api.SpeechResult.<init>(SpeechResult.java:38)
at edu.cmu.sphinx.api.AbstractSpeechRecognizer.getResult(AbstractSpeechRecognizer.java:61)
at com.microsoft.SpeechRecognitionSamples.TranscriberDemo.main(TranscriberDemo.java:43)
Maven POM:
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0 </modelVersion>
<groupId>com.microsoft.SpeechRecognitionSamples </groupId>
<artifactId>SpeechToTextCMUSphinx </artifactId>
<version>0.0.1-SNAPSHOT </version>
<packaging>jar </packaging>
<name>SpeechToTextCMUSphinx </name>
<url>http://maven.apache.org </url>
<properties>
<project.build.sourceEncoding>UTF-8 </project.build.sourceEncoding>
</properties>
<repositories>
<repository>
<id>snapshots-repo </id>
<url>https://oss.sonatype.org/content/repositories/snapshots </url>
<releases> <enabled>false </enabled> </releases>
<snapshots> <enabled>true </enabled> </snapshots>
</repository>
</repositories>
<dependencies>
<dependency>
<groupId>edu.cmu.sphinx </groupId>
<artifactId>sphinx4-core </artifactId>
<version>5prealpha-SNAPSHOT </version>
</dependency>
<dependency>
<groupId>edu.cmu.sphinx </groupId>
<artifactId>sphinx4-data </artifactId>
<version>5prealpha-SNAPSHOT </version>
</dependency>
<dependency>
<groupId>junit </groupId>
<artifactId>junit </artifactId>
<version>3.8.1 </version>
<scope>test </scope>
</dependency>
</dependencies>
<build>
<sourceDirectory>src/main/ </sourceDirectory>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins </groupId>
<artifactId>maven-shade-plugin </artifactId>
<version>2.3 </version>
<executions>
<execution>
<phase>package </phase>
<goals>
<goal>shade </goal>
</goals>
<configuration>
<filters>
<filter>
<artifact>*:* </artifact>
<excludes>
<exclude>META-INF/*.SF </exclude>
<exclude>META-INF/*.DSA </exclude>
<exclude>META-INF/*.RSA </exclude>
</excludes>
</filter>
</filters>
<!-- Additional configuration. -->
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins </groupId>
<artifactId>maven-surefire-plugin </artifactId>
<version>2.18.1 </version>
<configuration>
<useFile>false </useFile>
<disableXmlReport>true </disableXmlReport>
<!-- If you have classpath issue like NoDefClassError,... -->
<!-- useManifestOnlyJar>false </useManifestOnlyJar -->
<includes>
<include>**/*Test.* </include>
<include>**/*Suite.* </include>
</includes>
</configuration>
</plugin>
</plugins>
</build>
</project>
