examples : add whisper.android.java for compatibility with older Android versions using Java (#1382)

* save the recorded audio to a file

* Alignment -help

* Save the correct audio

* chage to a consistent coding style

* Correct typo

* Update examples/stream/stream.cpp

* Update examples/stream/stream.cpp

* Correct variable misuse

* Update examples/stream/stream.cpp

* Update examples/stream/stream.cpp

* Update examples/stream/stream.cpp

* Update examples/stream/stream.cpp

* add *.bin .cxx/ .gradle/ cmake-build-debug/ to gitignore

* add whisper.android.java

* Added support for older versions of Android of Java

* add examples for android java

* add README.md for android java

* add fullTranscribeWithTime

* 增加 toString()方法和测试

* change return type to void

* update to v1.4.1

* add WhisperService

* chage to whisper_full_get_segment_t1

* add method transcribeDataWithTime

* modified toString
```
return "[" + start + " --> " + end + "]:" + sentence;
```

* Optimize code logic

* update text view on handle

* set max lines

* change Chinese to English

* Update bindings/java/build.gradle

* Update .gitignore

* add android.java to github action

* chage android.java to   android_java in build.yml

* remove gradle

* chage jdk to temurin in android_java of CI

* chage jdk to temurin 11 in android_java of CI

* add x to gradlew

* set api-level for android_java of CI

* Update examples/whisper.android.java/app/src/main/jni/whisper/CMakeLists.txt

* add ndk version in build.gradle

* remove local.properties

* add testFullTranscribeWithTime

---------

Co-authored-by: litongmacos <litongjava@qq.com>
Co-authored-by: bobqianic <129547291+bobqianic@users.noreply.github.com>
This commit is contained in:
Tong Li
2023-11-12 06:31:58 -10:00
committed by GitHub
parent 9f8bbd3fee
commit 54a08bde29
59 changed files with 2299 additions and 1 deletions

View File

@ -9,6 +9,7 @@ archivesBaseName = 'whispercpp'
group = 'io.github.ggerganov'
version = '1.4.0'
sourceCompatibility = 1.8
targetCompatibility = 1.8

View File

@ -2,6 +2,7 @@ package io.github.ggerganov.whispercpp;
import com.sun.jna.Native;
import com.sun.jna.Pointer;
import io.github.ggerganov.whispercpp.bean.WhisperSegment;
import io.github.ggerganov.whispercpp.params.WhisperContextParams;
import io.github.ggerganov.whispercpp.params.WhisperFullParams;
import io.github.ggerganov.whispercpp.params.WhisperSamplingStrategy;
@ -9,6 +10,8 @@ import io.github.ggerganov.whispercpp.params.WhisperSamplingStrategy;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
/**
* Before calling most methods, you must call `initContext(modelPath)` to initialise the `ctx` Pointer.
@ -160,6 +163,28 @@ public class WhisperCpp implements AutoCloseable {
return str.toString().trim();
}
public List<WhisperSegment> fullTranscribeWithTime(WhisperFullParams whisperParams, float[] audioData) throws IOException {
if (ctx == null) {
throw new IllegalStateException("Model not initialised");
}
if (lib.whisper_full(ctx, whisperParams, audioData, audioData.length) != 0) {
throw new IOException("Failed to process audio");
}
int nSegments = lib.whisper_full_n_segments(ctx);
List<WhisperSegment> segments= new ArrayList<>(nSegments);
for (int i = 0; i < nSegments; i++) {
long t0 = lib.whisper_full_get_segment_t0(ctx, i);
String text = lib.whisper_full_get_segment_text(ctx, i);
long t1 = lib.whisper_full_get_segment_t1(ctx, i);
segments.add(new WhisperSegment(t0,t1,text));
}
return segments;
}
// public int getTextSegmentCount(Pointer ctx) {
// return lib.whisper_full_n_segments(ctx);

View File

@ -0,0 +1,47 @@
package io.github.ggerganov.whispercpp.bean;
/**
* Created by litonglinux@qq.com on 10/21/2023_7:48 AM
*/
public class WhisperSegment {
private long start, end;
private String sentence;
public WhisperSegment() {
}
public WhisperSegment(long start, long end, String sentence) {
this.start = start;
this.end = end;
this.sentence = sentence;
}
public long getStart() {
return start;
}
public long getEnd() {
return end;
}
public String getSentence() {
return sentence;
}
public void setStart(long start) {
this.start = start;
}
public void setEnd(long end) {
this.end = end;
}
public void setSentence(String sentence) {
this.sentence = sentence;
}
@Override
public String toString() {
return "[" + start + " --> " + end + "]:" + sentence;
}
}

View File

@ -2,6 +2,7 @@ package io.github.ggerganov.whispercpp;
import static org.junit.jupiter.api.Assertions.*;
import io.github.ggerganov.whispercpp.bean.WhisperSegment;
import io.github.ggerganov.whispercpp.params.CBool;
import io.github.ggerganov.whispercpp.params.WhisperFullParams;
import io.github.ggerganov.whispercpp.params.WhisperSamplingStrategy;
@ -11,6 +12,7 @@ import javax.sound.sampled.AudioInputStream;
import javax.sound.sampled.AudioSystem;
import java.io.File;
import java.io.FileNotFoundException;
import java.util.List;
class WhisperCppTest {
private static WhisperCpp whisper = new WhisperCpp();
@ -20,7 +22,8 @@ class WhisperCppTest {
static void init() throws FileNotFoundException {
// By default, models are loaded from ~/.cache/whisper/ and are usually named "ggml-${name}.bin"
// or you can provide the absolute path to the model file.
String modelName = "../../models/ggml-tiny.en.bin";
String modelName = "../../models/ggml-tiny.bin";
// String modelName = "../../models/ggml-tiny.en.bin";
try {
whisper.initContext(modelName);
// whisper.getFullDefaultParams(WhisperSamplingStrategy.WHISPER_SAMPLING_GREEDY);
@ -99,4 +102,44 @@ class WhisperCppTest {
audioInputStream.close();
}
}
@Test
void testFullTranscribeWithTime() throws Exception {
if (!modelInitialised) {
System.out.println("Model not initialised, skipping test");
return;
}
// Given
File file = new File(System.getProperty("user.dir"), "../../samples/jfk.wav");
AudioInputStream audioInputStream = AudioSystem.getAudioInputStream(file);
byte[] b = new byte[audioInputStream.available()];
float[] floats = new float[b.length / 2];
// WhisperFullParams params = whisper.getFullDefaultParams(WhisperSamplingStrategy.WHISPER_SAMPLING_GREEDY);
WhisperFullParams params = whisper.getFullDefaultParams(WhisperSamplingStrategy.WHISPER_SAMPLING_BEAM_SEARCH);
params.setProgressCallback((ctx, state, progress, user_data) -> System.out.println("progress: " + progress));
params.print_progress = CBool.FALSE;
// params.initial_prompt = "and so my fellow Americans um, like";
try {
audioInputStream.read(b);
for (int i = 0, j = 0; i < b.length; i += 2, j++) {
int intSample = (int) (b[i + 1]) << 8 | (int) (b[i]) & 0xFF;
floats[j] = intSample / 32767.0f;
}
List<WhisperSegment> segments = whisper.fullTranscribeWithTime(params, floats);
assertTrue(segments.size() > 0, "The size of segments should be greater than 0");
for (WhisperSegment segment : segments) {
System.out.println(segment);
}
} finally {
audioInputStream.close();
}
}
}