详细介绍：Java集成whisper.cpp

windows11,idea,java25,javaFx25

下载cmake

下载Visual Studio 的 C++ 构建工具，Visual Studio Community 2022（免费版），勾选 Desktop development with C++

1.打开 Visual Studio（管理员），切换到 whisper.cpp 源代码目录：

E:
cd E:\My_Dream\whisper.cpp

2. 创建并配置构建目录（这会在 whisper.cpp 文件夹内创建一个名为 build 的子文件夹）

cmake -B build

3.构建项目（使用 -j 可以并行编译；在 Windows 上默认使用所有可用核心）

cmake --build build --config Release -j

成功构建后，可执行文件（如 whisper-cli.exe、main.exe 等）将位于 build\bin\Release\ 目录下。

推荐手动下载模型！！！

1. 访问 Hugging Face 仓库。
2. 找到文件 ggml-small.bin（不是 ggml-small.en.bin，除非您只用英语）。
3. 点击下载（或直接链接：https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin）
4. 将下载的文件放到您的项目目录下：E:\My_Dream\whisper.cpp\models\ggml-small.bin
5. 如果 models 文件夹不存在，先创建它：mkdir models
6. 验证：在命令提示符中运行 dir models，确认看到 ggml-small.bin 且文件大小约 488 MB。

重新构建 whisper.cpp（静态链接，避免 DLL 兼容问题）

进入项目目录：

cd E:\My_Dream\whisper.cpp

删除旧构建目录（清理）：

rmdir /s /q build

重新配置并构建（明确指定静态共享库关闭）：

cmake -B build -DBUILD_SHARED_LIBS=OFF
cmake --build build --config Release -j

第三步：运行测试

build\bin\Release\whisper-cli.exe -m models/ggml-small.bin -f samples/jfk.wav

预期输出

[00:00:00.000 --> 00:00:11.000]   And so, my fellow Americans: ask not what your country can do for you—ask what you can do for your country.

项目添加依赖

<!--        whisper-jni-->
  <dependency>
  <groupId>io.github.givimad</groupId>
  <artifactId>whisper-jni</artifactId>
  <version>1.7.1</version>
  </dependency>

fxml页面与控制器

<?xml version="1.0" encoding="UTF-8"?>
  <?import javafx.geometry.Insets?>
    <?import javafx.scene.control.*?>
      <?import javafx.scene.layout.*?>
        <?import javafx.collections.FXCollections?>
          <?import java.lang.String?>
              <VBox spacing="15.0" alignment="TOP_CENTER" xmlns="http://javafx.com/javafx" xmlns:fx="http://javafx.com/fxml/1"
              fx:controller="com.flower.controller.WhisperTranscribeController">  <!-- 请自行创建对应 Controller -->
              <padding>
                <Insets top="20" right="30" bottom="20" left="30"/>
              </padding>
              <Label text="本地语音转文字（Whisper）" style="-fx-font-size: 20px; -fx-font-weight: bold;"/>
                <GridPane hgap="10" vgap="12" alignment="CENTER">
                <columnConstraints>
                  <ColumnConstraints hgrow="SOMETIMES" minWidth="120"/>
                  <ColumnConstraints hgrow="ALWAYS"/>
                </columnConstraints>
                <!-- 模型路径 -->
                  <Label text="模型文件：" GridPane.rowIndex="0" GridPane.columnIndex="0"/>
                    <HBox spacing="8" alignment="CENTER_LEFT" GridPane.rowIndex="0" GridPane.columnIndex="1">
                    <TextField fx:id="modelPathField" prefWidth="400" promptText="选择 ggml-*.bin 模型文件"/>
                    <Button text="浏览..." onAction="#chooseModelFile"/>
                  </HBox>
                  <!-- 音频文件路径 -->
                    <Label text="音频文件：" GridPane.rowIndex="1" GridPane.columnIndex="0"/>
                      <HBox spacing="8" alignment="CENTER_LEFT" GridPane.rowIndex="1" GridPane.columnIndex="1">
                      <TextField fx:id="audioPathField" prefWidth="400" promptText="支持 wav、mp3 等（会自动转 16k 单声道）"/>
                      <Button text="浏览..." onAction="#chooseAudioFile"/>
                    </HBox>
                    <!-- 语言 -->
                      <Label text="语言：" GridPane.rowIndex="2" GridPane.columnIndex="0"/>
                        <ComboBox fx:id="languageCombo" prefWidth="200" GridPane.rowIndex="2" GridPane.columnIndex="1">
                        <items>
                            <FXCollections fx:factory="observableArrayList">
                            <String fx:value="auto"/>
                            <String fx:value="en"/>
                            <String fx:value="zh"/>
                            <String fx:value="ja"/>
                            <String fx:value="ko"/>
                            <String fx:value="fr"/>
                            <String fx:value="de"/>
                            <String fx:value="es"/>
                            <!-- 可继续添加 -->
                            </FXCollections>
                          </items>
                        <value><String fx:value="auto"/></value>
                      </ComboBox>
                      <!-- 是否翻译 -->
                        <CheckBox fx:id="translateCheck" text="翻译成英语" GridPane.rowIndex="3" GridPane.columnIndex="1"/>
                        <!-- 是否时间戳 -->
                          <CheckBox fx:id="timestampsCheck" text="输出带时间戳（字幕格式）" selected="true" GridPane.rowIndex="4" GridPane.columnIndex="1"/>
                          <!-- 输出格式 -->
                            <Label text="输出格式：" GridPane.rowIndex="5" GridPane.columnIndex="0"/>
                              <ComboBox fx:id="outputFormatCombo" prefWidth="200" GridPane.rowIndex="5" GridPane.columnIndex="1">
                              <items>
                                  <FXCollections fx:factory="observableArrayList">
                                  <String fx:value="txt"/>
                                  <String fx:value="srt"/>
                                  <String fx:value="vtt"/>
                                </FXCollections>
                              </items>
                            <value><String fx:value="txt"/></value>
                          </ComboBox>
                          <!-- 保存地址 -->
                            <Label text="保存位置：" GridPane.rowIndex="6" GridPane.columnIndex="0"/>
                              <HBox spacing="8" alignment="CENTER_LEFT" GridPane.rowIndex="6" GridPane.columnIndex="1">
                              <TextField fx:id="savePathField" prefWidth="400" promptText="选择保存文件或文件夹"/>
                              <Button text="浏览..." onAction="#chooseSavePath"/>
                            </HBox>
                          </GridPane>
                            <HBox spacing="20" alignment="CENTER">
                            <Button text="开始转录" fx:id="startButton" style="-fx-font-size: 16px; -fx-padding: 10 20;" onAction="#startTranscription"/>
                            <ProgressBar fx:id="progressBar" prefWidth="300" visible="false"/>
                          </HBox>
                          <Separator/>
                          <Label text="转录结果：" style="-fx-font-size: 16px;"/>
                          <TextArea fx:id="resultArea" prefHeight="300" wrapText="true" editable="false"/>
                        </VBox>

package com.flower.controller;
import io.github.givimad.whisperjni.WhisperContext;
import io.github.givimad.whisperjni.WhisperFullParams;
import io.github.givimad.whisperjni.WhisperJNI;
import javafx.application.Platform;
import javafx.concurrent.Task;
import javafx.fxml.FXML;
import javafx.scene.control.*;
import javafx.stage.FileChooser;
import javafx.stage.Stage;
import org.springframework.stereotype.Component;
import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioInputStream;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.UnsupportedAudioFileException;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.net.URL;
import java.nio.ByteBuffer;
import java.nio.ByteOrder;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.ResourceBundle;
@Component
public class WhisperTranscribeController extends BaseFormController{
@FXML
private TextField modelPathField;
@FXML private TextField audioPathField;
@FXML private TextField savePathField;
@FXML private ComboBox<String> languageCombo;
  @FXML private CheckBox translateCheck;
  @FXML private CheckBox timestampsCheck;
  @FXML private ComboBox<String> outputFormatCombo;
    @FXML private Button startButton;
    @FXML private ProgressBar progressBar;
    @FXML private TextArea resultArea;
    private Stage stage;
    private WhisperJNI whisperJNI;
    @Override
    public void initialize(URL url, ResourceBundle resourceBundle) {
    // 初始化语言默认值
    languageCombo.getSelectionModel().select("auto");
    outputFormatCombo.getSelectionModel().select("txt");
    // 初始化 whisper-jni
    try {
    WhisperJNI.loadLibrary();
    whisperJNI = new WhisperJNI();
    resultArea.appendText("Whisper JNI 加载成功\n");
    resultArea.appendText("系统信息：\n" + whisperJNI.getSystemInfo() + "\n");
    } catch (Exception e) {
    showAlert("错误", "无法加载 Whisper JNI 库: " + e.getMessage());
    e.printStackTrace();
    }
    // 默认模型路径（可根据您的实际路径修改）
    modelPathField.setText("E:/My_Dream/whisper.cpp/models/ggml-small.bin");
    }
    public void setStage(Stage stage) {
    this.stage = stage;
    }
    @FXML
    private void chooseModelFile() {
    File file = showFileChooser("选择 Whisper 模型文件", "Whisper 模型 (*.bin)", "*.bin");
    if (file != null) {
    modelPathField.setText(file.getAbsolutePath());
    }
    }
    /**
    * Java Sound API（javax.sound.sampled） 默认只支持有限的音频格式
    */
    @FXML
    private void chooseAudioFile() {
    File file = showFileChooser("选择音频文件", "音频文件", "*.wav");
    if (file != null) {
    audioPathField.setText(file.getAbsolutePath());
    }
    }
    @FXML
    private void chooseSavePath() {
    FileChooser fileChooser = new FileChooser();
    fileChooser.setTitle("保存转录结果");
    String format = outputFormatCombo.getValue();
    String ext = format != null ? format : "txt";
    fileChooser.getExtensionFilters().add(new FileChooser.ExtensionFilter(
    "转录文件 (*." + ext + ")", "*." + ext));
    fileChooser.setInitialFileName("transcription." + ext);
    File file = fileChooser.showSaveDialog(stage);
    if (file != null) {
    savePathField.setText(file.getAbsolutePath());
    }
    }
    private File showFileChooser(String title, String filterName, String... extensions) {
    FileChooser fileChooser = new FileChooser();
    fileChooser.setTitle(title);
    fileChooser.getExtensionFilters().add(new FileChooser.ExtensionFilter(filterName, extensions));
    return fileChooser.showOpenDialog(stage);
    }
    @FXML
    private void startTranscription() {
    String modelPath = modelPathField.getText().trim();
    String audioPath = audioPathField.getText().trim();
    String savePath = savePathField.getText().trim();
    if (modelPath.isEmpty() || audioPath.isEmpty()) {
    showAlert("错误", "请先选择模型文件和音频文件！");
    return;
    }
    startButton.setDisable(true);
    progressBar.setVisible(true);
    progressBar.setProgress(ProgressBar.INDETERMINATE_PROGRESS);
    resultArea.clear();
    resultArea.appendText("正在加载模型和处理音频，请稍等...\n");
    Task<String> task = new Task<>() {
      @Override
      protected String call() throws Exception {
      Path model = Paths.get(modelPath);
      try (WhisperContext ctx = whisperJNI.init(model)) {
      float[] samples = loadAudioSamples(audioPath);
      WhisperFullParams params = new WhisperFullParams();
      String lang = languageCombo.getValue();
      params.language = "auto".equals(lang) ? null : lang;
      params.translate = translateCheck.isSelected();
      params.printTimestamps = timestampsCheck.isSelected();
      int result = whisperJNI.full(ctx, params, samples, samples.length);
      if (result != 0) {
      throw new RuntimeException("Whisper 转录失败，错误码: " + result);
      }
      int segments = whisperJNI.fullNSegments(ctx);
      StringBuilder transcription = new StringBuilder();
      for (int i = 0; i < segments; i++) {
      String text = whisperJNI.fullGetSegmentText(ctx, i).trim();
      long t0 = whisperJNI.fullGetSegmentTimestamp0(ctx, i);
      long t1 = whisperJNI.fullGetSegmentTimestamp1(ctx, i);
      if (timestampsCheck.isSelected()) {
      transcription.append(formatTimestamp(t0))
      .append(" --> ")
      .append(formatTimestamp(t1))
      .append("\n");
      }
      transcription.append(text).append("\n\n");
      }
      // 保存文件
      if (!savePath.isEmpty()) {
      String format = outputFormatCombo.getValue();
      String content = switch (format) {
      case "srt" -> toSrt(transcription.toString(), segments, ctx);
      case "vtt" -> toVtt(transcription.toString());
      default -> transcription.toString();
      };
      saveToFile(savePath, content);
      }
      return transcription.toString();
      }
      }
      @Override
      protected void succeeded() {
      Platform.runLater(() -> {
      resultArea.appendText("\n转录完成！\n\n");
      resultArea.appendText(getValue());
      if (!savePath.isEmpty()) {
      resultArea.appendText("\n文件已保存至：\n" + savePath + "\n");
      }
      finishTask();
      });
      }
      @Override
      protected void failed() {
      Platform.runLater(() -> {
      resultArea.appendText("\n转录失败：\n" + getException().getMessage() + "\n");
      getException().printStackTrace();
      finishTask();
      });
      }
      };
      new Thread(task).start();
      }
      private void finishTask() {
      progressBar.setVisible(false);
      startButton.setDisable(false);
      }
      // 与 WhisperTest.java 中相同的音频加载方法
      private float[] loadAudioSamples(String audioPathStr) throws IOException, UnsupportedAudioFileException {
      File audioFile = new File(audioPathStr);
      try (AudioInputStream audioStream = AudioSystem.getAudioInputStream(audioFile)) {
      AudioFormat baseFormat = audioStream.getFormat();
      AudioFormat targetFormat = new AudioFormat(
      AudioFormat.Encoding.PCM_FLOAT,
      16000.0f,
      32,
      1,
      4,
      16000.0f,
      baseFormat.isBigEndian()
      );
      try (AudioInputStream convertedStream = AudioSystem.getAudioInputStream(targetFormat, audioStream)) {
      byte[] bytes = convertedStream.readAllBytes();
      ByteBuffer buffer = ByteBuffer.wrap(bytes);
      buffer.order(baseFormat.isBigEndian() ? ByteOrder.BIG_ENDIAN : ByteOrder.LITTLE_ENDIAN);
      float[] samples = new float[bytes.length / 4];
      buffer.asFloatBuffer().get(samples);
      return samples;
      } catch (IllegalArgumentException e) {
      // 回退到 PCM_SIGNED 16-bit
      AudioFormat pcmFormat = new AudioFormat(
      AudioFormat.Encoding.PCM_SIGNED,
      16000.0f,
      16,
      1,
      2,
      16000.0f,
      baseFormat.isBigEndian()
      );
      try (AudioInputStream pcmStream = AudioSystem.getAudioInputStream(pcmFormat, audioStream)) {
      byte[] pcmBytes = pcmStream.readAllBytes();
      float[] samples = new float[pcmBytes.length / 2];
      ByteBuffer buffer = ByteBuffer.wrap(pcmBytes);
      buffer.order(pcmFormat.isBigEndian() ? ByteOrder.BIG_ENDIAN : ByteOrder.LITTLE_ENDIAN);
      for (int i = 0; i < samples.length; i++) {
      samples[i] = buffer.getShort() / 32768.0f;
      }
      return samples;
      }
      }
      }
      }
      private String formatTimestamp(long ms) {
      long hours = ms / 3600000;
      long minutes = (ms % 3600000) / 60000;
      long seconds = (ms % 60000) / 1000;
      long millis = ms % 1000;
      return String.format("%02d:%02d:%02d,%03d", hours, minutes, seconds, millis);
      }
      private String toSrt(String text, int segments, WhisperContext ctx) {
      StringBuilder srt = new StringBuilder();
      for (int i = 0; i < segments; i++) {
      long t0 = whisperJNI.fullGetSegmentTimestamp0(ctx, i);
      long t1 = whisperJNI.fullGetSegmentTimestamp1(ctx, i);
      String segmentText = whisperJNI.fullGetSegmentText(ctx, i).trim();
      srt.append(i + 1).append("\n");
      srt.append(formatTimestamp(t0)).append(" --> ").append(formatTimestamp(t1)).append("\n");
      srt.append(segmentText).append("\n\n");
      }
      return srt.toString();
      }
      private String toVtt(String text) {
      return "WEBVTT\n\n" + text.replaceAll("(\\d{2}:\\d{2}:\\d{2},\\d{3}) --> (\\d{2}:\\d{2}:\\d{2},\\d{3})", "$1 --> $2");
      }
      private void saveToFile(String path, String content) throws IOException {
      try (BufferedWriter writer = new BufferedWriter(new FileWriter(path))) {
      writer.write(content);
      }
      }
      private void showAlert(String title, String message) {
      Alert alert = new Alert(Alert.AlertType.ERROR);
      alert.setTitle(title);
      alert.setHeaderText(null);
      alert.setContentText(message);
      alert.showAndWait();
      }
      @Override
      public void resetForm() {
      }
      @Override
      public boolean validateForm() {
      return false;
      }
      }