whisper.rn 0.3.0-rc.5 → 0.3.0-rc.6

package/README.md

@@ -8,9 +8,12 @@ React Native binding of [whisper.cpp](https://github.com/ggerganov/whisper.cpp).
 
 [whisper.cpp](https://github.com/ggerganov/whisper.cpp): High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisper) automatic speech recognition (ASR) model
 
-<img src="https://user-images.githubusercontent.com/3001525/225511664-8b2ba3ec-864d-4f55-bcb0-447aef168a32.jpeg" width="500" />
+## Screenshots
 
-> Run example with release mode on iPhone 13 Pro Max
+| <img src="https://github.com/mybigday/whisper.rn/assets/3001525/2fea7b2d-c911-44fb-9afc-8efc7b594446" width="300" /> | <img src="https://github.com/mybigday/whisper.rn/assets/3001525/a5005a6c-44f7-4db9-95e8-0fd951a2e147" width="300" /> |
+| :------------------------------------------: | :------------------------------------------: |
+| iOS: Tested on iPhone 13 Pro Max | Android: Tested on Pixel 6 |
+| (tiny.en, Core ML enabled) | (tiny.en, armv8.2-a+fp16) |
 
 ## Installation
 
@@ -48,7 +51,6 @@ import { initWhisper } from 'whisper.rn'
 
 const whisperContext = await initWhisper({
   filePath: 'file://.../ggml-tiny.en.bin',
-  isBundleAsset: false, // Set to true if you want to load the model from bundle resources, the filePath will be like `ggml-tiny.en.bin`
 })
 
 const sampleFilePath = 'file://.../sample.wav'
@@ -81,6 +83,44 @@ In Android, you may need to request the microphone permission by [`PermissionAnd
 
 Please visit the [Documentation](docs/) for more details.
 
+## Usage with assets
+
+You can also use the model file / audio file from assets:
+
+```js
+import { initWhisper } from 'whisper.rn'
+
+const whisperContext = await initWhisper({
+  filePath: require('../assets/ggml-tiny.en.bin'),
+})
+
+const { stop, promise } =
+  whisperContext.transcribe(require('../assets/sample.wav'), options)
+
+// ...
+```
+
+This requires editing the `metro.config.js` to support assets:
+
+```js
+// ...
+const defaultAssetExts = require('metro-config/src/defaults/defaults').assetExts
+
+module.exports = {
+  // ...
+  resolver: {
+    // ...
+    assetExts: [
+      ...defaultAssetExts,
+      'bin', // whisper.rn: ggml model binary
+      'mil', // whisper.rn: CoreML model asset
+    ]
+  },
+}
+```
+
+Please note that it will significantly increase the size of the app in release mode.
+
 ## Core ML support
 
 __*Platform: iOS 15.0+, tvOS 15.0+*__
@@ -91,25 +131,44 @@ The `.mlmodelc` model files is load depend on the ggml model file path. For exam
 
 Currently there is no official way to get the Core ML models by URL, you will need to convert Core ML models by yourself. Please see [Core ML Support](https://github.com/ggerganov/whisper.cpp#core-ml-support) of whisper.cpp for more details.
 
-During the `.mlmodelc` is a directory, you will need to download 5 files:
+During the `.mlmodelc` is a directory, you will need to download 5 files (3 required):
 
 ```json5
 [
   'model.mil',
-  'metadata.json',
   'coremldata.bin',
   'weights/weight.bin',
-  'analytics/coremldata.bin',
+  // Not required:
+  // 'metadata.json', 'analytics/coremldata.bin',
 ]
 ```
 
-Or just add them to your app's bundle resources, like the example app does, but this would increase the app size significantly.
+Or just use `require` to bundle that in your app, like the example app does, but this would increase the app size significantly.
+
+```js
+const whisperContext = await initWhisper({
+  filePath: require('../assets/ggml-tiny.en.bin')
+  coreMLModelAsset:
+    Platform.OS === 'ios'
+      ? {
+          filename: 'ggml-tiny.en-encoder.mlmodelc',
+          assets: [
+            require('../assets/ggml-tiny.en-encoder.mlmodelc/weights/weight.bin'),
+            require('../assets/ggml-tiny.en-encoder.mlmodelc/model.mil'),
+            require('../assets/ggml-tiny.en-encoder.mlmodelc/coremldata.bin'),
+          ],
+        }
+      : undefined,
+})
+```
+
+In real world, we recommended to split the asset imports into another platform specific file (e.g. `context-opts.ios.js`) to avoid these unused files in the bundle for Android.
 
 ## Run with example
 
-The example app is using [react-native-fs](https://github.com/itinance/react-native-fs) to download the model file and audio file.
+The example app provide a simple UI for testing the functions.
 
-Model: `base.en` in https://huggingface.co/datasets/ggerganov/whisper.cpp  
+Used Whisper model: `tiny.en` in https://huggingface.co/datasets/ggerganov/whisper.cpp  
 Sample file: `jfk.wav` in https://github.com/ggerganov/whisper.cpp/tree/master/samples
 
 For test better performance on transcribe, you can run the app in Release mode.
@@ -130,6 +189,10 @@ jest.mock('whisper.rn', () => require('whisper.rn/jest/mock'))
 
 See the [contributing guide](CONTRIBUTING.md) to learn how to contribute to the repository and the development workflow.
 
+## Troubleshooting
+
+See the [troubleshooting](TROUBLESHOOTING.md) if you encounter any problem while using `whisper.rn`.
+
 ## License
 
 MIT

package/android/src/main/java/com/rnwhisper/Downloader.java

@@ -0,0 +1,83 @@
+package com.rnwhisper;
+
+import android.content.Context;
+
+import java.io.BufferedInputStream;
+import java.io.FileOutputStream;
+import java.io.File;
+import java.io.InputStream;
+import java.io.OutputStream;
+import java.net.URL;
+import java.net.URLConnection;
+
+/**
+ * NOTE: This is simple downloader,
+ * the main purpose is supported load assets on RN Debug mode,
+ * so it's a very crude implementation.
+ * 
+ * If you want to use file download in production to load model / audio files,
+ * I would recommend using react-native-fs or expo-file-system to manage the files.
+ */
+public class Downloader {
+  private static Context context;
+
+  public Downloader(Context context) {
+    this.context = context;
+  }
+
+  private String getDir() {
+    String dir = context.getCacheDir().getAbsolutePath() + "/rnwhisper_debug_assets/";
+    File file = new File(dir);
+    if (!file.exists()) {
+      file.mkdirs();
+    }
+    return dir;
+  }
+
+  private boolean fileExists(String filename) {
+    File file = new File(getDir() + filename);
+    return file.exists();
+  }
+
+  public String downloadFile(String urlPath) throws Exception {
+    String filename = urlPath.substring(urlPath.lastIndexOf('/') + 1);
+    if (filename.contains("?")) {
+      filename = filename.substring(0, filename.indexOf("?"));
+    }
+    String filepath = getDir() + filename;
+    if (fileExists(filename)) {
+      return filepath;
+    }
+    try {
+      URL url = new URL(urlPath);
+      URLConnection connection = url.openConnection();
+      connection.connect();
+      InputStream input = new BufferedInputStream(url.openStream());
+      OutputStream output = new FileOutputStream(filepath);
+      byte data[] = new byte[1024];
+      int count;
+      while ((count = input.read(data)) != -1) {
+        output.write(data, 0, count);
+      }
+      output.flush();
+      output.close();
+      input.close();
+    } catch (Exception e) {
+      throw e;
+    }
+    return filepath;
+  }
+
+  private void deleteFile(File fileOrDir) {
+    if (fileOrDir.isDirectory()) {
+      for (File child : fileOrDir.listFiles()) {
+        deleteFile(child);
+      }
+    }
+    fileOrDir.delete();
+  }
+
+  public void clearCache() {
+    deleteFile(new File(getDir()));
+  }
+}

package/android/src/main/java/com/rnwhisper/WhisperContext.java

@@ -26,6 +26,7 @@ import java.io.File;
 import java.io.FileInputStream;
 import java.io.IOException;
 import java.io.InputStream;
+import java.io.PushbackInputStream;
 import java.nio.ByteBuffer;
 import java.nio.ByteOrder;
 import java.nio.ShortBuffer;
@@ -281,10 +282,10 @@ public class WhisperContext {
     eventEmitter.emit(eventName, event);
   }
 
-  public WritableMap transcribeFile(int jobId, String filePath, ReadableMap options) throws IOException, Exception {
+  public WritableMap transcribeInputStream(int jobId, InputStream inputStream, ReadableMap options) throws IOException, Exception {
     this.jobId = jobId;
     isTranscribing = true;
-    float[] audioData = decodeWaveFile(new File(filePath));
+    float[] audioData = decodeWaveFile(inputStream);
     int code = full(jobId, options, audioData, audioData.length);
     isTranscribing = false;
     this.jobId = -1;
@@ -383,14 +384,12 @@ public class WhisperContext {
     freeContext(context);
   }
 
-  public static float[] decodeWaveFile(File file) throws IOException {
+  public static float[] decodeWaveFile(InputStream inputStream) throws IOException {
     ByteArrayOutputStream baos = new ByteArrayOutputStream();
-    try (InputStream inputStream = new FileInputStream(file)) {
-      byte[] buffer = new byte[1024];
-      int bytesRead;
-      while ((bytesRead = inputStream.read(buffer)) != -1) {
-        baos.write(buffer, 0, bytesRead);
-      }
+    byte[] buffer = new byte[1024];
+    int bytesRead;
+    while ((bytesRead = inputStream.read(buffer)) != -1) {
+      baos.write(buffer, 0, bytesRead);
     }
     ByteBuffer byteBuffer = ByteBuffer.wrap(baos.toByteArray());
     byteBuffer.order(ByteOrder.LITTLE_ENDIAN);
@@ -472,6 +471,7 @@ public class WhisperContext {
 
   protected static native long initContext(String modelPath);
   protected static native long initContextWithAsset(AssetManager assetManager, String modelPath);
+  protected static native long initContextWithInputStream(PushbackInputStream inputStream);
   protected static native int fullTranscribe(
     int job_id,
     long context,

package/android/src/main/jni/whisper/jni.cpp

@@ -20,6 +20,97 @@ static inline int min(int a, int b) {
     return (a < b) ? a : b;
 }
 
+// Load model from input stream (used for drawable / raw resources)
+struct input_stream_context {
+    JNIEnv *env;
+    jobject input_stream;
+};
+
+static size_t input_stream_read(void *ctx, void *output, size_t read_size) {
+    input_stream_context *context = (input_stream_context *)ctx;
+    JNIEnv *env = context->env;
+    jobject input_stream = context->input_stream;
+    jclass input_stream_class = env->GetObjectClass(input_stream);
+
+    jbyteArray buffer = env->NewByteArray(read_size);
+    jint bytes_read = env->CallIntMethod(
+        input_stream,
+        env->GetMethodID(input_stream_class, "read", "([B)I"),
+        buffer
+    );
+
+    if (bytes_read > 0) {
+        env->GetByteArrayRegion(buffer, 0, bytes_read, (jbyte *) output);
+    }
+
+    env->DeleteLocalRef(buffer);
+
+    return bytes_read;
+}
+
+static bool input_stream_is_eof(void *ctx) {
+    input_stream_context *context = (input_stream_context *)ctx;
+    JNIEnv *env = context->env;
+    jobject input_stream = context->input_stream;
+
+    jclass input_stream_class = env->GetObjectClass(input_stream);
+
+    jbyteArray buffer = env->NewByteArray(1);
+    jint bytes_read = env->CallIntMethod(
+        input_stream,
+        env->GetMethodID(input_stream_class, "read", "([B)I"),
+        buffer
+    );
+
+    bool is_eof = (bytes_read == -1);
+    if (!is_eof) {
+        // If we successfully read a byte, "unread" it by pushing it back into the stream.
+        env->CallVoidMethod(
+            input_stream,
+            env->GetMethodID(input_stream_class, "unread", "([BII)V"),
+            buffer,
+            0,
+            1
+        );
+    }
+
+    env->DeleteLocalRef(buffer);
+
+    return is_eof;
+}
+
+static void input_stream_close(void *ctx) {
+    input_stream_context *context = (input_stream_context *)ctx;
+    JNIEnv *env = context->env;
+    jobject input_stream = context->input_stream;
+    jclass input_stream_class = env->GetObjectClass(input_stream);
+    
+    env->CallVoidMethod(
+        input_stream,
+        env->GetMethodID(input_stream_class, "close", "()V")
+    );
+
+    env->DeleteGlobalRef(input_stream);
+}
+
+static struct whisper_context *whisper_init_from_input_stream(
+    JNIEnv *env,
+    jobject input_stream // PushbackInputStream
+) {
+    input_stream_context *context = new input_stream_context;
+    context->env = env;
+    context->input_stream = env->NewGlobalRef(input_stream);
+
+    whisper_model_loader loader = {
+        .context = context,
+        .read = &input_stream_read,
+        .eof = &input_stream_is_eof,
+        .close = &input_stream_close
+    };
+    return whisper_init(&loader);
+}
+
+// Load model from asset
 static size_t asset_read(void *ctx, void *output, size_t read_size) {
     return AAsset_read((AAsset *) ctx, output, read_size);
 }
@@ -81,6 +172,17 @@ Java_com_rnwhisper_WhisperContext_initContextWithAsset(
     return reinterpret_cast<jlong>(context);
 }
 
+JNIEXPORT jlong JNICALL
+Java_com_rnwhisper_WhisperContext_initContextWithInputStream(
+    JNIEnv *env,
+    jobject thiz,
+    jobject input_stream
+) {
+    UNUSED(thiz);
+    struct whisper_context *context = nullptr;
+    context = whisper_init_from_input_stream(env, input_stream);
+    return reinterpret_cast<jlong>(context);
+}
 
 JNIEXPORT jint JNICALL
 Java_com_rnwhisper_WhisperContext_fullTranscribe(

package/android/src/newarch/java/com/rnwhisper/RNWhisperModule.java

@@ -17,17 +17,22 @@ import com.facebook.react.module.annotations.ReactModule;
 
 import java.util.HashMap;
 import java.util.Random;
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.PushbackInputStream;
 
 @ReactModule(name = RNWhisperModule.NAME)
 public class RNWhisperModule extends NativeRNWhisperSpec implements LifecycleEventListener {
   public static final String NAME = "RNWhisper";
 
   private ReactApplicationContext reactContext;
+  private Downloader downloader;
 
   public RNWhisperModule(ReactApplicationContext reactContext) {
     super(reactContext);
     reactContext.addLifecycleEventListener(this);
     this.reactContext = reactContext;
+    this.downloader = new Downloader(reactContext);
   }
 
   @Override
@@ -49,19 +54,48 @@ public class RNWhisperModule extends NativeRNWhisperSpec implements LifecycleEve
 
   private HashMap<Integer, WhisperContext> contexts = new HashMap<>();
 
+  private int getResourceIdentifier(String filePath) {
+    int identifier = reactContext.getResources().getIdentifier(
+      filePath,
+      "drawable",
+      reactContext.getPackageName()
+    );
+    if (identifier == 0) {
+      identifier = reactContext.getResources().getIdentifier(
+        filePath,
+        "raw",
+        reactContext.getPackageName()
+      );
+    }
+    return identifier;
+  }
+
   @ReactMethod
-  public void initContext(final String modelPath, final boolean isBundleAsset, final Promise promise) {
+  public void initContext(final ReadableMap options, final Promise promise) {
     new AsyncTask<Void, Void, Integer>() {
       private Exception exception;
 
       @Override
       protected Integer doInBackground(Void... voids) {
         try {
+          String modelPath = options.getString("filePath");
+          boolean isBundleAsset = options.getBoolean("isBundleAsset");
+
+          String modelFilePath = modelPath;
+          if (!isBundleAsset && (modelPath.startsWith("http://") || modelPath.startsWith("https://"))) {
+            modelFilePath = downloader.downloadFile(modelPath);
+          }
+
           long context;
-          if (isBundleAsset) {
-            context = WhisperContext.initContextWithAsset(reactContext.getAssets(), modelPath);
+          int resId = getResourceIdentifier(modelFilePath);
+          if (resId > 0) {
+            context = WhisperContext.initContextWithInputStream(
+              new PushbackInputStream(reactContext.getResources().openRawResource(resId))
+            );
+          } else if (isBundleAsset) {
+            context = WhisperContext.initContextWithAsset(reactContext.getAssets(), modelFilePath);
           } else {
-            context = WhisperContext.initContext(modelPath);
+            context = WhisperContext.initContext(modelFilePath);
           }
           if (context == 0) {
             throw new Exception("Failed to initialize context");
@@ -108,7 +142,26 @@ public class RNWhisperModule extends NativeRNWhisperSpec implements LifecycleEve
       @Override
       protected WritableMap doInBackground(Void... voids) {
         try {
-          return context.transcribeFile((int) jobId, filePath, options);
+          String waveFilePath = filePath;
+
+          if (filePath.startsWith("http://") || filePath.startsWith("https://")) {
+            waveFilePath = downloader.downloadFile(filePath);
+          }
+
+          int resId = getResourceIdentifier(waveFilePath);
+          if (resId > 0) {
+            return context.transcribeInputStream(
+              (int) jobId,
+              reactContext.getResources().openRawResource(resId),
+              options
+            );
+          }
+
+          return context.transcribeInputStream(
+            (int) jobId,
+            new FileInputStream(new File(waveFilePath)),
+            options
+          );
         } catch (Exception e) {
           exception = e;
           return null;
@@ -228,5 +281,6 @@ public class RNWhisperModule extends NativeRNWhisperSpec implements LifecycleEve
       context.release();
     }
     contexts.clear();
+    downloader.clearCache();
   }
 }

package/android/src/oldarch/java/com/rnwhisper/RNWhisperModule.java

@@ -18,17 +18,22 @@ import com.facebook.react.module.annotations.ReactModule;
 
 import java.util.HashMap;
 import java.util.Random;
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.PushbackInputStream;
 
 @ReactModule(name = RNWhisperModule.NAME)
 public class RNWhisperModule extends ReactContextBaseJavaModule implements LifecycleEventListener {
   public static final String NAME = "RNWhisper";
 
   private ReactApplicationContext reactContext;
+  private Downloader downloader;
 
   public RNWhisperModule(ReactApplicationContext reactContext) {
     super(reactContext);
     reactContext.addLifecycleEventListener(this);
     this.reactContext = reactContext;
+    this.downloader = new Downloader(reactContext);
   }
 
   @Override
@@ -39,19 +44,48 @@ public class RNWhisperModule extends ReactContextBaseJavaModule implements Lifec
 
   private HashMap<Integer, WhisperContext> contexts = new HashMap<>();
 
+  private int getResourceIdentifier(String filePath) {
+    int identifier = reactContext.getResources().getIdentifier(
+      filePath,
+      "drawable",
+      reactContext.getPackageName()
+    );
+    if (identifier == 0) {
+      identifier = reactContext.getResources().getIdentifier(
+        filePath,
+        "raw",
+        reactContext.getPackageName()
+      );
+    }
+    return identifier;
+  }
+
   @ReactMethod
-  public void initContext(final String modelPath, final boolean isBundleAsset, final Promise promise) {
+  public void initContext(final ReadableMap options, final Promise promise) {
     new AsyncTask<Void, Void, Integer>() {
       private Exception exception;
 
       @Override
       protected Integer doInBackground(Void... voids) {
         try {
+          String modelPath = options.getString("filePath");
+          boolean isBundleAsset = options.getBoolean("isBundleAsset");
+
+          String modelFilePath = modelPath;
+          if (!isBundleAsset && (modelPath.startsWith("http://") || modelPath.startsWith("https://"))) {
+            modelFilePath = downloader.downloadFile(modelPath);
+          }
+
           long context;
-          if (isBundleAsset) {
-            context = WhisperContext.initContextWithAsset(reactContext.getAssets(), modelPath);
+          int resId = getResourceIdentifier(modelFilePath);
+          if (resId > 0) {
+            context = WhisperContext.initContextWithInputStream(
+              new PushbackInputStream(reactContext.getResources().openRawResource(resId))
+            );
+          } else if (isBundleAsset) {
+            context = WhisperContext.initContextWithAsset(reactContext.getAssets(), modelFilePath);
           } else {
-            context = WhisperContext.initContext(modelPath);
+            context = WhisperContext.initContext(modelFilePath);
           }
           if (context == 0) {
             throw new Exception("Failed to initialize context");
@@ -98,7 +132,26 @@ public class RNWhisperModule extends ReactContextBaseJavaModule implements Lifec
       @Override
       protected WritableMap doInBackground(Void... voids) {
         try {
-          return context.transcribeFile(jobId, filePath, options);
+          String waveFilePath = filePath;
+
+          if (filePath.startsWith("http://") || filePath.startsWith("https://")) {
+            waveFilePath = downloader.downloadFile(filePath);
+          }
+
+          int resId = getResourceIdentifier(waveFilePath);
+          if (resId > 0) {
+            return context.transcribeInputStream(
+              (int) jobId,
+              reactContext.getResources().openRawResource(resId),
+              options
+            );
+          }
+
+          return context.transcribeInputStream(
+            (int) jobId,
+            new FileInputStream(new File(waveFilePath)),
+            options
+          );
         } catch (Exception e) {
           exception = e;
           return null;
@@ -217,5 +270,6 @@ public class RNWhisperModule extends ReactContextBaseJavaModule implements Lifec
       context.release();
     }
     contexts.clear();
+    downloader.clearCache();
   }
 }

package/ios/RNWhisper.mm

@@ -1,5 +1,6 @@
 #import "RNWhisper.h"
 #import "RNWhisperContext.h"
+#import "RNWhisperDownloader.h"
 #include <stdlib.h>
 #include <string>
 
@@ -15,7 +16,7 @@ RCT_EXPORT_MODULE()
 
 + (BOOL)requiresMainQueueSetup
 {
-  return YES;
+  return NO;
 }
 
 - (NSDictionary *)constantsToExport
@@ -35,8 +36,7 @@ RCT_EXPORT_MODULE()
 }
 
 RCT_REMAP_METHOD(initContext,
-                 withPath:(NSString *)modelPath
-                 withBundleResource:(BOOL)isBundleAsset
+                 withOptions:(NSDictionary *)modelOptions
                  withResolver:(RCTPromiseResolveBlock)resolve
                  withRejecter:(RCTPromiseRejectBlock)reject)
 {
@@ -44,7 +44,26 @@ RCT_REMAP_METHOD(initContext,
         contexts = [[NSMutableDictionary alloc] init];
     }
 
+    NSString *modelPath = [modelOptions objectForKey:@"filePath"];
+    BOOL isBundleAsset = [[modelOptions objectForKey:@"isBundleAsset"] boolValue];
+
+    // For support debug assets in development mode
+    BOOL downloadCoreMLAssets = [[modelOptions objectForKey:@"downloadCoreMLAssets"] boolValue];
+    if (downloadCoreMLAssets) {
+        NSArray *coreMLAssets = [modelOptions objectForKey:@"coreMLAssets"];
+        // Download coreMLAssets ([{ uri, filepath }])
+        for (NSDictionary *coreMLAsset in coreMLAssets) {
+            NSString *path = coreMLAsset[@"uri"];
+            if ([path hasPrefix:@"http://"] || [path hasPrefix:@"https://"]) {
+                [RNWhisperDownloader downloadFile:path toFile:coreMLAsset[@"filepath"]];
+            }
+        }
+    }
+
     NSString *path = modelPath;
+    if ([path hasPrefix:@"http://"] || [path hasPrefix:@"https://"]) {
+        path = [RNWhisperDownloader downloadFile:path toFile:nil];
+    }
     if (isBundleAsset) {
         path = [[NSBundle mainBundle] pathForResource:modelPath ofType:nil];
     }
@@ -84,10 +103,13 @@ RCT_REMAP_METHOD(transcribeFile,
         return;
     }
 
-    NSURL *url = [NSURL fileURLWithPath:waveFilePath];
+    NSString *path = waveFilePath;
+    if ([path hasPrefix:@"http://"] || [path hasPrefix:@"https://"]) {
+        path = [RNWhisperDownloader downloadFile:path toFile:nil];
+    }
 
     int count = 0;
-    float *waveFile = [self decodeWaveFile:url count:&count];
+    float *waveFile = [self decodeWaveFile:path count:&count];
     if (waveFile == nil) {
         reject(@"whisper_error", @"Invalid file", nil);
         return;
@@ -185,8 +207,9 @@ RCT_REMAP_METHOD(releaseAllContexts,
     resolve(nil);
 }
 
-- (float *)decodeWaveFile:(NSURL*)fileURL count:(int *)count {
-    NSData *fileData = [NSData dataWithContentsOfURL:fileURL];
+- (float *)decodeWaveFile:(NSString*)filePath count:(int *)count {
+    NSURL *url = [NSURL fileURLWithPath:filePath];
+    NSData *fileData = [NSData dataWithContentsOfURL:url];
     if (fileData == nil) {
         return nil;
     }
@@ -219,6 +242,8 @@ RCT_REMAP_METHOD(releaseAllContexts,
 
     [contexts removeAllObjects];
     contexts = nil;
+
+    [RNWhisperDownloader clearCache];
 }
 
 #ifdef RCT_NEW_ARCH_ENABLED