1

我有一个使用expo-av库捕获音频的 React Native (Expo) 应用程序。

然后它将音频文件上传到 Amazon S3，然后在 Amazon Transcribe 中转录。

对于 Android，我将音频保存为“.m4a”文件，并将 Amazon Transcribe API 调用为：

transcribe_client.start_transcription_job(TranscriptionJobName = job_name,
                                          Media={'MediaFileUri' : file_uri},
                                          MediaFormat='mp4',
                                          LanguageCode='en-US')

从 iOS 设备上传的“MediaFormat”应该是什么，通常是“.caf”文件？

Amazon Transcribe 仅允许这些媒体格式

 MP3, MP4, WAV, FLAC, AMR, OGG, and WebM
4

1 回答 1

2

可能的解决方案：

  1. 创建一个 API 来为您完成转换。
    您可以使用例如FFMPEG python 库轻松创建一个。

  2. 使用已经制作的 API。
    通过使用cloudconvert API，您可以轻松地转换文件，但前提是您需要付费。

  3. 使用不同的库来录制 IOS 音频。
    有一个名为react-native-record-audio-ios的模块，它完全是为 IOS 制作的，可以在.caf、.m4a和.wav.

  4. 使用LAME api进行转换。如此处
    所述，您可以通过创建一个可以运行此的本机模块将文件转换为一个文件：.caf.mp3

FILE *pcm = fopen("file.caf", "rb");
FILE *mp3 = fopen("file.mp3", "wb");
const int PCM_SIZE = 8192;
const int MP3_SIZE = 8192;

short int pcm_buffer[PCM_SIZE*2];
unsigned char mp3_buffer[MP3_SIZE];

lame_t lame = lame_init();
lame_set_in_samplerate(lame, 44100);
lame_set_VBR(lame, vbr_default);
lame_init_params(lame);

do {
  read = fread(pcm_buffer, 2*sizeof(short int), PCM_SIZE, pcm);
  if (read == 0)
    write = lame_encode_flush(lame, mp3_buffer, MP3_SIZE);
  else
    write = lame_encode_buffer_interleaved(lame, pcm_buffer, read, mp3_buffer, MP3_SIZE);
  fwrite(mp3_buffer, write, 1, mp3);
} while (read != 0);

lame_close(lame);
fclose(mp3);
fclose(pcm);
  1. 创建运行此 objective-c代码的本机模块：
-(void) convertToWav
{
// set up an AVAssetReader to read from the iPod Library

NSString *cafFilePath=[[NSBundle mainBundle]pathForResource:@"test" ofType:@"caf"];

NSURL *assetURL = [NSURL fileURLWithPath:cafFilePath];
AVURLAsset *songAsset = [AVURLAsset URLAssetWithURL:assetURL options:nil];

NSError *assetError = nil;
AVAssetReader *assetReader = [AVAssetReader assetReaderWithAsset:songAsset
                                                           error:&assetError]
;
if (assetError) {
    NSLog (@"error: %@", assetError);
    return;
}

AVAssetReaderOutput *assetReaderOutput = [AVAssetReaderAudioMixOutput
                                          assetReaderAudioMixOutputWithAudioTracks:songAsset.tracks
                                          audioSettings: nil];
if (! [assetReader canAddOutput: assetReaderOutput]) {
    NSLog (@"can't add reader output... die!");
    return;
}
[assetReader addOutput: assetReaderOutput];

NSString *title = @"MyRec";
NSArray *docDirs = NSSearchPathForDirectoriesInDomains (NSDocumentDirectory, NSUserDomainMask, YES);
NSString *docDir = [docDirs objectAtIndex: 0];
NSString *wavFilePath = [[docDir stringByAppendingPathComponent :title]
                         stringByAppendingPathExtension:@"wav"];
if ([[NSFileManager defaultManager] fileExistsAtPath:wavFilePath])
{
    [[NSFileManager defaultManager] removeItemAtPath:wavFilePath error:nil];
}
NSURL *exportURL = [NSURL fileURLWithPath:wavFilePath];
AVAssetWriter *assetWriter = [AVAssetWriter assetWriterWithURL:exportURL
                                                      fileType:AVFileTypeWAVE
                                                         error:&assetError];
if (assetError)
{
    NSLog (@"error: %@", assetError);
    return;
}

AudioChannelLayout channelLayout;
memset(&channelLayout, 0, sizeof(AudioChannelLayout));
channelLayout.mChannelLayoutTag = kAudioChannelLayoutTag_Stereo;
NSDictionary *outputSettings = [NSDictionary dictionaryWithObjectsAndKeys:
                                [NSNumber numberWithInt:kAudioFormatLinearPCM], AVFormatIDKey,
                                [NSNumber numberWithFloat:44100.0], AVSampleRateKey,
                                [NSNumber numberWithInt:2], AVNumberOfChannelsKey,
                                [NSData dataWithBytes:&channelLayout length:sizeof(AudioChannelLayout)], AVChannelLayoutKey,
                                [NSNumber numberWithInt:16], AVLinearPCMBitDepthKey,
                                [NSNumber numberWithBool:NO], AVLinearPCMIsNonInterleaved,
                                [NSNumber numberWithBool:NO],AVLinearPCMIsFloatKey,
                                [NSNumber numberWithBool:NO], AVLinearPCMIsBigEndianKey,
                                nil];
AVAssetWriterInput *assetWriterInput = [AVAssetWriterInput assetWriterInputWithMediaType:AVMediaTypeAudio
                                                                          outputSettings:outputSettings];
if ([assetWriter canAddInput:assetWriterInput])
{
    [assetWriter addInput:assetWriterInput];
}
else
{
    NSLog (@"can't add asset writer input... die!");
    return;
}

assetWriterInput.expectsMediaDataInRealTime = NO;

[assetWriter startWriting];
[assetReader startReading];

AVAssetTrack *soundTrack = [songAsset.tracks objectAtIndex:0];
CMTime startTime = CMTimeMake (0, soundTrack.naturalTimeScale);
[assetWriter startSessionAtSourceTime: startTime];

__block UInt64 convertedByteCount = 0;
dispatch_queue_t mediaInputQueue = dispatch_queue_create("mediaInputQueue", NULL);

[assetWriterInput requestMediaDataWhenReadyOnQueue:mediaInputQueue
                                        usingBlock: ^
 {

     while (assetWriterInput.readyForMoreMediaData)
     {
         CMSampleBufferRef nextBuffer = [assetReaderOutput copyNextSampleBuffer];
         if (nextBuffer)
         {
             // append buffer
             [assetWriterInput appendSampleBuffer: nextBuffer];
             convertedByteCount += CMSampleBufferGetTotalSampleSize (nextBuffer);
             CMTime progressTime = CMSampleBufferGetPresentationTimeStamp(nextBuffer);

             CMTime sampleDuration = CMSampleBufferGetDuration(nextBuffer);
             if (CMTIME_IS_NUMERIC(sampleDuration))
                 progressTime= CMTimeAdd(progressTime, sampleDuration);
             float dProgress= CMTimeGetSeconds(progressTime) / CMTimeGetSeconds(songAsset.duration);
             NSLog(@"%f",dProgress);
         }
         else
         {

             [assetWriterInput markAsFinished];
             //              [assetWriter finishWriting];
             [assetReader cancelReading];

         }
     }
 }];
}

但是，正如这里所说：

因为 iPhone 不应该真正用于处理器密集型的事情，例如音频转换。

所以我向你推荐第三种解决方案，因为它更容易，而且看起来不像 Iphone 处理器的密集任务。

于 2021-01-20T18:46:34.203 回答