google-cloud-platform - 谷歌云平台 : Speech to Text Conversion of Large Media Files

Question

我正在尝试从从 youtube 下载的 mp4 媒体文件中提取文本。由于我正在使用谷歌云平台，所以想尝试一下谷歌云语音。

在所有安装和配置之后，我复制了以下代码片段以开始使用:

with io.open(file_name, 'rb') as audio_file:
    content = audio_file.read()
    audio = types.RecognitionAudio(content=content)

config = types.RecognitionConfig(encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16, sample_rate_hertz=16000, language_code='en-US')   

response = client.long_running_recognize(config, audio)

但是我收到以下关于文件大小的错误:

InvalidArgument: 400 Inline audio exceeds duration limit. Please use a GCS URI.

然后我读到我应该对大型媒体文件使用流。所以，我尝试了以下代码片段:

with io.open(file_name, 'rb') as audio_file:
    content = audio_file.read()

#In practice, stream should be a generator yielding chunks of audio data.

stream = [content]
requests = (types.StreamingRecognizeRequest(audio_content=chunk)for chunk in stream)

config = types.RecognitionConfig(encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,sample_rate_hertz=16000,language_code='en-US')

streaming_config = types.StreamingRecognitionConfig(config=config)

responses = client.streaming_recognize(streaming_config, requests)

但我仍然收到以下错误:

InvalidArgument: 400 Invalid audio content: too long.

因此，任何人都可以提出一种转录 mp4 文件和提取文本的方法。我对非常大的媒体文件没有任何复杂的要求。媒体文件最长可达 10-15 分钟。谢谢

Answer 1

该错误消息表示文件太大，您需要先将媒体文件复制到 Google Cloud Storage，然后指定 Cloud Storage URI，例如 gs://bucket/path/mediafile。

使用 Cloud Storage URI 的关键是:

RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

以下代码将向您展示如何为输入指定 GCS URI。 Google 有一个 complete example在github上。

  public static void syncRecognizeGcs(String gcsUri) throws Exception {
    // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
    try (SpeechClient speech = SpeechClient.create()) {
      // Builds the request for remote FLAC file
      RecognitionConfig config =
          RecognitionConfig.newBuilder()
              .setEncoding(AudioEncoding.FLAC)
              .setLanguageCode("en-US")
              .setSampleRateHertz(16000)
              .build();
      RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

      // Use blocking call for getting audio transcript
      RecognizeResponse response = speech.recognize(config, audio);
      List<SpeechRecognitionResult> results = response.getResultsList();

      for (SpeechRecognitionResult result : results) {
        // There can be several alternative transcripts for a given chunk of speech. Just use the
        // first (most likely) one here.
        SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);
        System.out.printf("Transcription: %s%n", alternative.getTranscript());
      }
    }
  }