Don't know how to transcribe wav file from Google Cloud Storage for LongRunningRecognize conversion to text in C#?

Question

I'm able to convert audio files to text as long as they are under a minute. I need to transcribe longer files. Apparently, you have to have the file in Cloud Storage but I can't figure out if there is one command that does that or if I have to do it separately. What I'm using now is:

var credential = GoogleCredential.FromFile(GoogleCredentials);
var channel = new Grpc.Core.Channel(SpeechClient.DefaultEndpoint.ToString(), credential.ToChannelCredentials());
var speech = SpeechClient.Create(channel);

var response = speech.LongRunningRecognize(
    new RecognitionConfig()
        {
            Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
            LanguageCode = "en",
        },
        RecognitionAudio.FromFile(waveFile));

response = response.PollUntilCompleted();

I know I need to specify a file in Cloud Storage like:

RecognitionAudio.FromStorageUri("gs://ldn-speech/" + waveFile);

But I don't know how to get the file into the gs bucket. Do I have to do that in a separate step or as part of one of the Speech API's? I'm looking for someone to show me an example.

EDIT: I found that I needed to upload the file separately and could use the credential file I had already been using in the speech recognition process: So, all I needed was:

var credential = GoogleCredential.FromFile(GoogleCredentials);
var storage = StorageClient.Create(credential);
using (var f = File.OpenRead(fullFileName))
{
fileName = Path.GetFileName(fullFileName);
storage.UploadObject(bucketName, fileName, null);
}

Does this answer your question? [Uploading objects to google cloud storage buckets in c#](https://stackoverflow.com/questions/26196515/uploading-objects-to-google-cloud-storage-buckets-in-c-sharp) — Kolban, Nov 09 '19 at 20:17
So, that would imply that (1) It's completely separate from the speech recognition process, (2) that none of the credentials set up in preparation for the speech API can be used to upload, and (3) there is no way to do this easily upload files with the credentials already established for speech channels. Are all those correct statements? — Velocedge, Nov 09 '19 at 20:35
I put all that code in only to have the program kick up an error and say I only needed the credential file... which I already have for the speech stuff. So, all I had to do was and the code that I edited above: — Velocedge, Nov 09 '19 at 21:25

score 1 · Answer 1 · answered Nov 14 '19 at 13:06

There is also another method of going about in your case.

As stated in your edit you indeed needed to upload the file separately to your Cloud Storage bucket. If you are planning on transcribing long audio files (longer than 1 minute) to text you may consider using Asynchronous Speech recognition: https://cloud.google.com/speech-to-text/docs/async-recognize#speech-async-recognize-gcs-csharp

The code sample uses Cloud Storage bucket to store raw audio input for long-running transcription processes. It also requires that you have created and activated a service account.

Here’s an example:

static object AsyncRecognizeGcs(string storageUri)
{
    var speech = SpeechClient.Create();
    var longOperation = speech.LongRunningRecognize(new RecognitionConfig()
    {
        Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
        SampleRateHertz = 16000,
        LanguageCode = "en",
    }, RecognitionAudio.FromStorageUri(storageUri));
    longOperation = longOperation.PollUntilCompleted();
    var response = longOperation.Result;
    foreach (var result in response.Results)
    {
        foreach (var alternative in result.Alternatives)
        {
            Console.WriteLine($"Transcript: { alternative.Transcript}");
        }
    }
    return 0;
}

score 0 · Answer 2 · answered Nov 17 '19 at 11:04

(1) I found that I did indeed need to upload the file separately to cloud storate. (2) could use the credential file I had already been using in the speech recognition process: So, all I needed was:

var credential = GoogleCredential.FromFile(GoogleCredentials);
var storage = StorageClient.Create(credential);
using (var f = File.OpenRead(fullFileName))
{
  fileName = Path.GetFileName(fullFileName);
  storage.UploadObject(bucketName, fileName, null);
}

Once in Cloud storage, I could transcribe it as I originally thought. Then delete the file after the process was complete with:

var credential = GoogleCredentials;
var storage = StorageClient.Create(credential);
using (var f = File.OpenRead(fullFileName))
{
  fileName = Path.GetFileName(fullFileName);
  storage.DeleteObject(bucketName, fileName);
}

Don't know how to transcribe wav file from Google Cloud Storage for LongRunningRecognize conversion to text in C#?

2 Answers2