private void startSpeechRecognition()
{
isFeeding = true;
stream = client.CreateStream();
var feedCount = 0;
var decodeRate = 100; // decode every 100 feeds
Task.Run(async() =>
{
while (isFeeding || !bufferQueue.IsEmpty)
{
if (!bufferQueue.IsEmpty && bufferQueue.TryDequeue(out short[] buffer))
{
client.FeedAudioContent(stream, buffer, Convert.ToUInt32(buffer.Length));
if (++feedCount % decodeRate == 0)
{
var transcription = client.IntermediateDecode(stream);
await Dispatcher.RunAsync(Windows.UI.Core.CoreDispatcherPriority.Normal, () =>
{
result.Text = transcription;
});
}
}
}
});
}
/// <summary>
/// Destroy a streaming state without decoding the computed logits.
/// This can be used if you no longer need the result of an ongoing streaming
/// inference and don't want to perform a costly decode operation.
/// </summary>
public unsafe void FreeStream(MozillaVoiceSttStream stream)
{
NativeImp.STT_FreeStream(stream.GetNativePointer());
stream.Dispose();
}
/// <summary>
/// Computes the intermediate decoding of an ongoing streaming inference, including metadata.
/// </summary>
/// <param name="stream">Instance of the stream to decode.</param>
/// <param name="aNumResults">Maximum number of candidate transcripts to return. Returned list might be smaller than this.</param>
/// <returns>The STT intermediate result.</returns>
public unsafe Metadata IntermediateDecodeWithMetadata(MozillaVoiceSttStream stream, uint aNumResults)
{
return(NativeImp.STT_IntermediateDecodeWithMetadata(stream.GetNativePointer(), aNumResults).PtrToMetadata());
}
/// <summary>
/// Computes the intermediate decoding of an ongoing streaming inference.
/// </summary>
/// <param name="stream">Instance of the stream to decode.</param>
/// <returns>The STT intermediate result.</returns>
public unsafe string IntermediateDecode(MozillaVoiceSttStream stream)
{
return(NativeImp.STT_IntermediateDecode(stream.GetNativePointer()).PtrToString());
}
/// <summary>
/// Closes the ongoing streaming inference, returns the STT result over the whole audio signal, including metadata.
/// </summary>
/// <param name="stream">Instance of the stream to finish.</param>
/// <param name="aNumResults">Maximum number of candidate transcripts to return. Returned list might be smaller than this.</param>
/// <returns>The extended metadata result.</returns>
public unsafe Metadata FinishStreamWithMetadata(MozillaVoiceSttStream stream, uint aNumResults)
{
return(NativeImp.STT_FinishStreamWithMetadata(stream.GetNativePointer(), aNumResults).PtrToMetadata());
}
/// <summary>
/// Closes the ongoing streaming inference, returns the STT result over the whole audio signal.
/// </summary>
/// <param name="stream">Instance of the stream to finish.</param>
/// <returns>The STT result.</returns>
public unsafe string FinishStream(MozillaVoiceSttStream stream)
{
return(NativeImp.STT_FinishStream(stream.GetNativePointer()).PtrToString());
}
/// <summary>
/// Feeds audio samples to an ongoing streaming inference.
/// </summary>
/// <param name="stream">Instance of the stream to feed the data.</param>
/// <param name="aBuffer">An array of 16-bit, mono raw audio samples at the appropriate sample rate (matching what the model was trained on).</param>
public unsafe void FeedAudioContent(MozillaVoiceSttStream stream, short[] aBuffer, uint aBufferSize)
{
NativeImp.STT_FeedAudioContent(stream.GetNativePointer(), aBuffer, aBufferSize);
}
