/// <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 DiscardStream()
{
NativeImp.DS_DiscardStream(ref _streamingStatePP);
}
/// <summary>
/// Use the DeepSpeech model to perform Speech-To-Text.
/// </summary>
/// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate.</param>
/// <param name="aBufferSize">The number of samples in the audio signal.</param>
/// <param name="aSampleRate">The sample-rate of the audio signal.</param>
/// <returns>The extended metadata. The user is responsible for freeing the struct. Returns NULL on error.</returns>
public unsafe Models.Metadata SpeechToTextWithMetadata(short[] aBuffer, uint aBufferSize, uint aSampleRate)
{
return(NativeImp.DS_SpeechToTextWithMetadata(_modelStatePP, aBuffer, aBufferSize, aSampleRate).PtrToMetadata());
}
/// <summary>
/// Closes the ongoing streaming inference, returns the STT result over the whole audio signal.
/// </summary>
/// <returns>The extended metadata. The user is responsible for freeing the struct.</returns>
public unsafe Models.Metadata FinishStreamWithMetadata()
{
return(NativeImp.DS_FinishStreamWithMetadata(_streamingStatePP).PtrToMetadata());
}
/// <summary>
/// Prints the versions of Tensorflow and DeepSpeech.
/// </summary>
public unsafe void PrintVersions()
{
NativeImp.DS_PrintVersions();
}
/// <summary>
/// Set beam width value used by the model.
/// </summary>
/// <param name="aBeamWidth">The beam width used by the decoder. A larger beam width value generates better results at the cost of decoding time.</param>
/// <exception cref="ArgumentException">Thrown on failure.</exception>
public unsafe void SetModelBeamWidth(uint aBeamWidth)
{
var resultCode = NativeImp.DS_SetModelBeamWidth(_modelStatePP, aBeamWidth);
EvaluateResultCode(resultCode);
}
/// <summary>
/// Feeds audio samples to an ongoing streaming inference.
/// </summary>
/// <param name="aBuffer">An array of 16-bit, mono raw audio samples at the appropriate sample rate.</param>
public unsafe void FeedAudioContent(short[] aBuffer, uint aBufferSize)
{
NativeImp.DS_FeedAudioContent(_streamingStatePP, aBuffer, aBufferSize);
}
/// <summary>
/// Frees associated resources and destroys models objects.
/// </summary>
public unsafe void Dispose()
{
NativeImp.DS_FreeModel(_modelStatePP);
}
/// <summary>
/// Use the DeepSpeech model to perform Speech-To-Text, return results including metadata.
/// </summary>
/// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).</param>
/// <param name="aBufferSize">The number of samples in the audio signal.</param>
/// <param name="aNumResults">Maximum number of candidate transcripts to return. Returned list might be smaller than this.</param>
/// <returns>The extended metadata. Returns NULL on error.</returns>
public unsafe Metadata SpeechToTextWithMetadata(short[] aBuffer, uint aBufferSize, uint aNumResults)
{
return(NativeImp.DS_SpeechToTextWithMetadata(_modelStatePP, aBuffer, aBufferSize, aNumResults).PtrToMetadata());
}
/// <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()
{
NativeImp.DS_FreeStream(ref _streamingStatePP);
}
/// <summary>
/// Free a DeepSpeech allocated Metadata struct
/// </summary>
public unsafe void FreeMetadata(IntPtr intPtr)
{
NativeImp.DS_FreeMetadata(intPtr);
}
/// <summary>
/// Creates a new streaming inference state.
/// </summary>
/// <exception cref="ArgumentException">Thrown when the native binary failed to initialize the streaming mode.</exception>
public unsafe void CreateStream()
{
var resultCode = NativeImp.DS_CreateStream(_modelStatePP, ref _streamingStatePP);
EvaluateResultCode(resultCode);
}
/// <summary>
/// Frees associated resources and destroys models objects.
/// </summary>
public unsafe void Dispose()
{
NativeImp.DS_DestroyModel(_modelStatePP);
}
/// <summary>
/// Use the DeepSpeech model to perform Speech-To-Text.
/// </summary>
/// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate.</param>
/// <param name="aBufferSize">The number of samples in the audio signal.</param>
/// <param name="aSampleRate">The sample-rate of the audio signal.</param>
/// <returns>The STT result. The user is responsible for freeing the string. Returns NULL on error.</returns>
public unsafe string SpeechToText(short[] aBuffer, uint aBufferSize, uint aSampleRate)
{
return(NativeImp.DS_SpeechToText(_modelStatePP, aBuffer, aBufferSize, aSampleRate));
}
/// <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(DeepSpeechStream stream)
{
NativeImp.DS_FreeStream(stream.GetNativePointer());
stream.Dispose();
}
/// <summary>
/// Disable decoding using an external scorer.
/// </summary>
/// <exception cref="ArgumentException">Thrown when an external scorer is not enabled.</exception>
public unsafe void DisableExternalScorer()
{
var resultCode = NativeImp.DS_DisableExternalScorer(_modelStatePP);
EvaluateResultCode(resultCode);
}
/// <summary>
/// Use the DeepSpeech model to perform Speech-To-Text.
/// </summary>
/// <param name="aBuffer">A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).</param>
/// <param name="aBufferSize">The number of samples in the audio signal.</param>
/// <returns>The STT result. Returns NULL on error.</returns>
public unsafe string SpeechToText(short[] aBuffer, uint aBufferSize)
{
return(NativeImp.DS_SpeechToText(_modelStatePP, aBuffer, aBufferSize).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(DeepSpeechStream stream, short[] aBuffer, uint aBufferSize)
{
NativeImp.DS_FeedAudioContent(stream.GetNativePointer(), aBuffer, aBufferSize);
}
/// <summary>
/// Get beam width value used by the model. If SetModelBeamWidth was not
/// called before, will return the default value loaded from the model file.
/// </summary>
/// <returns>Beam width value used by the model.</returns>
public unsafe uint GetModelBeamWidth()
{
return(NativeImp.DS_GetModelBeamWidth(_modelStatePP));
}
/// <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(DeepSpeechStream stream)
{
return(NativeImp.DS_FinishStream(stream.GetNativePointer()).PtrToString());
}
/// <summary>
/// Return the sample rate expected by the model.
/// </summary>
/// <returns>Sample rate.</returns>
public unsafe int GetModelSampleRate()
{
return(NativeImp.DS_GetModelSampleRate(_modelStatePP));
}
/// <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(DeepSpeechStream stream, uint aNumResults)
{
return(NativeImp.DS_FinishStreamWithMetadata(stream.GetNativePointer(), aNumResults).PtrToMetadata());
}
/// <summary>
/// Closes the ongoing streaming inference, returns the STT result over the whole audio signal.
/// </summary>
/// <returns>The STT result. The user is responsible for freeing the string.</returns>
public unsafe string FinishStream()
{
return(NativeImp.DS_FinishStream(_streamingStatePP).PtrToString());
}
/// <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(DeepSpeechStream stream)
{
return(NativeImp.DS_IntermediateDecode(stream.GetNativePointer()).PtrToString());
}
/// <summary>
/// Computes the intermediate decoding of an ongoing streaming inference. This is an expensive process as the decoder implementation isn't
/// currently capable of streaming, so it always starts from the beginning of the audio.
/// </summary>
/// <returns>The STT intermediate result. The user is responsible for freeing the string.</returns>
public unsafe string IntermediateDecode()
{
return(NativeImp.DS_IntermediateDecode(_streamingStatePP));
}
/// <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(DeepSpeechStream stream, uint aNumResults)
{
return(NativeImp.DS_IntermediateDecodeWithMetadata(stream.GetNativePointer(), aNumResults).PtrToMetadata());
}
/// <summary>
/// Creates a new streaming inference state.
/// </summary>
/// <param name="aPreAllocFrames">Number of timestep frames to reserve.
/// One timestep is equivalent to two window lengths(20ms).
/// If set to 0 we reserve enough frames for 3 seconds of audio(150).</param>
/// <param name="aSampleRate">The sample-rate of the audio signal</param>
/// <returns>Zero for success, non-zero on failure</returns>
public unsafe int SetupStream(uint aPreAllocFrames, uint aSampleRate)
{
return(NativeImp.DS_SetupStream(_modelStatePP, aPreAllocFrames, aSampleRate, ref _streamingStatePP));
}
/// <summary>
/// Return version of this library. The returned version is a semantic version
/// (SemVer 2.0.0).
/// </summary>
public unsafe string Version()
{
return(NativeImp.DS_Version().PtrToString());
}
/// <summary>
/// Free a DeepSpeech allocated string
/// </summary>
public unsafe void FreeString(IntPtr intPtr)
{
NativeImp.DS_FreeString(intPtr);
}
/// <summary>
/// Creates a new streaming inference state.
/// </summary>
/// <param name="aSampleRate">The sample-rate of the audio signal</param>
/// <exception cref="ArgumentException">Thrown when the native binary failed to initialize the streaming mode.</exception>
public unsafe void SetupStream(uint aSampleRate)
{
var resultCode = NativeImp.DS_SetupStream(_modelStatePP, aSampleRate, ref _streamingStatePP);
EvaluateResultCode(resultCode);
}
