More renames
This commit is contained in:
parent
ee1235678d
commit
4d726e820d
@ -1,130 +0,0 @@
|
||||
using MozillaVoiceSttClient.Models;
|
||||
using System;
|
||||
using System.IO;
|
||||
|
||||
namespace MozillaVoiceSttClient.Interfaces
|
||||
{
|
||||
/// <summary>
|
||||
/// Client interface of Mozilla Voice STT.
|
||||
/// </summary>
|
||||
public interface IModel : IDisposable
|
||||
{
|
||||
/// <summary>
|
||||
/// Return version of this library. The returned version is a semantic version
|
||||
/// (SemVer 2.0.0).
|
||||
/// </summary>
|
||||
unsafe string Version();
|
||||
|
||||
/// <summary>
|
||||
/// Return the sample rate expected by the model.
|
||||
/// </summary>
|
||||
/// <returns>Sample rate.</returns>
|
||||
unsafe int GetModelSampleRate();
|
||||
|
||||
/// <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>
|
||||
unsafe uint GetModelBeamWidth();
|
||||
|
||||
/// <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>
|
||||
unsafe void SetModelBeamWidth(uint aBeamWidth);
|
||||
|
||||
/// <summary>
|
||||
/// Enable decoding using an external scorer.
|
||||
/// </summary>
|
||||
/// <param name="aScorerPath">The path to the external scorer file.</param>
|
||||
/// <exception cref="ArgumentException">Thrown when the native binary failed to enable decoding with an external scorer.</exception>
|
||||
/// <exception cref="FileNotFoundException">Thrown when cannot find the scorer file.</exception>
|
||||
unsafe void EnableExternalScorer(string aScorerPath);
|
||||
|
||||
/// <summary>
|
||||
/// Disable decoding using an external scorer.
|
||||
/// </summary>
|
||||
/// <exception cref="ArgumentException">Thrown when an external scorer is not enabled.</exception>
|
||||
unsafe void DisableExternalScorer();
|
||||
|
||||
/// <summary>
|
||||
/// Set hyperparameters alpha and beta of the external scorer.
|
||||
/// </summary>
|
||||
/// <param name="aAlpha">The alpha hyperparameter of the decoder. Language model weight.</param>
|
||||
/// <param name="aBeta">The beta hyperparameter of the decoder. Word insertion weight.</param>
|
||||
/// <exception cref="ArgumentException">Thrown when an external scorer is not enabled.</exception>
|
||||
unsafe void SetScorerAlphaBeta(float aAlpha, float aBeta);
|
||||
|
||||
/// <summary>
|
||||
/// Use the Mozilla Voice STT 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>
|
||||
unsafe string SpeechToText(short[] aBuffer,
|
||||
uint aBufferSize);
|
||||
|
||||
/// <summary>
|
||||
/// Use the Mozilla Voice STT 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>
|
||||
unsafe Metadata SpeechToTextWithMetadata(short[] aBuffer,
|
||||
uint aBufferSize,
|
||||
uint aNumResults);
|
||||
|
||||
/// <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>
|
||||
unsafe void FreeStream(MozillaVoiceSttStream stream);
|
||||
|
||||
/// <summary>
|
||||
/// Creates a new streaming inference state.
|
||||
/// </summary>
|
||||
unsafe MozillaVoiceSttStream CreateStream();
|
||||
|
||||
/// <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>
|
||||
unsafe void FeedAudioContent(MozillaVoiceSttStream stream, short[] aBuffer, uint aBufferSize);
|
||||
|
||||
/// <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>
|
||||
unsafe string IntermediateDecode(MozillaVoiceSttStream stream);
|
||||
|
||||
/// <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 extended metadata result.</returns>
|
||||
unsafe Metadata IntermediateDecodeWithMetadata(MozillaVoiceSttStream stream, uint aNumResults);
|
||||
|
||||
/// <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>
|
||||
unsafe string FinishStream(MozillaVoiceSttStream stream);
|
||||
|
||||
/// <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>
|
||||
unsafe Metadata FinishStreamWithMetadata(MozillaVoiceSttStream stream, uint aNumResults);
|
||||
}
|
||||
}
|
@ -1,12 +1,12 @@
|
||||
using MozillaVoiceStt.Interfaces;
|
||||
using MozillaVoiceStt.Extensions;
|
||||
using MozillaVoiceSttClient.Interfaces;
|
||||
using MozillaVoiceSttClient.Extensions;
|
||||
|
||||
using System;
|
||||
using System.IO;
|
||||
using MozillaVoiceStt.Enums;
|
||||
using MozillaVoiceStt.Models;
|
||||
|
||||
namespace MozillaVoiceStt
|
||||
namespace MozillaVoiceSttClient
|
||||
{
|
||||
/// <summary>
|
||||
/// Concrete implementation of <see cref="MozillaVoiceStt.Interfaces.IMozillaVoiceSttModel"/>.
|
||||
|
@ -15,8 +15,8 @@ public class MozillaVoiceSttModel {
|
||||
private SWIGTYPE_p_ModelState _msp;
|
||||
|
||||
private void evaluateErrorCode(int errorCode) {
|
||||
STT_Error_Codes code = STT_Error_Codes.swigToEnum(errorCode);
|
||||
if (code != STT_Error_Codes.ERR_OK) {
|
||||
Error_Codes code = Error_Codes.swigToEnum(errorCode);
|
||||
if (code != Error_Codes.ERR_OK) {
|
||||
throw new RuntimeException("Error: " + impl.ErrorCodeToErrorMessage(errorCode) + " (0x" + Integer.toHexString(errorCode) + ").");
|
||||
}
|
||||
}
|
||||
|
@ -8,11 +8,11 @@
|
||||
|
||||
/* Begin PBXBuildFile section */
|
||||
502AED2D24D9676500E9A4AD /* mozilla_voice_stt.framework in Frameworks */ = {isa = PBXBuildFile; fileRef = 502AED2C24D9676500E9A4AD /* mozilla_voice_stt.framework */; };
|
||||
502AED3024D9677B00E9A4AD /* mozilla_voice_stt.framework in Embed Frameworks */ = {isa = PBXBuildFile; fileRef = 502AED2E24D9677000E9A4AD /* mozilla_voice_stt.framework */; settings = {ATTRIBUTES = (CodeSignOnCopy, RemoveHeadersOnCopy, ); }; };
|
||||
504EC34324CF4EFD0073C22E /* SpeechRecognitionImpl.swift in Sources */ = {isa = PBXBuildFile; fileRef = 504EC34124CF4EFD0073C22E /* SpeechRecognitionImpl.swift */; };
|
||||
504EC34424CF4EFD0073C22E /* AudioContext.swift in Sources */ = {isa = PBXBuildFile; fileRef = 504EC34224CF4EFD0073C22E /* AudioContext.swift */; };
|
||||
507CD3A324B61FEB00409BBB /* libmozilla_voice_stt.so in Frameworks */ = {isa = PBXBuildFile; fileRef = 507CD3A224B61FEA00409BBB /* libmozilla_voice_stt.so */; };
|
||||
507CD3A424B61FFC00409BBB /* libmozilla_voice_stt.so in Embed Frameworks */ = {isa = PBXBuildFile; fileRef = 507CD3A224B61FEA00409BBB /* libmozilla_voice_stt.so */; settings = {ATTRIBUTES = (CodeSignOnCopy, ); }; };
|
||||
509DF81924D9B2C200D1026D /* mozilla_voice_stt.framework in Embed Frameworks */ = {isa = PBXBuildFile; fileRef = 502AED2C24D9676500E9A4AD /* mozilla_voice_stt.framework */; settings = {ATTRIBUTES = (CodeSignOnCopy, RemoveHeadersOnCopy, ); }; };
|
||||
50F787F32497683900D52237 /* AppDelegate.swift in Sources */ = {isa = PBXBuildFile; fileRef = 50F787F22497683900D52237 /* AppDelegate.swift */; };
|
||||
50F787F52497683900D52237 /* SceneDelegate.swift in Sources */ = {isa = PBXBuildFile; fileRef = 50F787F42497683900D52237 /* SceneDelegate.swift */; };
|
||||
50F787F72497683900D52237 /* ContentView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 50F787F62497683900D52237 /* ContentView.swift */; };
|
||||
@ -45,7 +45,7 @@
|
||||
dstPath = "";
|
||||
dstSubfolderSpec = 10;
|
||||
files = (
|
||||
502AED3024D9677B00E9A4AD /* mozilla_voice_stt.framework in Embed Frameworks */,
|
||||
509DF81924D9B2C200D1026D /* mozilla_voice_stt.framework in Embed Frameworks */,
|
||||
507CD3A424B61FFC00409BBB /* libmozilla_voice_stt.so in Embed Frameworks */,
|
||||
);
|
||||
name = "Embed Frameworks";
|
||||
@ -55,7 +55,6 @@
|
||||
|
||||
/* Begin PBXFileReference section */
|
||||
502AED2C24D9676500E9A4AD /* mozilla_voice_stt.framework */ = {isa = PBXFileReference; explicitFileType = wrapper.framework; path = mozilla_voice_stt.framework; sourceTree = BUILT_PRODUCTS_DIR; };
|
||||
502AED2E24D9677000E9A4AD /* mozilla_voice_stt.framework */ = {isa = PBXFileReference; lastKnownFileType = wrapper.framework; name = mozilla_voice_stt.framework; path = "DerivedData/mozilla_voice_stt/Build/Products/Debug-iphoneos/mozilla_voice_stt.framework"; sourceTree = "<group>"; };
|
||||
504EC34124CF4EFD0073C22E /* SpeechRecognitionImpl.swift */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.swift; path = SpeechRecognitionImpl.swift; sourceTree = "<group>"; };
|
||||
504EC34224CF4EFD0073C22E /* AudioContext.swift */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.swift; path = AudioContext.swift; sourceTree = "<group>"; };
|
||||
507CD3A224B61FEA00409BBB /* libmozilla_voice_stt.so */ = {isa = PBXFileReference; lastKnownFileType = "compiled.mach-o.dylib"; path = libmozilla_voice_stt.so; sourceTree = "<group>"; };
|
||||
@ -110,7 +109,6 @@
|
||||
50F787E62497683900D52237 = {
|
||||
isa = PBXGroup;
|
||||
children = (
|
||||
502AED2E24D9677000E9A4AD /* mozilla_voice_stt.framework */,
|
||||
50F787F12497683900D52237 /* mozilla_voice_stt_test */,
|
||||
50F787F02497683900D52237 /* Products */,
|
||||
50F2B0FC2498D6C7007CD876 /* Frameworks */,
|
||||
|
@ -0,0 +1,98 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<Scheme
|
||||
LastUpgradeVersion = "1160"
|
||||
version = "1.3">
|
||||
<BuildAction
|
||||
parallelizeBuildables = "YES"
|
||||
buildImplicitDependencies = "YES">
|
||||
<BuildActionEntries>
|
||||
<BuildActionEntry
|
||||
buildForTesting = "YES"
|
||||
buildForRunning = "YES"
|
||||
buildForProfiling = "YES"
|
||||
buildForArchiving = "YES"
|
||||
buildForAnalyzing = "YES">
|
||||
<BuildableReference
|
||||
BuildableIdentifier = "primary"
|
||||
BlueprintIdentifier = "50F787EE2497683900D52237"
|
||||
BuildableName = "mozilla_voice_stt_test.app"
|
||||
BlueprintName = "mozilla_voice_stt_test"
|
||||
ReferencedContainer = "container:mozilla_voice_stt_test.xcodeproj">
|
||||
</BuildableReference>
|
||||
</BuildActionEntry>
|
||||
</BuildActionEntries>
|
||||
</BuildAction>
|
||||
<TestAction
|
||||
buildConfiguration = "Debug"
|
||||
selectedDebuggerIdentifier = "Xcode.DebuggerFoundation.Debugger.LLDB"
|
||||
selectedLauncherIdentifier = "Xcode.DebuggerFoundation.Launcher.LLDB"
|
||||
shouldUseLaunchSchemeArgsEnv = "YES">
|
||||
<Testables>
|
||||
<TestableReference
|
||||
skipped = "NO">
|
||||
<BuildableReference
|
||||
BuildableIdentifier = "primary"
|
||||
BlueprintIdentifier = "50F788042497683A00D52237"
|
||||
BuildableName = "mozilla_voice_stt_testTests.xctest"
|
||||
BlueprintName = "mozilla_voice_stt_testTests"
|
||||
ReferencedContainer = "container:mozilla_voice_stt_test.xcodeproj">
|
||||
</BuildableReference>
|
||||
</TestableReference>
|
||||
<TestableReference
|
||||
skipped = "NO">
|
||||
<BuildableReference
|
||||
BuildableIdentifier = "primary"
|
||||
BlueprintIdentifier = "50F7880F2497683A00D52237"
|
||||
BuildableName = "mozilla_voice_stt_testUITests.xctest"
|
||||
BlueprintName = "mozilla_voice_stt_testUITests"
|
||||
ReferencedContainer = "container:mozilla_voice_stt_test.xcodeproj">
|
||||
</BuildableReference>
|
||||
</TestableReference>
|
||||
</Testables>
|
||||
</TestAction>
|
||||
<LaunchAction
|
||||
buildConfiguration = "Debug"
|
||||
selectedDebuggerIdentifier = "Xcode.DebuggerFoundation.Debugger.LLDB"
|
||||
selectedLauncherIdentifier = "Xcode.DebuggerFoundation.Launcher.LLDB"
|
||||
launchStyle = "0"
|
||||
useCustomWorkingDirectory = "NO"
|
||||
ignoresPersistentStateOnLaunch = "NO"
|
||||
debugDocumentVersioning = "YES"
|
||||
debugServiceExtension = "internal"
|
||||
allowLocationSimulation = "YES">
|
||||
<BuildableProductRunnable
|
||||
runnableDebuggingMode = "0">
|
||||
<BuildableReference
|
||||
BuildableIdentifier = "primary"
|
||||
BlueprintIdentifier = "50F787EE2497683900D52237"
|
||||
BuildableName = "mozilla_voice_stt_test.app"
|
||||
BlueprintName = "mozilla_voice_stt_test"
|
||||
ReferencedContainer = "container:mozilla_voice_stt_test.xcodeproj">
|
||||
</BuildableReference>
|
||||
</BuildableProductRunnable>
|
||||
</LaunchAction>
|
||||
<ProfileAction
|
||||
buildConfiguration = "Release"
|
||||
shouldUseLaunchSchemeArgsEnv = "YES"
|
||||
savedToolIdentifier = ""
|
||||
useCustomWorkingDirectory = "NO"
|
||||
debugDocumentVersioning = "YES">
|
||||
<BuildableProductRunnable
|
||||
runnableDebuggingMode = "0">
|
||||
<BuildableReference
|
||||
BuildableIdentifier = "primary"
|
||||
BlueprintIdentifier = "50F787EE2497683900D52237"
|
||||
BuildableName = "mozilla_voice_stt_test.app"
|
||||
BlueprintName = "mozilla_voice_stt_test"
|
||||
ReferencedContainer = "container:mozilla_voice_stt_test.xcodeproj">
|
||||
</BuildableReference>
|
||||
</BuildableProductRunnable>
|
||||
</ProfileAction>
|
||||
<AnalyzeAction
|
||||
buildConfiguration = "Debug">
|
||||
</AnalyzeAction>
|
||||
<ArchiveAction
|
||||
buildConfiguration = "Release"
|
||||
revealArchiveInOrganizer = "YES">
|
||||
</ArchiveAction>
|
||||
</Scheme>
|
Loading…
Reference in New Issue
Block a user