experiments/STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Add Swift wrapper framework

Browse Source
This commit is contained in:
Reuben Morais 2020-06-14 12:05:45 +02:00
parent a1aa873259
commit a274c26a89
29 changed files with 2740 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
native_client/swift/.gitignore vendored Normal file
View File

@ -0,0 +1,4 @@
.DS_Store
build/
xcuserdata/
/deepspeech_ios/libdeepspeech.dylib

499
native_client/swift/deepspeech_ios.xcodeproj/project.pbxproj Normal file
View File

@ -0,0 +1,499 @@
// !$*UTF8*$!
{
archiveVersion = 1;
classes = {
};
objectVersion = 50;
objects = {
/* Begin PBXBuildFile section */
505B136B24960D550007DADA /* deepspeech_ios.framework in Frameworks */ = {isa = PBXBuildFile; fileRef = 505B136124960D550007DADA /* deepspeech_ios.framework */; };
505B137224960D550007DADA /* deepspeech_ios.h in Headers */ = {isa = PBXBuildFile; fileRef = 505B136424960D550007DADA /* deepspeech_ios.h */; settings = {ATTRIBUTES = (Public, ); }; };
505B137D24961AF20007DADA /* deepspeech.h in Headers */ = {isa = PBXBuildFile; fileRef = 505B137C24961AF20007DADA /* deepspeech.h */; settings = {ATTRIBUTES = (Private, ); }; };
505B137F24961BA70007DADA /* DeepSpeech.swift in Sources */ = {isa = PBXBuildFile; fileRef = 505B137E24961BA70007DADA /* DeepSpeech.swift */; };
507CD39B24B61FA100409BBB /* libdeepspeech.so in Frameworks */ = {isa = PBXBuildFile; fileRef = 507CD39A24B61FA100409BBB /* libdeepspeech.so */; };
/* End PBXBuildFile section */
/* Begin PBXContainerItemProxy section */
505B136C24960D550007DADA /* PBXContainerItemProxy */ = {
isa = PBXContainerItemProxy;
containerPortal = 505B135824960D550007DADA /* Project object */;
proxyType = 1;
remoteGlobalIDString = 505B136024960D550007DADA;
remoteInfo = deepspeech_ios;
};
/* End PBXContainerItemProxy section */
/* Begin PBXCopyFilesBuildPhase section */
505B138A249628290007DADA /* Embed Libraries */ = {
isa = PBXCopyFilesBuildPhase;
buildActionMask = 12;
dstPath = "";
dstSubfolderSpec = 10;
files = (
);
name = "Embed Libraries";
runOnlyForDeploymentPostprocessing = 0;
};
/* End PBXCopyFilesBuildPhase section */
/* Begin PBXFileReference section */
505B136124960D550007DADA /* deepspeech_ios.framework */ = {isa = PBXFileReference; explicitFileType = wrapper.framework; includeInIndex = 0; path = deepspeech_ios.framework; sourceTree = BUILT_PRODUCTS_DIR; };
505B136424960D550007DADA /* deepspeech_ios.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = deepspeech_ios.h; sourceTree = "<group>"; };
505B136524960D550007DADA /* Info.plist */ = {isa = PBXFileReference; lastKnownFileType = text.plist.xml; path = Info.plist; sourceTree = "<group>"; };
505B136A24960D550007DADA /* deepspeech_iosTests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = deepspeech_iosTests.xctest; sourceTree = BUILT_PRODUCTS_DIR; };
505B137B249619C90007DADA /* deepspeech_ios.modulemap */ = {isa = PBXFileReference; lastKnownFileType = "sourcecode.module-map"; path = deepspeech_ios.modulemap; sourceTree = "<group>"; };
505B137C24961AF20007DADA /* deepspeech.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; name = deepspeech.h; path = ../../deepspeech.h; sourceTree = "<group>"; };
505B137E24961BA70007DADA /* DeepSpeech.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = DeepSpeech.swift; sourceTree = "<group>"; };
507CD39A24B61FA100409BBB /* libdeepspeech.so */ = {isa = PBXFileReference; lastKnownFileType = "compiled.mach-o.dylib"; path = libdeepspeech.so; sourceTree = "<group>"; };
/* End PBXFileReference section */
/* Begin PBXFrameworksBuildPhase section */
505B135E24960D550007DADA /* Frameworks */ = {
isa = PBXFrameworksBuildPhase;
buildActionMask = 2147483647;
files = (
507CD39B24B61FA100409BBB /* libdeepspeech.so in Frameworks */,
);
runOnlyForDeploymentPostprocessing = 0;
};
505B136724960D550007DADA /* Frameworks */ = {
isa = PBXFrameworksBuildPhase;
buildActionMask = 2147483647;
files = (
505B136B24960D550007DADA /* deepspeech_ios.framework in Frameworks */,
);
runOnlyForDeploymentPostprocessing = 0;
};
/* End PBXFrameworksBuildPhase section */
/* Begin PBXGroup section */
505B135724960D550007DADA = {
isa = PBXGroup;
children = (
505B136324960D550007DADA /* deepspeech_ios */,
505B136224960D550007DADA /* Products */,
505B1380249620C60007DADA /* Frameworks */,
);
sourceTree = "<group>";
};
505B136224960D550007DADA /* Products */ = {
isa = PBXGroup;
children = (
505B136124960D550007DADA /* deepspeech_ios.framework */,
505B136A24960D550007DADA /* deepspeech_iosTests.xctest */,
);
name = Products;
sourceTree = "<group>";
};
505B136324960D550007DADA /* deepspeech_ios */ = {
isa = PBXGroup;
children = (
505B137C24961AF20007DADA /* deepspeech.h */,
505B136424960D550007DADA /* deepspeech_ios.h */,
505B137E24961BA70007DADA /* DeepSpeech.swift */,
505B137B249619C90007DADA /* deepspeech_ios.modulemap */,
505B136524960D550007DADA /* Info.plist */,
);
path = deepspeech_ios;
sourceTree = "<group>";
};
505B1380249620C60007DADA /* Frameworks */ = {
isa = PBXGroup;
children = (
507CD39A24B61FA100409BBB /* libdeepspeech.so */,
);
name = Frameworks;
sourceTree = "<group>";
};
/* End PBXGroup section */
/* Begin PBXHeadersBuildPhase section */
505B135C24960D550007DADA /* Headers */ = {
isa = PBXHeadersBuildPhase;
buildActionMask = 2147483647;
files = (
505B137224960D550007DADA /* deepspeech_ios.h in Headers */,
505B137D24961AF20007DADA /* deepspeech.h in Headers */,
);
runOnlyForDeploymentPostprocessing = 0;
};
/* End PBXHeadersBuildPhase section */
/* Begin PBXNativeTarget section */
505B136024960D550007DADA /* deepspeech_ios */ = {
isa = PBXNativeTarget;
buildConfigurationList = 505B137524960D550007DADA /* Build configuration list for PBXNativeTarget "deepspeech_ios" */;
buildPhases = (
505B135C24960D550007DADA /* Headers */,
505B135D24960D550007DADA /* Sources */,
505B135E24960D550007DADA /* Frameworks */,
505B135F24960D550007DADA /* Resources */,
505B138A249628290007DADA /* Embed Libraries */,
);
buildRules = (
);
dependencies = (
);
name = deepspeech_ios;
productName = deepspeech_ios;
productReference = 505B136124960D550007DADA /* deepspeech_ios.framework */;
productType = "com.apple.product-type.framework";
};
505B136924960D550007DADA /* deepspeech_iosTests */ = {
isa = PBXNativeTarget;
buildConfigurationList = 505B137824960D550007DADA /* Build configuration list for PBXNativeTarget "deepspeech_iosTests" */;
buildPhases = (
505B136624960D550007DADA /* Sources */,
505B136724960D550007DADA /* Frameworks */,
505B136824960D550007DADA /* Resources */,
);
buildRules = (
);
dependencies = (
505B136D24960D550007DADA /* PBXTargetDependency */,
);
name = deepspeech_iosTests;
productName = deepspeech_iosTests;
productReference = 505B136A24960D550007DADA /* deepspeech_iosTests.xctest */;
productType = "com.apple.product-type.bundle.unit-test";
};
/* End PBXNativeTarget section */
/* Begin PBXProject section */
505B135824960D550007DADA /* Project object */ = {
isa = PBXProject;
attributes = {
LastSwiftUpdateCheck = 1150;
LastUpgradeCheck = 1150;
ORGANIZATIONNAME = Mozilla;
TargetAttributes = {
505B136024960D550007DADA = {
CreatedOnToolsVersion = 11.5;
LastSwiftMigration = 1150;
};
505B136924960D550007DADA = {
CreatedOnToolsVersion = 11.5;
};
};
};
buildConfigurationList = 505B135B24960D550007DADA /* Build configuration list for PBXProject "deepspeech_ios" */;
compatibilityVersion = "Xcode 9.3";
developmentRegion = en;
hasScannedForEncodings = 0;
knownRegions = (
en,
Base,
);
mainGroup = 505B135724960D550007DADA;
productRefGroup = 505B136224960D550007DADA /* Products */;
projectDirPath = "";
projectRoot = "";
targets = (
505B136024960D550007DADA /* deepspeech_ios */,
505B136924960D550007DADA /* deepspeech_iosTests */,
);
};
/* End PBXProject section */
/* Begin PBXResourcesBuildPhase section */
505B135F24960D550007DADA /* Resources */ = {
isa = PBXResourcesBuildPhase;
buildActionMask = 2147483647;
files = (
);
runOnlyForDeploymentPostprocessing = 0;
};
505B136824960D550007DADA /* Resources */ = {
isa = PBXResourcesBuildPhase;
buildActionMask = 2147483647;
files = (
);
runOnlyForDeploymentPostprocessing = 0;
};
/* End PBXResourcesBuildPhase section */
/* Begin PBXSourcesBuildPhase section */
505B135D24960D550007DADA /* Sources */ = {
isa = PBXSourcesBuildPhase;
buildActionMask = 2147483647;
files = (
505B137F24961BA70007DADA /* DeepSpeech.swift in Sources */,
);
runOnlyForDeploymentPostprocessing = 0;
};
505B136624960D550007DADA /* Sources */ = {
isa = PBXSourcesBuildPhase;
buildActionMask = 2147483647;
files = (
);
runOnlyForDeploymentPostprocessing = 0;
};
/* End PBXSourcesBuildPhase section */
/* Begin PBXTargetDependency section */
505B136D24960D550007DADA /* PBXTargetDependency */ = {
isa = PBXTargetDependency;
target = 505B136024960D550007DADA /* deepspeech_ios */;
targetProxy = 505B136C24960D550007DADA /* PBXContainerItemProxy */;
};
/* End PBXTargetDependency section */
/* Begin XCBuildConfiguration section */
505B137324960D550007DADA /* Debug */ = {
isa = XCBuildConfiguration;
buildSettings = {
ALWAYS_SEARCH_USER_PATHS = NO;
CLANG_ANALYZER_NONNULL = YES;
CLANG_ANALYZER_NUMBER_OBJECT_CONVERSION = YES_AGGRESSIVE;
CLANG_CXX_LANGUAGE_STANDARD = "gnu++14";
CLANG_CXX_LIBRARY = "libc++";
CLANG_ENABLE_MODULES = YES;
CLANG_ENABLE_OBJC_ARC = YES;
CLANG_ENABLE_OBJC_WEAK = YES;
CLANG_WARN_BLOCK_CAPTURE_AUTORELEASING = YES;
CLANG_WARN_BOOL_CONVERSION = YES;
CLANG_WARN_COMMA = YES;
CLANG_WARN_CONSTANT_CONVERSION = YES;
CLANG_WARN_DEPRECATED_OBJC_IMPLEMENTATIONS = YES;
CLANG_WARN_DIRECT_OBJC_ISA_USAGE = YES_ERROR;
CLANG_WARN_DOCUMENTATION_COMMENTS = YES;
CLANG_WARN_EMPTY_BODY = YES;
CLANG_WARN_ENUM_CONVERSION = YES;
CLANG_WARN_INFINITE_RECURSION = YES;
CLANG_WARN_INT_CONVERSION = YES;
CLANG_WARN_NON_LITERAL_NULL_CONVERSION = YES;
CLANG_WARN_OBJC_IMPLICIT_RETAIN_SELF = YES;
CLANG_WARN_OBJC_LITERAL_CONVERSION = YES;
CLANG_WARN_OBJC_ROOT_CLASS = YES_ERROR;
CLANG_WARN_RANGE_LOOP_ANALYSIS = YES;
CLANG_WARN_STRICT_PROTOTYPES = YES;
CLANG_WARN_SUSPICIOUS_MOVE = YES;
CLANG_WARN_UNGUARDED_AVAILABILITY = YES_AGGRESSIVE;
CLANG_WARN_UNREACHABLE_CODE = YES;
CLANG_WARN__DUPLICATE_METHOD_MATCH = YES;
COPY_PHASE_STRIP = NO;
CURRENT_PROJECT_VERSION = 1;
DEBUG_INFORMATION_FORMAT = dwarf;
ENABLE_STRICT_OBJC_MSGSEND = YES;
ENABLE_TESTABILITY = YES;
GCC_C_LANGUAGE_STANDARD = gnu11;
GCC_DYNAMIC_NO_PIC = NO;
GCC_NO_COMMON_BLOCKS = YES;
GCC_OPTIMIZATION_LEVEL = 0;
GCC_PREPROCESSOR_DEFINITIONS = (
"DEBUG=1",
"$(inherited)",
);
GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
GCC_WARN_ABOUT_RETURN_TYPE = YES_ERROR;
GCC_WARN_UNDECLARED_SELECTOR = YES;
GCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE;
GCC_WARN_UNUSED_FUNCTION = YES;
GCC_WARN_UNUSED_VARIABLE = YES;
IPHONEOS_DEPLOYMENT_TARGET = 13.5;
MTL_ENABLE_DEBUG_INFO = INCLUDE_SOURCE;
MTL_FAST_MATH = YES;
ONLY_ACTIVE_ARCH = YES;
SDKROOT = iphoneos;
SWIFT_ACTIVE_COMPILATION_CONDITIONS = DEBUG;
SWIFT_OPTIMIZATION_LEVEL = "-Onone";
VERSIONING_SYSTEM = "apple-generic";
VERSION_INFO_PREFIX = "";
};
name = Debug;
};
505B137424960D550007DADA /* Release */ = {
isa = XCBuildConfiguration;
buildSettings = {
ALWAYS_SEARCH_USER_PATHS = NO;
CLANG_ANALYZER_NONNULL = YES;
CLANG_ANALYZER_NUMBER_OBJECT_CONVERSION = YES_AGGRESSIVE;
CLANG_CXX_LANGUAGE_STANDARD = "gnu++14";
CLANG_CXX_LIBRARY = "libc++";
CLANG_ENABLE_MODULES = YES;
CLANG_ENABLE_OBJC_ARC = YES;
CLANG_ENABLE_OBJC_WEAK = YES;
CLANG_WARN_BLOCK_CAPTURE_AUTORELEASING = YES;
CLANG_WARN_BOOL_CONVERSION = YES;
CLANG_WARN_COMMA = YES;
CLANG_WARN_CONSTANT_CONVERSION = YES;
CLANG_WARN_DEPRECATED_OBJC_IMPLEMENTATIONS = YES;
CLANG_WARN_DIRECT_OBJC_ISA_USAGE = YES_ERROR;
CLANG_WARN_DOCUMENTATION_COMMENTS = YES;
CLANG_WARN_EMPTY_BODY = YES;
CLANG_WARN_ENUM_CONVERSION = YES;
CLANG_WARN_INFINITE_RECURSION = YES;
CLANG_WARN_INT_CONVERSION = YES;
CLANG_WARN_NON_LITERAL_NULL_CONVERSION = YES;
CLANG_WARN_OBJC_IMPLICIT_RETAIN_SELF = YES;
CLANG_WARN_OBJC_LITERAL_CONVERSION = YES;
CLANG_WARN_OBJC_ROOT_CLASS = YES_ERROR;
CLANG_WARN_RANGE_LOOP_ANALYSIS = YES;
CLANG_WARN_STRICT_PROTOTYPES = YES;
CLANG_WARN_SUSPICIOUS_MOVE = YES;
CLANG_WARN_UNGUARDED_AVAILABILITY = YES_AGGRESSIVE;
CLANG_WARN_UNREACHABLE_CODE = YES;
CLANG_WARN__DUPLICATE_METHOD_MATCH = YES;
COPY_PHASE_STRIP = NO;
CURRENT_PROJECT_VERSION = 1;
DEBUG_INFORMATION_FORMAT = "dwarf-with-dsym";
ENABLE_NS_ASSERTIONS = NO;
ENABLE_STRICT_OBJC_MSGSEND = YES;
GCC_C_LANGUAGE_STANDARD = gnu11;
GCC_NO_COMMON_BLOCKS = YES;
GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
GCC_WARN_ABOUT_RETURN_TYPE = YES_ERROR;
GCC_WARN_UNDECLARED_SELECTOR = YES;
GCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE;
GCC_WARN_UNUSED_FUNCTION = YES;
GCC_WARN_UNUSED_VARIABLE = YES;
IPHONEOS_DEPLOYMENT_TARGET = 13.5;
MTL_ENABLE_DEBUG_INFO = NO;
MTL_FAST_MATH = YES;
SDKROOT = iphoneos;
SWIFT_COMPILATION_MODE = wholemodule;
SWIFT_OPTIMIZATION_LEVEL = "-O";
VALIDATE_PRODUCT = YES;
VERSIONING_SYSTEM = "apple-generic";
VERSION_INFO_PREFIX = "";
};
name = Release;
};
505B137624960D550007DADA /* Debug */ = {
isa = XCBuildConfiguration;
buildSettings = {
CLANG_ENABLE_MODULES = YES;
CODE_SIGN_IDENTITY = "Apple Development";
"CODE_SIGN_IDENTITY[sdk=macosx*]" = "Apple Development";
CODE_SIGN_STYLE = Automatic;
DEFINES_MODULE = YES;
DEVELOPMENT_TEAM = AWCG9S27P7;
DYLIB_COMPATIBILITY_VERSION = 1;
DYLIB_CURRENT_VERSION = 1;
DYLIB_INSTALL_NAME_BASE = "@rpath";
INFOPLIST_FILE = deepspeech_ios/Info.plist;
INSTALL_PATH = "$(LOCAL_LIBRARY_DIR)/Frameworks";
LD_RUNPATH_SEARCH_PATHS = (
"$(inherited)",
"@executable_path/Frameworks",
"@loader_path/Frameworks",
);
LIBRARY_SEARCH_PATHS = (
"$(inherited)",
"$(PROJECT_DIR)/deepspeech_ios",
"$(PROJECT_DIR)",
);
MODULEMAP_FILE = deepspeech_ios/deepspeech_ios.modulemap;
PRODUCT_BUNDLE_IDENTIFIER = "org.mozilla.deepspeech-ios";
PRODUCT_NAME = "$(TARGET_NAME:c99extidentifier)";
SKIP_INSTALL = YES;
SWIFT_OPTIMIZATION_LEVEL = "-Onone";
SWIFT_VERSION = 5.0;
TARGETED_DEVICE_FAMILY = "1,2";
};
name = Debug;
};
505B137724960D550007DADA /* Release */ = {
isa = XCBuildConfiguration;
buildSettings = {
CLANG_ENABLE_MODULES = YES;
CODE_SIGN_IDENTITY = "Apple Development";
"CODE_SIGN_IDENTITY[sdk=macosx*]" = "Apple Development";
CODE_SIGN_STYLE = Automatic;
DEFINES_MODULE = YES;
DEVELOPMENT_TEAM = AWCG9S27P7;
DYLIB_COMPATIBILITY_VERSION = 1;
DYLIB_CURRENT_VERSION = 1;
DYLIB_INSTALL_NAME_BASE = "@rpath";
INFOPLIST_FILE = deepspeech_ios/Info.plist;
INSTALL_PATH = "$(LOCAL_LIBRARY_DIR)/Frameworks";
LD_RUNPATH_SEARCH_PATHS = (
"$(inherited)",
"@executable_path/Frameworks",
"@loader_path/Frameworks",
);
LIBRARY_SEARCH_PATHS = (
"$(inherited)",
"$(PROJECT_DIR)/deepspeech_ios",
"$(PROJECT_DIR)",
);
MODULEMAP_FILE = deepspeech_ios/deepspeech_ios.modulemap;
PRODUCT_BUNDLE_IDENTIFIER = "org.mozilla.deepspeech-ios";
PRODUCT_NAME = "$(TARGET_NAME:c99extidentifier)";
SKIP_INSTALL = YES;
SWIFT_VERSION = 5.0;
TARGETED_DEVICE_FAMILY = "1,2";
};
name = Release;
};
505B137924960D550007DADA /* Debug */ = {
isa = XCBuildConfiguration;
buildSettings = {
ALWAYS_EMBED_SWIFT_STANDARD_LIBRARIES = YES;
CODE_SIGN_STYLE = Automatic;
INFOPLIST_FILE = deepspeech_iosTests/Info.plist;
LD_RUNPATH_SEARCH_PATHS = (
"$(inherited)",
"@executable_path/Frameworks",
"@loader_path/Frameworks",
);
PRODUCT_BUNDLE_IDENTIFIER = "org.mozilla.deepspeech-iosTests";
PRODUCT_NAME = "$(TARGET_NAME)";
SWIFT_VERSION = 5.0;
TARGETED_DEVICE_FAMILY = "1,2";
};
name = Debug;
};
505B137A24960D550007DADA /* Release */ = {
isa = XCBuildConfiguration;
buildSettings = {
ALWAYS_EMBED_SWIFT_STANDARD_LIBRARIES = YES;
CODE_SIGN_STYLE = Automatic;
INFOPLIST_FILE = deepspeech_iosTests/Info.plist;
LD_RUNPATH_SEARCH_PATHS = (
"$(inherited)",
"@executable_path/Frameworks",
"@loader_path/Frameworks",
);
PRODUCT_BUNDLE_IDENTIFIER = "org.mozilla.deepspeech-iosTests";
PRODUCT_NAME = "$(TARGET_NAME)";
SWIFT_VERSION = 5.0;
TARGETED_DEVICE_FAMILY = "1,2";
};
name = Release;
};
/* End XCBuildConfiguration section */
/* Begin XCConfigurationList section */
505B135B24960D550007DADA /* Build configuration list for PBXProject "deepspeech_ios" */ = {
isa = XCConfigurationList;
buildConfigurations = (
505B137324960D550007DADA /* Debug */,
505B137424960D550007DADA /* Release */,
);
defaultConfigurationIsVisible = 0;
defaultConfigurationName = Release;
};
505B137524960D550007DADA /* Build configuration list for PBXNativeTarget "deepspeech_ios" */ = {
isa = XCConfigurationList;
buildConfigurations = (
505B137624960D550007DADA /* Debug */,
505B137724960D550007DADA /* Release */,
);
defaultConfigurationIsVisible = 0;
defaultConfigurationName = Release;
};
505B137824960D550007DADA /* Build configuration list for PBXNativeTarget "deepspeech_iosTests" */ = {
isa = XCConfigurationList;
buildConfigurations = (
505B137924960D550007DADA /* Debug */,
505B137A24960D550007DADA /* Release */,
);
defaultConfigurationIsVisible = 0;
defaultConfigurationName = Release;
};
/* End XCConfigurationList section */
};
rootObject = 505B135824960D550007DADA /* Project object */;
}

7
native_client/swift/deepspeech_ios.xcodeproj/project.xcworkspace/contents.xcworkspacedata generated Normal file
View File

@ -0,0 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<Workspace
version = "1.0">
<FileRef
location = "self:deepspeech_ios.xcodeproj">
</FileRef>
</Workspace>

8
native_client/swift/deepspeech_ios.xcodeproj/project.xcworkspace/xcshareddata/IDEWorkspaceChecks.plist Normal file
View File

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>IDEDidComputeMac32BitWarning</key>
<true/>
</dict>
</plist>

77
native_client/swift/deepspeech_ios.xcodeproj/xcshareddata/xcschemes/deepspeech_ios.xcscheme Normal file
View File

@ -0,0 +1,77 @@
<?xml version="1.0" encoding="UTF-8"?>
<Scheme
LastUpgradeVersion = "1150"
version = "1.3">
<BuildAction
parallelizeBuildables = "YES"
buildImplicitDependencies = "YES">
<BuildActionEntries>
<BuildActionEntry
buildForTesting = "YES"
buildForRunning = "YES"
buildForProfiling = "YES"
buildForArchiving = "YES"
buildForAnalyzing = "YES">
<BuildableReference
BuildableIdentifier = "primary"
BlueprintIdentifier = "505B136024960D550007DADA"
BuildableName = "deepspeech_ios.framework"
BlueprintName = "deepspeech_ios"
ReferencedContainer = "container:deepspeech_ios.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 = "505B136924960D550007DADA"
BuildableName = "deepspeech_iosTests.xctest"
BlueprintName = "deepspeech_iosTests"
ReferencedContainer = "container:deepspeech_ios.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">
</LaunchAction>
<ProfileAction
buildConfiguration = "Release"
shouldUseLaunchSchemeArgsEnv = "YES"
savedToolIdentifier = ""
useCustomWorkingDirectory = "NO"
debugDocumentVersioning = "YES">
<MacroExpansion>
<BuildableReference
BuildableIdentifier = "primary"
BlueprintIdentifier = "505B136024960D550007DADA"
BuildableName = "deepspeech_ios.framework"
BlueprintName = "deepspeech_ios"
ReferencedContainer = "container:deepspeech_ios.xcodeproj">
</BuildableReference>
</MacroExpansion>
</ProfileAction>
<AnalyzeAction
buildConfiguration = "Debug">
</AnalyzeAction>
<ArchiveAction
buildConfiguration = "Release"
revealArchiveInOrganizer = "YES">
</ArchiveAction>
</Scheme>

10
native_client/swift/deepspeech_ios.xcworkspace/contents.xcworkspacedata generated Normal file
View File

@ -0,0 +1,10 @@
<?xml version="1.0" encoding="UTF-8"?>
<Workspace
version = "1.0">
<FileRef
location = "group:deepspeech_ios.xcodeproj">
</FileRef>
<FileRef
location = "group:deepspeech_ios_test/deepspeech_ios_test.xcodeproj">
</FileRef>
</Workspace>

8
native_client/swift/deepspeech_ios.xcworkspace/xcshareddata/IDEWorkspaceChecks.plist Normal file
View File

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>IDEDidComputeMac32BitWarning</key>
<true/>
</dict>
</plist>

8
native_client/swift/deepspeech_ios.xcworkspace/xcshareddata/WorkspaceSettings.xcsettings Normal file
View File

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>PreviewsEnabled</key>
<false/>
</dict>
</plist>

301
native_client/swift/deepspeech_ios/DeepSpeech.swift Normal file
View File

@ -0,0 +1,301 @@
//
// DeepSpeech.swift
// deepspeech_ios
//
// Created by Reuben Morais on 14.06.20.
// Copyright © 2020 Mozilla. All rights reserved.
//
import deepspeech_ios.libdeepspeech_Private
public enum DeepSpeechError: Error {
// Should be kept in sync with deepspeech.h
case noModel(errorCode: Int32)
case invalidAlphabet(errorCode: Int32)
case invalidShape(errorCode: Int32)
case invalidScorer(errorCode: Int32)
case modelIncompatible(errorCode: Int32)
case scorerNotEnabled(errorCode: Int32)
case scorerUnreadable(errorCode: Int32)
case scorerInvalidLm(errorCode: Int32)
case scorerNoTrie(errorCode: Int32)
case scorerInvalidTrie(errorCode: Int32)
case scorerVersionMismatch(errorCode: Int32)
case failInitMmap(errorCode: Int32)
case failInitSess(errorCode: Int32)
case failInterpreter(errorCode: Int32)
case failRunSess(errorCode: Int32)
case failCreateStream(errorCode: Int32)
case failReadProtobuf(errorCode: Int32)
case failCreateSess(errorCode: Int32)
case failCreateModel(errorCode: Int32)
// Additional case for invalid error codes, should never happen unless the user has mixed header and binary versions
case invalidErrorCode(errorCode: Int32)
}
extension DeepSpeechError : LocalizedError {
public var errorDescription: String? {
switch self {
case .noModel(let errorCode),
.invalidAlphabet(let errorCode),
.invalidShape(let errorCode),
.invalidScorer(let errorCode),
.modelIncompatible(let errorCode),
.scorerNotEnabled(let errorCode),
.scorerUnreadable(let errorCode),
.scorerInvalidLm(let errorCode),
.scorerNoTrie(let errorCode),
.scorerInvalidTrie(let errorCode),
.scorerVersionMismatch(let errorCode),
.failInitMmap(let errorCode),
.failInitSess(let errorCode),
.failInterpreter(let errorCode),
.failRunSess(let errorCode),
.failCreateStream(let errorCode),
.failReadProtobuf(let errorCode),
.failCreateSess(let errorCode),
.failCreateModel(let errorCode),
.invalidErrorCode(let errorCode):
let result = DS_ErrorCodeToErrorMessage(errorCode)
defer { DS_FreeString(result) }
return String(cString: result!)
}
}
}
private func errorCodeToEnum(errorCode: Int32) -> DeepSpeechError {
switch Int(errorCode) {
case Int(DS_ERR_NO_MODEL.rawValue):
return DeepSpeechError.noModel(errorCode: errorCode)
case Int(DS_ERR_INVALID_ALPHABET.rawValue):
return DeepSpeechError.invalidAlphabet(errorCode: errorCode)
case Int(DS_ERR_INVALID_SHAPE.rawValue):
return DeepSpeechError.invalidShape(errorCode: errorCode)
case Int(DS_ERR_INVALID_SCORER.rawValue):
return DeepSpeechError.invalidScorer(errorCode: errorCode)
case Int(DS_ERR_MODEL_INCOMPATIBLE.rawValue):
return DeepSpeechError.modelIncompatible(errorCode: errorCode)
case Int(DS_ERR_SCORER_NOT_ENABLED.rawValue):
return DeepSpeechError.scorerNotEnabled(errorCode: errorCode)
case Int(DS_ERR_SCORER_UNREADABLE.rawValue):
return DeepSpeechError.scorerUnreadable(errorCode: errorCode)
case Int(DS_ERR_SCORER_INVALID_LM.rawValue):
return DeepSpeechError.scorerInvalidLm(errorCode: errorCode)
case Int(DS_ERR_SCORER_NO_TRIE.rawValue):
return DeepSpeechError.scorerNoTrie(errorCode: errorCode)
case Int(DS_ERR_SCORER_INVALID_TRIE.rawValue):
return DeepSpeechError.scorerInvalidTrie(errorCode: errorCode)
case Int(DS_ERR_SCORER_VERSION_MISMATCH.rawValue):
return DeepSpeechError.scorerVersionMismatch(errorCode: errorCode)
case Int(DS_ERR_FAIL_INIT_MMAP.rawValue):
return DeepSpeechError.failInitMmap(errorCode: errorCode)
case Int(DS_ERR_FAIL_INIT_SESS.rawValue):
return DeepSpeechError.failInitSess(errorCode: errorCode)
case Int(DS_ERR_FAIL_INTERPRETER.rawValue):
return DeepSpeechError.failInterpreter(errorCode: errorCode)
case Int(DS_ERR_FAIL_RUN_SESS.rawValue):
return DeepSpeechError.failRunSess(errorCode: errorCode)
case Int(DS_ERR_FAIL_CREATE_STREAM.rawValue):
return DeepSpeechError.failCreateStream(errorCode: errorCode)
case Int(DS_ERR_FAIL_READ_PROTOBUF.rawValue):
return DeepSpeechError.failReadProtobuf(errorCode: errorCode)
case Int(DS_ERR_FAIL_CREATE_SESS.rawValue):
return DeepSpeechError.failCreateSess(errorCode: errorCode)
case Int(DS_ERR_FAIL_CREATE_MODEL.rawValue):
return DeepSpeechError.failCreateModel(errorCode: errorCode)
default:
return DeepSpeechError.invalidErrorCode(errorCode: errorCode)
}
}
private func evaluateErrorCode(errorCode: Int32) throws {
if errorCode != Int32(DS_ERR_OK.rawValue) {
throw errorCodeToEnum(errorCode: errorCode)
}
}
public struct DeepSpeechTokenMetadata {
let text: String
let timestep: Int
let startTime: Float
internal init(fromInternal: TokenMetadata) {
text = String(cString: fromInternal.text)
timestep = Int(fromInternal.timestep)
startTime = fromInternal.start_time
}
}
public struct DeepSpeechCandidateTranscript {
private(set) var tokens: [DeepSpeechTokenMetadata] = []
let confidence: Double
internal init(fromInternal: CandidateTranscript) {
let tokensBuffer = UnsafeBufferPointer<TokenMetadata>(start: fromInternal.tokens, count: Int(fromInternal.num_tokens))
for tok in tokensBuffer {
tokens.append(DeepSpeechTokenMetadata(fromInternal: tok))
}
confidence = fromInternal.confidence
}
}
public struct DeepSpeechMetadata {
private(set) var transcripts: [DeepSpeechCandidateTranscript] = []
internal init(fromInternal: UnsafeMutablePointer<Metadata>) {
let md = fromInternal.pointee
let transcriptsBuffer = UnsafeBufferPointer<CandidateTranscript>(start: md.transcripts, count: Int(md.num_transcripts))
for tr in transcriptsBuffer {
transcripts.append(DeepSpeechCandidateTranscript(fromInternal: tr))
}
}
}
public class DeepSpeechStream {
private var streamCtx: OpaquePointer!
internal init(streamContext: OpaquePointer) {
streamCtx = streamContext
}
deinit {
if streamCtx != nil {
DS_FreeStream(streamCtx)
streamCtx = nil
}
}
public func feedAudioContent(buffer: Array<Int16>) {
precondition(streamCtx != nil, "calling method on invalidated Stream")
buffer.withUnsafeBufferPointer { unsafeBufferPointer in
feedAudioContent(buffer: unsafeBufferPointer)
}
}
public func feedAudioContent(buffer: UnsafeBufferPointer<Int16>) {
precondition(streamCtx != nil, "calling method on invalidated Stream")
DS_FeedAudioContent(streamCtx, buffer.baseAddress, UInt32(buffer.count))
}
public func intermediateDecode() -> String {
precondition(streamCtx != nil, "calling method on invalidated Stream")
let result = DS_IntermediateDecode(streamCtx)
defer { DS_FreeString(result) }
return String(cString: result!)
}
public func intermediateDecodeWithMetadata(numResults: Int) -> DeepSpeechMetadata {
precondition(streamCtx != nil, "calling method on invalidated Stream")
let result = DS_IntermediateDecodeWithMetadata(streamCtx, UInt32(numResults))!
defer { DS_FreeMetadata(result) }
return DeepSpeechMetadata(fromInternal: result)
}
public func finishStream() -> String {
precondition(streamCtx != nil, "calling method on invalidated Stream")
let result = DS_FinishStream(streamCtx)
defer {
DS_FreeString(result)
streamCtx = nil
}
return String(cString: result!)
}
}
public class DeepSpeechModel {
private var modelCtx: OpaquePointer!
public init(modelPath: String) throws {
let err = DS_CreateModel(modelPath, &modelCtx)
try evaluateErrorCode(errorCode: err)
}
deinit {
DS_FreeModel(modelCtx)
modelCtx = nil
}
public func getBeamWidth() -> Int {
return Int(DS_GetModelBeamWidth(modelCtx))
}
public func setBeamWidth(beamWidth: Int) throws {
let err = DS_SetModelBeamWidth(modelCtx, UInt32(beamWidth))
try evaluateErrorCode(errorCode: err)
}
public var sampleRate: Int {
get {
return Int(DS_GetModelSampleRate(modelCtx))
}
}
public func enableExternalScorer(scorerPath: String) throws {
let err = DS_EnableExternalScorer(modelCtx, scorerPath)
try evaluateErrorCode(errorCode: err)
}
public func disableExternalScorer() throws {
let err = DS_DisableExternalScorer(modelCtx)
try evaluateErrorCode(errorCode: err)
}
public func setScorerAlphaBeta(alpha: Float, beta: Float) throws {
let err = DS_SetScorerAlphaBeta(modelCtx, alpha, beta)
try evaluateErrorCode(errorCode: err)
}
public func speechToText(buffer: Array<Int16>) -> String {
return buffer.withUnsafeBufferPointer { unsafeBufferPointer -> String in
return speechToText(buffer: unsafeBufferPointer)
}
}
public func speechToText(buffer: UnsafeBufferPointer<Int16>) -> String {
let result = DS_SpeechToText(modelCtx, buffer.baseAddress, UInt32(buffer.count))
defer { DS_FreeString(result) }
return String(cString: result!)
}
public func speechToTextWithMetadata(buffer: Array<Int16>, numResults: Int) -> DeepSpeechMetadata {
return buffer.withUnsafeBufferPointer { unsafeBufferPointer -> DeepSpeechMetadata in
let result = DS_SpeechToTextWithMetadata(modelCtx, unsafeBufferPointer.baseAddress, UInt32(buffer.count), UInt32(numResults))!
defer { DS_FreeMetadata(result) }
return DeepSpeechMetadata(fromInternal: result)
}
}
public func createStream() throws -> DeepSpeechStream {
var streamContext: OpaquePointer!
let err = DS_CreateStream(modelCtx, &streamContext)
try evaluateErrorCode(errorCode: err)
return DeepSpeechStream(streamContext: streamContext)
}
public class func open(path: String, scorerPath: Optional<String> = nil) -> OpaquePointer {
var fooOpaque: OpaquePointer!
DS_CreateModel(path, &fooOpaque)
if let scorerPath = scorerPath {
DS_EnableExternalScorer(fooOpaque, scorerPath)
}
return fooOpaque
}
public class func createStream(modelState: OpaquePointer) -> OpaquePointer {
var fooOpaque: OpaquePointer!
DS_CreateStream(modelState, &fooOpaque)
return fooOpaque
}
}
public func DeepSpeechVersion() -> String {
let result = DS_Version()
defer { DS_FreeString(result) }
return String(cString: result!)
}

22
native_client/swift/deepspeech_ios/Info.plist Normal file
View File

@ -0,0 +1,22 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>CFBundleDevelopmentRegion</key>
<string>$(DEVELOPMENT_LANGUAGE)</string>
<key>CFBundleExecutable</key>
<string>$(EXECUTABLE_NAME)</string>
<key>CFBundleIdentifier</key>
<string>$(PRODUCT_BUNDLE_IDENTIFIER)</string>
<key>CFBundleInfoDictionaryVersion</key>
<string>6.0</string>
<key>CFBundleName</key>
<string>$(PRODUCT_NAME)</string>
<key>CFBundlePackageType</key>
<string>$(PRODUCT_BUNDLE_PACKAGE_TYPE)</string>
<key>CFBundleShortVersionString</key>
<string>1.0</string>
<key>CFBundleVersion</key>
<string>$(CURRENT_PROJECT_VERSION)</string>
</dict>
</plist>

357
native_client/swift/deepspeech_ios/deepspeech.h Normal file
View File

@ -0,0 +1,357 @@
#ifndef DEEPSPEECH_H
#define DEEPSPEECH_H
#ifdef __cplusplus
extern "C" {
#endif
#ifndef SWIG
#if defined _MSC_VER
#define DEEPSPEECH_EXPORT __declspec(dllexport)
#else
#define DEEPSPEECH_EXPORT __attribute__ ((visibility("default")))
#endif /*End of _MSC_VER*/
#else
#define DEEPSPEECH_EXPORT
#endif
typedef struct ModelState ModelState;
typedef struct StreamingState StreamingState;
/**
* @brief Stores text of an individual token, along with its timing information
*/
typedef struct TokenMetadata {
/** The text corresponding to this token */
const char* const text;
/** Position of the token in units of 20ms */
const unsigned int timestep;
/** Position of the token in seconds */
const float start_time;
} TokenMetadata;
/**
* @brief A single transcript computed by the model, including a confidence
* value and the metadata for its constituent tokens.
*/
typedef struct CandidateTranscript {
/** Array of TokenMetadata objects */
const TokenMetadata* const tokens;
/** Size of the tokens array */
const unsigned int num_tokens;
/** Approximated confidence value for this transcript. This is roughly the
* sum of the acoustic model logit values for each timestep/character that
* contributed to the creation of this transcript.
*/
const double confidence;
} CandidateTranscript;
/**
* @brief An array of CandidateTranscript objects computed by the model.
*/
typedef struct Metadata {
/** Array of CandidateTranscript objects */
const CandidateTranscript* const transcripts;
/** Size of the transcripts array */
const unsigned int num_transcripts;
} Metadata;
// sphinx-doc: error_code_listing_start
#define DS_FOR_EACH_ERROR(APPLY) \
APPLY(DS_ERR_OK, 0x0000, "No error.") \
APPLY(DS_ERR_NO_MODEL, 0x1000, "Missing model information.") \
APPLY(DS_ERR_INVALID_ALPHABET, 0x2000, "Invalid alphabet embedded in model. (Data corruption?)") \
APPLY(DS_ERR_INVALID_SHAPE, 0x2001, "Invalid model shape.") \
APPLY(DS_ERR_INVALID_SCORER, 0x2002, "Invalid scorer file.") \
APPLY(DS_ERR_MODEL_INCOMPATIBLE, 0x2003, "Incompatible model.") \
APPLY(DS_ERR_SCORER_NOT_ENABLED, 0x2004, "External scorer is not enabled.") \
APPLY(DS_ERR_SCORER_UNREADABLE, 0x2005, "Could not read scorer file.") \
APPLY(DS_ERR_SCORER_INVALID_LM, 0x2006, "Could not recognize language model header in scorer.") \
APPLY(DS_ERR_SCORER_NO_TRIE, 0x2007, "Reached end of scorer file before loading vocabulary trie.") \
APPLY(DS_ERR_SCORER_INVALID_TRIE, 0x2008, "Invalid magic in trie header.") \
APPLY(DS_ERR_SCORER_VERSION_MISMATCH, 0x2009, "Scorer file version does not match expected version.") \
APPLY(DS_ERR_FAIL_INIT_MMAP, 0x3000, "Failed to initialize memory mapped model.") \
APPLY(DS_ERR_FAIL_INIT_SESS, 0x3001, "Failed to initialize the session.") \
APPLY(DS_ERR_FAIL_INTERPRETER, 0x3002, "Interpreter failed.") \
APPLY(DS_ERR_FAIL_RUN_SESS, 0x3003, "Failed to run the session.") \
APPLY(DS_ERR_FAIL_CREATE_STREAM, 0x3004, "Error creating the stream.") \
APPLY(DS_ERR_FAIL_READ_PROTOBUF, 0x3005, "Error reading the proto buffer model file.") \
APPLY(DS_ERR_FAIL_CREATE_SESS, 0x3006, "Failed to create session.") \
APPLY(DS_ERR_FAIL_CREATE_MODEL, 0x3007, "Could not allocate model state.")
// sphinx-doc: error_code_listing_end
enum DeepSpeech_Error_Codes
{
#define DEFINE(NAME, VALUE, DESC) NAME = VALUE,
DS_FOR_EACH_ERROR(DEFINE)
#undef DEFINE
};
/**
* @brief An object providing an interface to a trained DeepSpeech model.
*
* @param aModelPath The path to the frozen model graph.
* @param[out] retval a ModelState pointer
*
* @return Zero on success, non-zero on failure.
*/
DEEPSPEECH_EXPORT
int DS_CreateModel(const char* aModelPath,
ModelState** retval);
/**
* @brief Get beam width value used by the model. If {@link DS_SetModelBeamWidth}
* was not called before, will return the default value loaded from the
* model file.
*
* @param aCtx A ModelState pointer created with {@link DS_CreateModel}.
*
* @return Beam width value used by the model.
*/
DEEPSPEECH_EXPORT
unsigned int DS_GetModelBeamWidth(const ModelState* aCtx);
/**
* @brief Set beam width value used by the model.
*
* @param aCtx A ModelState pointer created with {@link DS_CreateModel}.
* @param aBeamWidth The beam width used by the model. A larger beam width value
* generates better results at the cost of decoding time.
*
* @return Zero on success, non-zero on failure.
*/
DEEPSPEECH_EXPORT
int DS_SetModelBeamWidth(ModelState* aCtx,
unsigned int aBeamWidth);
/**
* @brief Return the sample rate expected by a model.
*
* @param aCtx A ModelState pointer created with {@link DS_CreateModel}.
*
* @return Sample rate expected by the model for its input.
*/
DEEPSPEECH_EXPORT
int DS_GetModelSampleRate(const ModelState* aCtx);
/**
* @brief Frees associated resources and destroys model object.
*/
DEEPSPEECH_EXPORT
void DS_FreeModel(ModelState* ctx);
/**
* @brief Enable decoding using an external scorer.
*
* @param aCtx The ModelState pointer for the model being changed.
* @param aScorerPath The path to the external scorer file.
*
* @return Zero on success, non-zero on failure (invalid arguments).
*/
DEEPSPEECH_EXPORT
int DS_EnableExternalScorer(ModelState* aCtx,
const char* aScorerPath);
/**
* @brief Disable decoding using an external scorer.
*
* @param aCtx The ModelState pointer for the model being changed.
*
* @return Zero on success, non-zero on failure.
*/
DEEPSPEECH_EXPORT
int DS_DisableExternalScorer(ModelState* aCtx);
/**
* @brief Set hyperparameters alpha and beta of the external scorer.
*
* @param aCtx The ModelState pointer for the model being changed.
* @param aAlpha The alpha hyperparameter of the decoder. Language model weight.
* @param aLMBeta The beta hyperparameter of the decoder. Word insertion weight.
*
* @return Zero on success, non-zero on failure.
*/
DEEPSPEECH_EXPORT
int DS_SetScorerAlphaBeta(ModelState* aCtx,
float aAlpha,
float aBeta);
/**
* @brief Use the DeepSpeech model to convert speech to text.
*
* @param aCtx The ModelState pointer for the model to use.
* @param aBuffer A 16-bit, mono raw audio signal at the appropriate
* sample rate (matching what the model was trained on).
* @param aBufferSize The number of samples in the audio signal.
*
* @return The STT result. The user is responsible for freeing the string using
* {@link DS_FreeString()}. Returns NULL on error.
*/
DEEPSPEECH_EXPORT
char* DS_SpeechToText(ModelState* aCtx,
const short* aBuffer,
unsigned int aBufferSize);
/**
* @brief Use the DeepSpeech model to convert speech to text and output results
* including metadata.
*
* @param aCtx The ModelState pointer for the model to use.
* @param aBuffer A 16-bit, mono raw audio signal at the appropriate
* sample rate (matching what the model was trained on).
* @param aBufferSize The number of samples in the audio signal.
* @param aNumResults The maximum number of CandidateTranscript structs to return. Returned value might be smaller than this.
*
* @return Metadata struct containing multiple CandidateTranscript structs. Each
* transcript has per-token metadata including timing information. The
* user is responsible for freeing Metadata by calling {@link DS_FreeMetadata()}.
* Returns NULL on error.
*/
DEEPSPEECH_EXPORT
Metadata* DS_SpeechToTextWithMetadata(ModelState* aCtx,
const short* aBuffer,
unsigned int aBufferSize,
unsigned int aNumResults);
/**
* @brief Create a new streaming inference state. The streaming state returned
* by this function can then be passed to {@link DS_FeedAudioContent()}
* and {@link DS_FinishStream()}.
*
* @param aCtx The ModelState pointer for the model to use.
* @param[out] retval an opaque pointer that represents the streaming state. Can
* be NULL if an error occurs.
*
* @return Zero for success, non-zero on failure.
*/
DEEPSPEECH_EXPORT
int DS_CreateStream(ModelState* aCtx,
StreamingState** retval);
/**
* @brief Feed audio samples to an ongoing streaming inference.
*
* @param aSctx A streaming state pointer returned by {@link DS_CreateStream()}.
* @param aBuffer An array of 16-bit, mono raw audio samples at the
* appropriate sample rate (matching what the model was trained on).
* @param aBufferSize The number of samples in @p aBuffer.
*/
DEEPSPEECH_EXPORT
void DS_FeedAudioContent(StreamingState* aSctx,
const short* aBuffer,
unsigned int aBufferSize);
/**
* @brief Compute the intermediate decoding of an ongoing streaming inference.
*
* @param aSctx A streaming state pointer returned by {@link DS_CreateStream()}.
*
* @return The STT intermediate result. The user is responsible for freeing the
* string using {@link DS_FreeString()}.
*/
DEEPSPEECH_EXPORT
char* DS_IntermediateDecode(const StreamingState* aSctx);
/**
* @brief Compute the intermediate decoding of an ongoing streaming inference,
* return results including metadata.
*
* @param aSctx A streaming state pointer returned by {@link DS_CreateStream()}.
* @param aNumResults The number of candidate transcripts to return.
*
* @return Metadata struct containing multiple candidate transcripts. Each transcript
* has per-token metadata including timing information. The user is
* responsible for freeing Metadata by calling {@link DS_FreeMetadata()}.
* Returns NULL on error.
*/
DEEPSPEECH_EXPORT
Metadata* DS_IntermediateDecodeWithMetadata(const StreamingState* aSctx,
unsigned int aNumResults);
/**
* @brief Compute the final decoding of an ongoing streaming inference and return
* the result. Signals the end of an ongoing streaming inference.
*
* @param aSctx A streaming state pointer returned by {@link DS_CreateStream()}.
*
* @return The STT result. The user is responsible for freeing the string using
* {@link DS_FreeString()}.
*
* @note This method will free the state pointer (@p aSctx).
*/
DEEPSPEECH_EXPORT
char* DS_FinishStream(StreamingState* aSctx);
/**
* @brief Compute the final decoding of an ongoing streaming inference and return
* results including metadata. Signals the end of an ongoing streaming
* inference.
*
* @param aSctx A streaming state pointer returned by {@link DS_CreateStream()}.
* @param aNumResults The number of candidate transcripts to return.
*
* @return Metadata struct containing multiple candidate transcripts. Each transcript
* has per-token metadata including timing information. The user is
* responsible for freeing Metadata by calling {@link DS_FreeMetadata()}.
* Returns NULL on error.
*
* @note This method will free the state pointer (@p aSctx).
*/
DEEPSPEECH_EXPORT
Metadata* DS_FinishStreamWithMetadata(StreamingState* aSctx,
unsigned int aNumResults);
/**
* @brief 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.
*
* @param aSctx A streaming state pointer returned by {@link DS_CreateStream()}.
*
* @note This method will free the state pointer (@p aSctx).
*/
DEEPSPEECH_EXPORT
void DS_FreeStream(StreamingState* aSctx);
/**
* @brief Free memory allocated for metadata information.
*/
DEEPSPEECH_EXPORT
void DS_FreeMetadata(Metadata* m);
/**
* @brief Free a char* string returned by the DeepSpeech API.
*/
DEEPSPEECH_EXPORT
void DS_FreeString(char* str);
/**
* @brief Returns the version of this library. The returned version is a semantic
* version (SemVer 2.0.0). The string returned must be freed with {@link DS_FreeString()}.
*
* @return The version string.
*/
DEEPSPEECH_EXPORT
char* DS_Version();
/**
* @brief Returns a textual description corresponding to an error code.
* The string returned must be freed with @{link DS_FreeString()}.
*
* @return The error description.
*/
DEEPSPEECH_EXPORT
char* DS_ErrorCodeToErrorMessage(int aErrorCode);
#undef DEEPSPEECH_EXPORT
#ifdef __cplusplus
}
#endif
#endif /* DEEPSPEECH_H */

13
native_client/swift/deepspeech_ios/deepspeech_ios.h Normal file
View File

@ -0,0 +1,13 @@
//
// deepspeech_ios.h
// deepspeech_ios
//
// Created by Reuben Morais on 14.06.20.
// Copyright © 2020 Mozilla. All rights reserved.
//
#import <Foundation/Foundation.h>
// In this header, you should import all the public headers of your framework using statements like #import <deepspeech_ios/PublicHeader.h>

12
native_client/swift/deepspeech_ios/deepspeech_ios.modulemap Normal file
View File

@ -0,0 +1,12 @@
framework module deepspeech_ios {
umbrella header "deepspeech_ios.h"
export *
module * { export * }
explicit module libdeepspeech_Private {
header "deepspeech.h"
export *
link "deepspeech"
}
}

637
native_client/swift/deepspeech_ios_test/deepspeech_ios_test.xcodeproj/project.pbxproj Normal file
View File

@ -0,0 +1,637 @@
// !$*UTF8*$!
{
archiveVersion = 1;
classes = {
};
objectVersion = 50;
objects = {
/* Begin PBXBuildFile section */
507CD3A124B61FE400409BBB /* deepspeech_ios.framework in Frameworks */ = {isa = PBXBuildFile; fileRef = 507CD3A024B61FE400409BBB /* deepspeech_ios.framework */; };
507CD3A324B61FEB00409BBB /* libdeepspeech.so in Frameworks */ = {isa = PBXBuildFile; fileRef = 507CD3A224B61FEA00409BBB /* libdeepspeech.so */; };
507CD3A424B61FFC00409BBB /* libdeepspeech.so in Embed Frameworks */ = {isa = PBXBuildFile; fileRef = 507CD3A224B61FEA00409BBB /* libdeepspeech.so */; settings = {ATTRIBUTES = (CodeSignOnCopy, ); }; };
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 */; };
50F787F92497683A00D52237 /* Assets.xcassets in Resources */ = {isa = PBXBuildFile; fileRef = 50F787F82497683A00D52237 /* Assets.xcassets */; };
50F787FC2497683A00D52237 /* Preview Assets.xcassets in Resources */ = {isa = PBXBuildFile; fileRef = 50F787FB2497683A00D52237 /* Preview Assets.xcassets */; };
50F787FF2497683A00D52237 /* LaunchScreen.storyboard in Resources */ = {isa = PBXBuildFile; fileRef = 50F787FD2497683A00D52237 /* LaunchScreen.storyboard */; };
50F7880A2497683A00D52237 /* deepspeech_ios_testTests.swift in Sources */ = {isa = PBXBuildFile; fileRef = 50F788092497683A00D52237 /* deepspeech_ios_testTests.swift */; };
50F788152497683A00D52237 /* deepspeech_ios_testUITests.swift in Sources */ = {isa = PBXBuildFile; fileRef = 50F788142497683A00D52237 /* deepspeech_ios_testUITests.swift */; };
/* End PBXBuildFile section */
/* Begin PBXContainerItemProxy section */
50F788062497683A00D52237 /* PBXContainerItemProxy */ = {
isa = PBXContainerItemProxy;
containerPortal = 50F787E72497683900D52237 /* Project object */;
proxyType = 1;
remoteGlobalIDString = 50F787EE2497683900D52237;
remoteInfo = deepspeech_ios_test;
};
50F788112497683A00D52237 /* PBXContainerItemProxy */ = {
isa = PBXContainerItemProxy;
containerPortal = 50F787E72497683900D52237 /* Project object */;
proxyType = 1;
remoteGlobalIDString = 50F787EE2497683900D52237;
remoteInfo = deepspeech_ios_test;
};
/* End PBXContainerItemProxy section */
/* Begin PBXCopyFilesBuildPhase section */
50F2B10E2498EB59007CD876 /* Embed Frameworks */ = {
isa = PBXCopyFilesBuildPhase;
buildActionMask = 2147483647;
dstPath = "";
dstSubfolderSpec = 10;
files = (
507CD3A424B61FFC00409BBB /* libdeepspeech.so in Embed Frameworks */,
);
name = "Embed Frameworks";
runOnlyForDeploymentPostprocessing = 0;
};
/* End PBXCopyFilesBuildPhase section */
/* Begin PBXFileReference section */
507CD3A024B61FE400409BBB /* deepspeech_ios.framework */ = {isa = PBXFileReference; explicitFileType = wrapper.framework; path = deepspeech_ios.framework; sourceTree = BUILT_PRODUCTS_DIR; };
507CD3A224B61FEA00409BBB /* libdeepspeech.so */ = {isa = PBXFileReference; lastKnownFileType = "compiled.mach-o.dylib"; name = libdeepspeech.so; path = ../libdeepspeech.so; sourceTree = "<group>"; };
50F787EF2497683900D52237 /* deepspeech_ios_test.app */ = {isa = PBXFileReference; explicitFileType = wrapper.application; includeInIndex = 0; path = deepspeech_ios_test.app; sourceTree = BUILT_PRODUCTS_DIR; };
50F787F22497683900D52237 /* AppDelegate.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = AppDelegate.swift; sourceTree = "<group>"; };
50F787F42497683900D52237 /* SceneDelegate.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = SceneDelegate.swift; sourceTree = "<group>"; };
50F787F62497683900D52237 /* ContentView.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = ContentView.swift; sourceTree = "<group>"; };
50F787F82497683A00D52237 /* Assets.xcassets */ = {isa = PBXFileReference; lastKnownFileType = folder.assetcatalog; path = Assets.xcassets; sourceTree = "<group>"; };
50F787FB2497683A00D52237 /* Preview Assets.xcassets */ = {isa = PBXFileReference; lastKnownFileType = folder.assetcatalog; path = "Preview Assets.xcassets"; sourceTree = "<group>"; };
50F787FE2497683A00D52237 /* Base */ = {isa = PBXFileReference; lastKnownFileType = file.storyboard; name = Base; path = Base.lproj/LaunchScreen.storyboard; sourceTree = "<group>"; };
50F788002497683A00D52237 /* Info.plist */ = {isa = PBXFileReference; lastKnownFileType = text.plist.xml; path = Info.plist; sourceTree = "<group>"; };
50F788052497683A00D52237 /* deepspeech_ios_testTests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = deepspeech_ios_testTests.xctest; sourceTree = BUILT_PRODUCTS_DIR; };
50F788092497683A00D52237 /* deepspeech_ios_testTests.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = deepspeech_ios_testTests.swift; sourceTree = "<group>"; };
50F7880B2497683A00D52237 /* Info.plist */ = {isa = PBXFileReference; lastKnownFileType = text.plist.xml; path = Info.plist; sourceTree = "<group>"; };
50F788102497683A00D52237 /* deepspeech_ios_testUITests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = deepspeech_ios_testUITests.xctest; sourceTree = BUILT_PRODUCTS_DIR; };
50F788142497683A00D52237 /* deepspeech_ios_testUITests.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = deepspeech_ios_testUITests.swift; sourceTree = "<group>"; };
50F788162497683A00D52237 /* Info.plist */ = {isa = PBXFileReference; lastKnownFileType = text.plist.xml; path = Info.plist; sourceTree = "<group>"; };
/* End PBXFileReference section */
/* Begin PBXFrameworksBuildPhase section */
50F787EC2497683900D52237 /* Frameworks */ = {
isa = PBXFrameworksBuildPhase;
buildActionMask = 2147483647;
files = (
507CD3A324B61FEB00409BBB /* libdeepspeech.so in Frameworks */,
507CD3A124B61FE400409BBB /* deepspeech_ios.framework in Frameworks */,
);
runOnlyForDeploymentPostprocessing = 0;
};
50F788022497683A00D52237 /* Frameworks */ = {
isa = PBXFrameworksBuildPhase;
buildActionMask = 2147483647;
files = (
);
runOnlyForDeploymentPostprocessing = 0;
};
50F7880D2497683A00D52237 /* Frameworks */ = {
isa = PBXFrameworksBuildPhase;
buildActionMask = 2147483647;
files = (
);
runOnlyForDeploymentPostprocessing = 0;
};
/* End PBXFrameworksBuildPhase section */
/* Begin PBXGroup section */
50F2B0FC2498D6C7007CD876 /* Frameworks */ = {
isa = PBXGroup;
children = (
507CD3A224B61FEA00409BBB /* libdeepspeech.so */,
507CD3A024B61FE400409BBB /* deepspeech_ios.framework */,
);
name = Frameworks;
sourceTree = "<group>";
};
50F787E62497683900D52237 = {
isa = PBXGroup;
children = (
50F787F12497683900D52237 /* deepspeech_ios_test */,
50F788082497683A00D52237 /* deepspeech_ios_testTests */,
50F788132497683A00D52237 /* deepspeech_ios_testUITests */,
50F787F02497683900D52237 /* Products */,
50F2B0FC2498D6C7007CD876 /* Frameworks */,
);
sourceTree = "<group>";
};
50F787F02497683900D52237 /* Products */ = {
isa = PBXGroup;
children = (
50F787EF2497683900D52237 /* deepspeech_ios_test.app */,
50F788052497683A00D52237 /* deepspeech_ios_testTests.xctest */,
50F788102497683A00D52237 /* deepspeech_ios_testUITests.xctest */,
);
name = Products;
sourceTree = "<group>";
};
50F787F12497683900D52237 /* deepspeech_ios_test */ = {
isa = PBXGroup;
children = (
50F787F22497683900D52237 /* AppDelegate.swift */,
50F787F42497683900D52237 /* SceneDelegate.swift */,
50F787F62497683900D52237 /* ContentView.swift */,
50F787F82497683A00D52237 /* Assets.xcassets */,
50F787FD2497683A00D52237 /* LaunchScreen.storyboard */,
50F788002497683A00D52237 /* Info.plist */,
50F787FA2497683A00D52237 /* Preview Content */,
);
path = deepspeech_ios_test;
sourceTree = "<group>";
};
50F787FA2497683A00D52237 /* Preview Content */ = {
isa = PBXGroup;
children = (
50F787FB2497683A00D52237 /* Preview Assets.xcassets */,
);
path = "Preview Content";
sourceTree = "<group>";
};
50F788082497683A00D52237 /* deepspeech_ios_testTests */ = {
isa = PBXGroup;
children = (
50F788092497683A00D52237 /* deepspeech_ios_testTests.swift */,
50F7880B2497683A00D52237 /* Info.plist */,
);
path = deepspeech_ios_testTests;
sourceTree = "<group>";
};
50F788132497683A00D52237 /* deepspeech_ios_testUITests */ = {
isa = PBXGroup;
children = (
50F788142497683A00D52237 /* deepspeech_ios_testUITests.swift */,
50F788162497683A00D52237 /* Info.plist */,
);
path = deepspeech_ios_testUITests;
sourceTree = "<group>";
};
/* End PBXGroup section */
/* Begin PBXNativeTarget section */
50F787EE2497683900D52237 /* deepspeech_ios_test */ = {
isa = PBXNativeTarget;
buildConfigurationList = 50F788192497683A00D52237 /* Build configuration list for PBXNativeTarget "deepspeech_ios_test" */;
buildPhases = (
50F787EB2497683900D52237 /* Sources */,
50F787EC2497683900D52237 /* Frameworks */,
50F787ED2497683900D52237 /* Resources */,
50F2B10E2498EB59007CD876 /* Embed Frameworks */,
);
buildRules = (
);
dependencies = (
);
name = deepspeech_ios_test;
productName = deepspeech_ios_test;
productReference = 50F787EF2497683900D52237 /* deepspeech_ios_test.app */;
productType = "com.apple.product-type.application";
};
50F788042497683A00D52237 /* deepspeech_ios_testTests */ = {
isa = PBXNativeTarget;
buildConfigurationList = 50F7881C2497683A00D52237 /* Build configuration list for PBXNativeTarget "deepspeech_ios_testTests" */;
buildPhases = (
50F788012497683A00D52237 /* Sources */,
50F788022497683A00D52237 /* Frameworks */,
50F788032497683A00D52237 /* Resources */,
);
buildRules = (
);
dependencies = (
50F788072497683A00D52237 /* PBXTargetDependency */,
);
name = deepspeech_ios_testTests;
productName = deepspeech_ios_testTests;
productReference = 50F788052497683A00D52237 /* deepspeech_ios_testTests.xctest */;
productType = "com.apple.product-type.bundle.unit-test";
};
50F7880F2497683A00D52237 /* deepspeech_ios_testUITests */ = {
isa = PBXNativeTarget;
buildConfigurationList = 50F7881F2497683A00D52237 /* Build configuration list for PBXNativeTarget "deepspeech_ios_testUITests" */;
buildPhases = (
50F7880C2497683A00D52237 /* Sources */,
50F7880D2497683A00D52237 /* Frameworks */,
50F7880E2497683A00D52237 /* Resources */,
);
buildRules = (
);
dependencies = (
50F788122497683A00D52237 /* PBXTargetDependency */,
);
name = deepspeech_ios_testUITests;
productName = deepspeech_ios_testUITests;
productReference = 50F788102497683A00D52237 /* deepspeech_ios_testUITests.xctest */;
productType = "com.apple.product-type.bundle.ui-testing";
};
/* End PBXNativeTarget section */
/* Begin PBXProject section */
50F787E72497683900D52237 /* Project object */ = {
isa = PBXProject;
attributes = {
LastSwiftUpdateCheck = 1150;
LastUpgradeCheck = 1150;
ORGANIZATIONNAME = Mozilla;
TargetAttributes = {
50F787EE2497683900D52237 = {
CreatedOnToolsVersion = 11.5;
};
50F788042497683A00D52237 = {
CreatedOnToolsVersion = 11.5;
TestTargetID = 50F787EE2497683900D52237;
};
50F7880F2497683A00D52237 = {
CreatedOnToolsVersion = 11.5;
TestTargetID = 50F787EE2497683900D52237;
};
};
};
buildConfigurationList = 50F787EA2497683900D52237 /* Build configuration list for PBXProject "deepspeech_ios_test" */;
compatibilityVersion = "Xcode 9.3";
developmentRegion = en;
hasScannedForEncodings = 0;
knownRegions = (
en,
Base,
);
mainGroup = 50F787E62497683900D52237;
productRefGroup = 50F787F02497683900D52237 /* Products */;
projectDirPath = "";
projectRoot = "";
targets = (
50F787EE2497683900D52237 /* deepspeech_ios_test */,
50F788042497683A00D52237 /* deepspeech_ios_testTests */,
50F7880F2497683A00D52237 /* deepspeech_ios_testUITests */,
);
};
/* End PBXProject section */
/* Begin PBXResourcesBuildPhase section */
50F787ED2497683900D52237 /* Resources */ = {
isa = PBXResourcesBuildPhase;
buildActionMask = 2147483647;
files = (
50F787FF2497683A00D52237 /* LaunchScreen.storyboard in Resources */,
50F787FC2497683A00D52237 /* Preview Assets.xcassets in Resources */,
50F787F92497683A00D52237 /* Assets.xcassets in Resources */,
);
runOnlyForDeploymentPostprocessing = 0;
};
50F788032497683A00D52237 /* Resources */ = {
isa = PBXResourcesBuildPhase;
buildActionMask = 2147483647;
files = (
);
runOnlyForDeploymentPostprocessing = 0;
};
50F7880E2497683A00D52237 /* Resources */ = {
isa = PBXResourcesBuildPhase;
buildActionMask = 2147483647;
files = (
);
runOnlyForDeploymentPostprocessing = 0;
};
/* End PBXResourcesBuildPhase section */
/* Begin PBXSourcesBuildPhase section */
50F787EB2497683900D52237 /* Sources */ = {
isa = PBXSourcesBuildPhase;
buildActionMask = 2147483647;
files = (
50F787F32497683900D52237 /* AppDelegate.swift in Sources */,
50F787F52497683900D52237 /* SceneDelegate.swift in Sources */,
50F787F72497683900D52237 /* ContentView.swift in Sources */,
);
runOnlyForDeploymentPostprocessing = 0;
};
50F788012497683A00D52237 /* Sources */ = {
isa = PBXSourcesBuildPhase;
buildActionMask = 2147483647;
files = (
50F7880A2497683A00D52237 /* deepspeech_ios_testTests.swift in Sources */,
);
runOnlyForDeploymentPostprocessing = 0;
};
50F7880C2497683A00D52237 /* Sources */ = {
isa = PBXSourcesBuildPhase;
buildActionMask = 2147483647;
files = (
50F788152497683A00D52237 /* deepspeech_ios_testUITests.swift in Sources */,
);
runOnlyForDeploymentPostprocessing = 0;
};
/* End PBXSourcesBuildPhase section */
/* Begin PBXTargetDependency section */
50F788072497683A00D52237 /* PBXTargetDependency */ = {
isa = PBXTargetDependency;
target = 50F787EE2497683900D52237 /* deepspeech_ios_test */;
targetProxy = 50F788062497683A00D52237 /* PBXContainerItemProxy */;
};
50F788122497683A00D52237 /* PBXTargetDependency */ = {
isa = PBXTargetDependency;
target = 50F787EE2497683900D52237 /* deepspeech_ios_test */;
targetProxy = 50F788112497683A00D52237 /* PBXContainerItemProxy */;
};
/* End PBXTargetDependency section */
/* Begin PBXVariantGroup section */
50F787FD2497683A00D52237 /* LaunchScreen.storyboard */ = {
isa = PBXVariantGroup;
children = (
50F787FE2497683A00D52237 /* Base */,
);
name = LaunchScreen.storyboard;
sourceTree = "<group>";
};
/* End PBXVariantGroup section */
/* Begin XCBuildConfiguration section */
50F788172497683A00D52237 /* Debug */ = {
isa = XCBuildConfiguration;
buildSettings = {
ALWAYS_SEARCH_USER_PATHS = NO;
CLANG_ANALYZER_NONNULL = YES;
CLANG_ANALYZER_NUMBER_OBJECT_CONVERSION = YES_AGGRESSIVE;
CLANG_CXX_LANGUAGE_STANDARD = "gnu++14";
CLANG_CXX_LIBRARY = "libc++";
CLANG_ENABLE_MODULES = YES;
CLANG_ENABLE_OBJC_ARC = YES;
CLANG_ENABLE_OBJC_WEAK = YES;
CLANG_WARN_BLOCK_CAPTURE_AUTORELEASING = YES;
CLANG_WARN_BOOL_CONVERSION = YES;
CLANG_WARN_COMMA = YES;
CLANG_WARN_CONSTANT_CONVERSION = YES;
CLANG_WARN_DEPRECATED_OBJC_IMPLEMENTATIONS = YES;
CLANG_WARN_DIRECT_OBJC_ISA_USAGE = YES_ERROR;
CLANG_WARN_DOCUMENTATION_COMMENTS = YES;
CLANG_WARN_EMPTY_BODY = YES;
CLANG_WARN_ENUM_CONVERSION = YES;
CLANG_WARN_INFINITE_RECURSION = YES;
CLANG_WARN_INT_CONVERSION = YES;
CLANG_WARN_NON_LITERAL_NULL_CONVERSION = YES;
CLANG_WARN_OBJC_IMPLICIT_RETAIN_SELF = YES;
CLANG_WARN_OBJC_LITERAL_CONVERSION = YES;
CLANG_WARN_OBJC_ROOT_CLASS = YES_ERROR;
CLANG_WARN_RANGE_LOOP_ANALYSIS = YES;
CLANG_WARN_STRICT_PROTOTYPES = YES;
CLANG_WARN_SUSPICIOUS_MOVE = YES;
CLANG_WARN_UNGUARDED_AVAILABILITY = YES_AGGRESSIVE;
CLANG_WARN_UNREACHABLE_CODE = YES;
CLANG_WARN__DUPLICATE_METHOD_MATCH = YES;
COPY_PHASE_STRIP = NO;
DEBUG_INFORMATION_FORMAT = dwarf;
ENABLE_STRICT_OBJC_MSGSEND = YES;
ENABLE_TESTABILITY = YES;
GCC_C_LANGUAGE_STANDARD = gnu11;
GCC_DYNAMIC_NO_PIC = NO;
GCC_NO_COMMON_BLOCKS = YES;
GCC_OPTIMIZATION_LEVEL = 0;
GCC_PREPROCESSOR_DEFINITIONS = (
"DEBUG=1",
"$(inherited)",
);
GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
GCC_WARN_ABOUT_RETURN_TYPE = YES_ERROR;
GCC_WARN_UNDECLARED_SELECTOR = YES;
GCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE;
GCC_WARN_UNUSED_FUNCTION = YES;
GCC_WARN_UNUSED_VARIABLE = YES;
IPHONEOS_DEPLOYMENT_TARGET = 13.5;
MTL_ENABLE_DEBUG_INFO = INCLUDE_SOURCE;
MTL_FAST_MATH = YES;
ONLY_ACTIVE_ARCH = YES;
SDKROOT = iphoneos;
SWIFT_ACTIVE_COMPILATION_CONDITIONS = DEBUG;
SWIFT_OPTIMIZATION_LEVEL = "-Onone";
};
name = Debug;
};
50F788182497683A00D52237 /* Release */ = {
isa = XCBuildConfiguration;
buildSettings = {
ALWAYS_SEARCH_USER_PATHS = NO;
CLANG_ANALYZER_NONNULL = YES;
CLANG_ANALYZER_NUMBER_OBJECT_CONVERSION = YES_AGGRESSIVE;
CLANG_CXX_LANGUAGE_STANDARD = "gnu++14";
CLANG_CXX_LIBRARY = "libc++";
CLANG_ENABLE_MODULES = YES;
CLANG_ENABLE_OBJC_ARC = YES;
CLANG_ENABLE_OBJC_WEAK = YES;
CLANG_WARN_BLOCK_CAPTURE_AUTORELEASING = YES;
CLANG_WARN_BOOL_CONVERSION = YES;
CLANG_WARN_COMMA = YES;
CLANG_WARN_CONSTANT_CONVERSION = YES;
CLANG_WARN_DEPRECATED_OBJC_IMPLEMENTATIONS = YES;
CLANG_WARN_DIRECT_OBJC_ISA_USAGE = YES_ERROR;
CLANG_WARN_DOCUMENTATION_COMMENTS = YES;
CLANG_WARN_EMPTY_BODY = YES;
CLANG_WARN_ENUM_CONVERSION = YES;
CLANG_WARN_INFINITE_RECURSION = YES;
CLANG_WARN_INT_CONVERSION = YES;
CLANG_WARN_NON_LITERAL_NULL_CONVERSION = YES;
CLANG_WARN_OBJC_IMPLICIT_RETAIN_SELF = YES;
CLANG_WARN_OBJC_LITERAL_CONVERSION = YES;
CLANG_WARN_OBJC_ROOT_CLASS = YES_ERROR;
CLANG_WARN_RANGE_LOOP_ANALYSIS = YES;
CLANG_WARN_STRICT_PROTOTYPES = YES;
CLANG_WARN_SUSPICIOUS_MOVE = YES;
CLANG_WARN_UNGUARDED_AVAILABILITY = YES_AGGRESSIVE;
CLANG_WARN_UNREACHABLE_CODE = YES;
CLANG_WARN__DUPLICATE_METHOD_MATCH = YES;
COPY_PHASE_STRIP = NO;
DEBUG_INFORMATION_FORMAT = "dwarf-with-dsym";
ENABLE_NS_ASSERTIONS = NO;
ENABLE_STRICT_OBJC_MSGSEND = YES;
GCC_C_LANGUAGE_STANDARD = gnu11;
GCC_NO_COMMON_BLOCKS = YES;
GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
GCC_WARN_ABOUT_RETURN_TYPE = YES_ERROR;
GCC_WARN_UNDECLARED_SELECTOR = YES;
GCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE;
GCC_WARN_UNUSED_FUNCTION = YES;
GCC_WARN_UNUSED_VARIABLE = YES;
IPHONEOS_DEPLOYMENT_TARGET = 13.5;
MTL_ENABLE_DEBUG_INFO = NO;
MTL_FAST_MATH = YES;
SDKROOT = iphoneos;
SWIFT_COMPILATION_MODE = wholemodule;
SWIFT_OPTIMIZATION_LEVEL = "-O";
VALIDATE_PRODUCT = YES;
};
name = Release;
};
50F7881A2497683A00D52237 /* Debug */ = {
isa = XCBuildConfiguration;
buildSettings = {
ASSETCATALOG_COMPILER_APPICON_NAME = AppIcon;
CODE_SIGN_STYLE = Automatic;
DEVELOPMENT_ASSET_PATHS = "\"deepspeech_ios_test/Preview Content\"";
DEVELOPMENT_TEAM = AWCG9S27P7;
ENABLE_PREVIEWS = YES;
FRAMEWORK_SEARCH_PATHS = "$(PROJECT_DIR)";
INFOPLIST_FILE = deepspeech_ios_test/Info.plist;
LD_RUNPATH_SEARCH_PATHS = (
"$(inherited)",
"@executable_path/Frameworks",
);
LIBRARY_SEARCH_PATHS = (
"$(inherited)",
"$(PROJECT_DIR)",
);
PRODUCT_BUNDLE_IDENTIFIER = "org.mozilla.deepspeech-ios-test";
PRODUCT_NAME = "$(TARGET_NAME)";
SWIFT_VERSION = 5.0;
TARGETED_DEVICE_FAMILY = "1,2";
};
name = Debug;
};
50F7881B2497683A00D52237 /* Release */ = {
isa = XCBuildConfiguration;
buildSettings = {
ASSETCATALOG_COMPILER_APPICON_NAME = AppIcon;
CODE_SIGN_STYLE = Automatic;
DEVELOPMENT_ASSET_PATHS = "\"deepspeech_ios_test/Preview Content\"";
DEVELOPMENT_TEAM = AWCG9S27P7;
ENABLE_PREVIEWS = YES;
FRAMEWORK_SEARCH_PATHS = "$(PROJECT_DIR)";
INFOPLIST_FILE = deepspeech_ios_test/Info.plist;
LD_RUNPATH_SEARCH_PATHS = (
"$(inherited)",
"@executable_path/Frameworks",
);
LIBRARY_SEARCH_PATHS = (
"$(inherited)",
"$(PROJECT_DIR)",
);
PRODUCT_BUNDLE_IDENTIFIER = "org.mozilla.deepspeech-ios-test";
PRODUCT_NAME = "$(TARGET_NAME)";
SWIFT_VERSION = 5.0;
TARGETED_DEVICE_FAMILY = "1,2";
};
name = Release;
};
50F7881D2497683A00D52237 /* Debug */ = {
isa = XCBuildConfiguration;
buildSettings = {
ALWAYS_EMBED_SWIFT_STANDARD_LIBRARIES = YES;
BUNDLE_LOADER = "$(TEST_HOST)";
CODE_SIGN_STYLE = Automatic;
INFOPLIST_FILE = deepspeech_ios_testTests/Info.plist;
IPHONEOS_DEPLOYMENT_TARGET = 13.5;
LD_RUNPATH_SEARCH_PATHS = (
"$(inherited)",
"@executable_path/Frameworks",
"@loader_path/Frameworks",
);
PRODUCT_BUNDLE_IDENTIFIER = "org.mozilla.deepspeech-ios-testTests";
PRODUCT_NAME = "$(TARGET_NAME)";
SWIFT_VERSION = 5.0;
TARGETED_DEVICE_FAMILY = "1,2";
TEST_HOST = "$(BUILT_PRODUCTS_DIR)/deepspeech_ios_test.app/deepspeech_ios_test";
};
name = Debug;
};
50F7881E2497683A00D52237 /* Release */ = {
isa = XCBuildConfiguration;
buildSettings = {
ALWAYS_EMBED_SWIFT_STANDARD_LIBRARIES = YES;
BUNDLE_LOADER = "$(TEST_HOST)";
CODE_SIGN_STYLE = Automatic;
INFOPLIST_FILE = deepspeech_ios_testTests/Info.plist;
IPHONEOS_DEPLOYMENT_TARGET = 13.5;
LD_RUNPATH_SEARCH_PATHS = (
"$(inherited)",
"@executable_path/Frameworks",
"@loader_path/Frameworks",
);
PRODUCT_BUNDLE_IDENTIFIER = "org.mozilla.deepspeech-ios-testTests";
PRODUCT_NAME = "$(TARGET_NAME)";
SWIFT_VERSION = 5.0;
TARGETED_DEVICE_FAMILY = "1,2";
TEST_HOST = "$(BUILT_PRODUCTS_DIR)/deepspeech_ios_test.app/deepspeech_ios_test";
};
name = Release;
};
50F788202497683A00D52237 /* Debug */ = {
isa = XCBuildConfiguration;
buildSettings = {
ALWAYS_EMBED_SWIFT_STANDARD_LIBRARIES = YES;
CODE_SIGN_STYLE = Automatic;
INFOPLIST_FILE = deepspeech_ios_testUITests/Info.plist;
LD_RUNPATH_SEARCH_PATHS = (
"$(inherited)",
"@executable_path/Frameworks",
"@loader_path/Frameworks",
);
PRODUCT_BUNDLE_IDENTIFIER = "org.mozilla.deepspeech-ios-testUITests";
PRODUCT_NAME = "$(TARGET_NAME)";
SWIFT_VERSION = 5.0;
TARGETED_DEVICE_FAMILY = "1,2";
TEST_TARGET_NAME = deepspeech_ios_test;
};
name = Debug;
};
50F788212497683A00D52237 /* Release */ = {
isa = XCBuildConfiguration;
buildSettings = {
ALWAYS_EMBED_SWIFT_STANDARD_LIBRARIES = YES;
CODE_SIGN_STYLE = Automatic;
INFOPLIST_FILE = deepspeech_ios_testUITests/Info.plist;
LD_RUNPATH_SEARCH_PATHS = (
"$(inherited)",
"@executable_path/Frameworks",
"@loader_path/Frameworks",
);
PRODUCT_BUNDLE_IDENTIFIER = "org.mozilla.deepspeech-ios-testUITests";
PRODUCT_NAME = "$(TARGET_NAME)";
SWIFT_VERSION = 5.0;
TARGETED_DEVICE_FAMILY = "1,2";
TEST_TARGET_NAME = deepspeech_ios_test;
};
name = Release;
};
/* End XCBuildConfiguration section */
/* Begin XCConfigurationList section */
50F787EA2497683900D52237 /* Build configuration list for PBXProject "deepspeech_ios_test" */ = {
isa = XCConfigurationList;
buildConfigurations = (
50F788172497683A00D52237 /* Debug */,
50F788182497683A00D52237 /* Release */,
);
defaultConfigurationIsVisible = 0;
defaultConfigurationName = Release;
};
50F788192497683A00D52237 /* Build configuration list for PBXNativeTarget "deepspeech_ios_test" */ = {
isa = XCConfigurationList;
buildConfigurations = (
50F7881A2497683A00D52237 /* Debug */,
50F7881B2497683A00D52237 /* Release */,
);
defaultConfigurationIsVisible = 0;
defaultConfigurationName = Release;
};
50F7881C2497683A00D52237 /* Build configuration list for PBXNativeTarget "deepspeech_ios_testTests" */ = {
isa = XCConfigurationList;
buildConfigurations = (
50F7881D2497683A00D52237 /* Debug */,
50F7881E2497683A00D52237 /* Release */,
);
defaultConfigurationIsVisible = 0;
defaultConfigurationName = Release;
};
50F7881F2497683A00D52237 /* Build configuration list for PBXNativeTarget "deepspeech_ios_testUITests" */ = {
isa = XCConfigurationList;
buildConfigurations = (
50F788202497683A00D52237 /* Debug */,
50F788212497683A00D52237 /* Release */,
);
defaultConfigurationIsVisible = 0;
defaultConfigurationName = Release;
};
/* End XCConfigurationList section */
};
rootObject = 50F787E72497683900D52237 /* Project object */;
}

7
native_client/swift/deepspeech_ios_test/deepspeech_ios_test.xcodeproj/project.xcworkspace/contents.xcworkspacedata generated Normal file
View File

@ -0,0 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<Workspace
version = "1.0">
<FileRef
location = "self:deepspeech_ios_test.xcodeproj">
</FileRef>
</Workspace>

8
native_client/swift/deepspeech_ios_test/deepspeech_ios_test.xcodeproj/project.xcworkspace/xcshareddata/IDEWorkspaceChecks.plist Normal file
View File

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>IDEDidComputeMac32BitWarning</key>
<true/>
</dict>
</plist>

106
native_client/swift/deepspeech_ios_test/deepspeech_ios_test.xcodeproj/xcshareddata/xcschemes/deepspeech_ios_test.xcscheme Normal file
View File

@ -0,0 +1,106 @@
<?xml version="1.0" encoding="UTF-8"?>
<Scheme
LastUpgradeVersion = "1150"
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 = "deepspeech_ios_test.app"
BlueprintName = "deepspeech_ios_test"
ReferencedContainer = "container:deepspeech_ios_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 = "deepspeech_ios_testTests.xctest"
BlueprintName = "deepspeech_ios_testTests"
ReferencedContainer = "container:deepspeech_ios_test.xcodeproj">
</BuildableReference>
</TestableReference>
<TestableReference
skipped = "NO">
<BuildableReference
BuildableIdentifier = "primary"
BlueprintIdentifier = "50F7880F2497683A00D52237"
BuildableName = "deepspeech_ios_testUITests.xctest"
BlueprintName = "deepspeech_ios_testUITests"
ReferencedContainer = "container:deepspeech_ios_test.xcodeproj">
</BuildableReference>
</TestableReference>
</Testables>
</TestAction>
<LaunchAction
buildConfiguration = "Debug"
selectedDebuggerIdentifier = "Xcode.DebuggerFoundation.Debugger.LLDB"
selectedLauncherIdentifier = "Xcode.DebuggerFoundation.Launcher.LLDB"
enableAddressSanitizer = "YES"
launchStyle = "0"
useCustomWorkingDirectory = "NO"
ignoresPersistentStateOnLaunch = "NO"
debugDocumentVersioning = "YES"
debugServiceExtension = "internal"
allowLocationSimulation = "YES">
<BuildableProductRunnable
runnableDebuggingMode = "0">
<BuildableReference
BuildableIdentifier = "primary"
BlueprintIdentifier = "50F787EE2497683900D52237"
BuildableName = "deepspeech_ios_test.app"
BlueprintName = "deepspeech_ios_test"
ReferencedContainer = "container:deepspeech_ios_test.xcodeproj">
</BuildableReference>
</BuildableProductRunnable>
<AdditionalOptions>
<AdditionalOption
key = "NSZombieEnabled"
value = "YES"
isEnabled = "YES">
</AdditionalOption>
</AdditionalOptions>
</LaunchAction>
<ProfileAction
buildConfiguration = "Release"
shouldUseLaunchSchemeArgsEnv = "YES"
savedToolIdentifier = ""
useCustomWorkingDirectory = "NO"
debugDocumentVersioning = "YES">
<BuildableProductRunnable
runnableDebuggingMode = "0">
<BuildableReference
BuildableIdentifier = "primary"
BlueprintIdentifier = "50F787EE2497683900D52237"
BuildableName = "deepspeech_ios_test.app"
BlueprintName = "deepspeech_ios_test"
ReferencedContainer = "container:deepspeech_ios_test.xcodeproj">
</BuildableReference>
</BuildableProductRunnable>
</ProfileAction>
<AnalyzeAction
buildConfiguration = "Debug">
</AnalyzeAction>
<ArchiveAction
buildConfiguration = "Release"
revealArchiveInOrganizer = "YES">
</ArchiveAction>
</Scheme>

255
native_client/swift/deepspeech_ios_test/deepspeech_ios_test/AppDelegate.swift Normal file
View File

@ -0,0 +1,255 @@
//
// AppDelegate.swift
// deepspeech_ios_test
//
// Created by Reuben Morais on 15.06.20.
// Copyright © 2020 Mozilla. All rights reserved.
//
import UIKit
import Foundation
import AVFoundation
import AudioToolbox
import Accelerate
import deepspeech_ios
/// Holds audio information used for building waveforms
final class AudioContext {
/// The audio asset URL used to load the context
public let audioURL: URL
/// Total number of samples in loaded asset
public let totalSamples: Int
/// Loaded asset
public let asset: AVAsset
// Loaded assetTrack
public let assetTrack: AVAssetTrack
private init(audioURL: URL, totalSamples: Int, asset: AVAsset, assetTrack: AVAssetTrack) {
self.audioURL = audioURL
self.totalSamples = totalSamples
self.asset = asset
self.assetTrack = assetTrack
}
public static func load(fromAudioURL audioURL: URL, completionHandler: @escaping (_ audioContext: AudioContext?) -> ()) {
let asset = AVURLAsset(url: audioURL, options: [AVURLAssetPreferPreciseDurationAndTimingKey: NSNumber(value: true as Bool)])
guard let assetTrack = asset.tracks(withMediaType: AVMediaType.audio).first else {
fatalError("Couldn't load AVAssetTrack")
}
asset.loadValuesAsynchronously(forKeys: ["duration"]) {
var error: NSError?
let status = asset.statusOfValue(forKey: "duration", error: &error)
switch status {
case .loaded:
guard
let formatDescriptions = assetTrack.formatDescriptions as? [CMAudioFormatDescription],
let audioFormatDesc = formatDescriptions.first,
let asbd = CMAudioFormatDescriptionGetStreamBasicDescription(audioFormatDesc)
else { break }
let totalSamples = Int((asbd.pointee.mSampleRate) * Float64(asset.duration.value) / Float64(asset.duration.timescale))
let audioContext = AudioContext(audioURL: audioURL, totalSamples: totalSamples, asset: asset, assetTrack: assetTrack)
completionHandler(audioContext)
return
case .failed, .cancelled, .loading, .unknown:
print("Couldn't load asset: \(error?.localizedDescription ?? "Unknown error")")
}
completionHandler(nil)
}
}
}
func render(audioContext: AudioContext?, stream: DeepSpeechStream) {
guard let audioContext = audioContext else {
fatalError("Couldn't create the audioContext")
}
let sampleRange: CountableRange<Int> = 0..<audioContext.totalSamples
guard let reader = try? AVAssetReader(asset: audioContext.asset)
else {
fatalError("Couldn't initialize the AVAssetReader")
}
reader.timeRange = CMTimeRange(start: CMTime(value: Int64(sampleRange.lowerBound), timescale: audioContext.asset.duration.timescale),
duration: CMTime(value: Int64(sampleRange.count), timescale: audioContext.asset.duration.timescale))
let outputSettingsDict: [String : Any] = [
AVFormatIDKey: Int(kAudioFormatLinearPCM),
AVLinearPCMBitDepthKey: 16,
AVLinearPCMIsBigEndianKey: false,
AVLinearPCMIsFloatKey: false,
AVLinearPCMIsNonInterleaved: false
]
let readerOutput = AVAssetReaderTrackOutput(track: audioContext.assetTrack,
outputSettings: outputSettingsDict)
readerOutput.alwaysCopiesSampleData = false
reader.add(readerOutput)
var sampleBuffer = Data()
// 16-bit samples
reader.startReading()
defer { reader.cancelReading() }
while reader.status == .reading {
guard let readSampleBuffer = readerOutput.copyNextSampleBuffer(),
let readBuffer = CMSampleBufferGetDataBuffer(readSampleBuffer) else {
break
}
// Append audio sample buffer into our current sample buffer
var readBufferLength = 0
var readBufferPointer: UnsafeMutablePointer<Int8>?
CMBlockBufferGetDataPointer(readBuffer,
atOffset: 0,
lengthAtOffsetOut: &readBufferLength,
totalLengthOut: nil,
dataPointerOut: &readBufferPointer)
sampleBuffer.append(UnsafeBufferPointer(start: readBufferPointer, count: readBufferLength))
CMSampleBufferInvalidate(readSampleBuffer)
let totalSamples = sampleBuffer.count / MemoryLayout<Int16>.size
print("read \(totalSamples) samples")
sampleBuffer.withUnsafeBytes { (samples: UnsafeRawBufferPointer) in
let unsafeBufferPointer = samples.bindMemory(to: Int16.self)
stream.feedAudioContent(buffer: unsafeBufferPointer)
}
sampleBuffer.removeAll()
}
// if (reader.status == AVAssetReaderStatusFailed || reader.status == AVAssetReaderStatusUnknown)
guard reader.status == .completed else {
fatalError("Couldn't read the audio file")
}
}
func test(model: DeepSpeechModel, audioPath: String, completion: @escaping () -> ()) {
let url = URL(fileURLWithPath: audioPath)
//var format = AudioStreamBasicDescription.init()
//format.mSampleRate = 16000;
//format.mFormatID = kAudioFormatLinearPCM;
//format.mFormatFlags = kAudioFormatFlagIsSignedInteger | kAudioFormatFlagsNativeEndian | kAudioFormatFlagIsPacked;
//format.mBitsPerChannel = 16;
//format.mChannelsPerFrame = 1;
//format.mBytesPerFrame = format.mChannelsPerFrame * format.mBitsPerChannel / 8;
//format.mFramesPerPacket = 1;
//format.mBytesPerPacket = format.mFramesPerPacket * format.mBytesPerFrame;
//
//var file = Optional<ExtAudioFileRef>.init(nilLiteral: ());
//let status = ExtAudioFileCreateWithURL(url as CFURL,
// kAudioFileWAVEType,
// &format,
// nil,
// 0,
// &file)
//print("status: \(status)")
//let status2 = ExtAudioFileSetProperty(file!,
// kExtAudioFileProperty_ClientDataFormat,
// UInt32(MemoryLayout<AudioStreamBasicDescription>.size),
// &format)
//print("status: \(status2)")
//
//ExtAudioFileRead(file, <#T##ioNumberFrames: UnsafeMutablePointer<UInt32>##UnsafeMutablePointer<UInt32>#>, <#T##ioData: UnsafeMutablePointer<AudioBufferList>##UnsafeMutablePointer<AudioBufferList>#>)
let stream = try! model.createStream()
print("\(audioPath)")
let start = CFAbsoluteTimeGetCurrent()
AudioContext.load(fromAudioURL: url, completionHandler: { audioContext in
guard let audioContext = audioContext else {
fatalError("Couldn't create the audioContext")
}
render(audioContext: audioContext, stream: stream)
let result = stream.finishStream()
let end = CFAbsoluteTimeGetCurrent()
print("\"\(audioPath)\": \(end - start) - \(result)")
completion()
})
//let file = try! AVAudioFile(forReading: url)
//print("file length \(file.length)")
//let format = AVAudioFormat(commonFormat: .pcmFormatInt16, sampleRate: 16000, channels: 1, interleaved: false)!
//let stream = createStream(modelState: modelState)
//while file.framePosition < file.length {
// let pcmBuf = AVAudioPCMBuffer.init(pcmFormat: format, frameCapacity: 8 * 1024)! // arbitrary frameCapacity
// try! file.read(into: pcmBuf)
// if pcmBuf.frameLength == 0 {
// break
// }
// print("read \(pcmBuf.frameLength) frames into buffer")
// let rawPtr = pcmBuf.audioBufferList.pointee.mBuffers.mData!
// let ptr = rawPtr.bindMemory(to: Int16.self, capacity: Int(pcmBuf.frameLength))
// print("first few samples: \(ptr[0]) \(ptr[1]) \(ptr[2]) \(ptr[3]) ")
// DS_FeedAudioContent(stream, ptr, UInt32(pcmBuf.frameLength))
//}
//let result = DS_FinishStream(stream)
//return String.init(cString: result!)
}
@UIApplicationMain
class AppDelegate: UIResponder, UIApplicationDelegate {
func application(_ application: UIApplication, didFinishLaunchingWithOptions launchOptions: [UIApplication.LaunchOptionsKey: Any]?) -> Bool {
let model = try! DeepSpeechModel(modelPath: Bundle.main.path(forResource: "output_graph", ofType: "tflite")!)
try! model.enableExternalScorer(scorerPath: Bundle.main.path(forResource: "librispeech_en_utf8_nonpruned_o6", ofType: "scorer")!)
let files = [
"5639-40744-0008",
"1089-134686-0019",
"2094-142345-0053",
"8463-294825-0010",
"121-123852-0001",
"7021-79740-0008",
"6930-76324-0010",
"5105-28240-0001",
"1089-134691-0012",
"5142-33396-0027",
"260-123288-0004",
"6930-75918-0008",
"8463-294828-0005",
"61-70970-0002"
]
let serialQueue = DispatchQueue(label: "serialQueue")
let group = DispatchGroup()
group.enter()
serialQueue.async {
test(model: model, audioPath: Bundle.main.path(forResource: "1284-134647-0003", ofType: "wav")!) {
group.leave()
}
}
for path in files {
group.wait()
group.enter()
test(model: model, audioPath: Bundle.main.path(forResource: path, ofType: "wav")!) {
group.leave()
}
}
return true
}
// MARK: UISceneSession Lifecycle
func application(_ application: UIApplication, configurationForConnecting connectingSceneSession: UISceneSession, options: UIScene.ConnectionOptions) -> UISceneConfiguration {
// Called when a new scene session is being created.
// Use this method to select a configuration to create the new scene with.
return UISceneConfiguration(name: "Default Configuration", sessionRole: connectingSceneSession.role)
}
func application(_ application: UIApplication, didDiscardSceneSessions sceneSessions: Set<UISceneSession>) {
// Called when the user discards a scene session.
// If any sessions were discarded while the application was not running, this will be called shortly after application:didFinishLaunchingWithOptions.
// Use this method to release any resources that were specific to the discarded scenes, as they will not return.
}
}

98
native_client/swift/deepspeech_ios_test/deepspeech_ios_test/Assets.xcassets/AppIcon.appiconset/Contents.json Normal file
View File

@ -0,0 +1,98 @@
{
"images" : [
{
"idiom" : "iphone",
"scale" : "2x",
"size" : "20x20"
},
{
"idiom" : "iphone",
"scale" : "3x",
"size" : "20x20"
},
{
"idiom" : "iphone",
"scale" : "2x",
"size" : "29x29"
},
{
"idiom" : "iphone",
"scale" : "3x",
"size" : "29x29"
},
{
"idiom" : "iphone",
"scale" : "2x",
"size" : "40x40"
},
{
"idiom" : "iphone",
"scale" : "3x",
"size" : "40x40"
},
{
"idiom" : "iphone",
"scale" : "2x",
"size" : "60x60"
},
{
"idiom" : "iphone",
"scale" : "3x",
"size" : "60x60"
},
{
"idiom" : "ipad",
"scale" : "1x",
"size" : "20x20"
},
{
"idiom" : "ipad",
"scale" : "2x",
"size" : "20x20"
},
{
"idiom" : "ipad",
"scale" : "1x",
"size" : "29x29"
},
{
"idiom" : "ipad",
"scale" : "2x",
"size" : "29x29"
},
{
"idiom" : "ipad",
"scale" : "1x",
"size" : "40x40"
},
{
"idiom" : "ipad",
"scale" : "2x",
"size" : "40x40"
},
{
"idiom" : "ipad",
"scale" : "1x",
"size" : "76x76"
},
{
"idiom" : "ipad",
"scale" : "2x",
"size" : "76x76"
},
{
"idiom" : "ipad",
"scale" : "2x",
"size" : "83.5x83.5"
},
{
"idiom" : "ios-marketing",
"scale" : "1x",
"size" : "1024x1024"
}
],
"info" : {
"author" : "xcode",
"version" : 1
}
}

6
native_client/swift/deepspeech_ios_test/deepspeech_ios_test/Assets.xcassets/Contents.json Normal file
View File

@ -0,0 +1,6 @@
{
"info" : {
"author" : "xcode",
"version" : 1
}
}

25
native_client/swift/deepspeech_ios_test/deepspeech_ios_test/Base.lproj/LaunchScreen.storyboard Normal file
View File

@ -0,0 +1,25 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<document type="com.apple.InterfaceBuilder3.CocoaTouch.Storyboard.XIB" version="3.0" toolsVersion="13122.16" targetRuntime="iOS.CocoaTouch" propertyAccessControl="none" useAutolayout="YES" launchScreen="YES" useTraitCollections="YES" useSafeAreas="YES" colorMatched="YES" initialViewController="01J-lp-oVM">
<dependencies>
<plugIn identifier="com.apple.InterfaceBuilder.IBCocoaTouchPlugin" version="13104.12"/>
<capability name="Safe area layout guides" minToolsVersion="9.0"/>
<capability name="documents saved in the Xcode 8 format" minToolsVersion="8.0"/>
</dependencies>
<scenes>
<!--View Controller-->
<scene sceneID="EHf-IW-A2E">
<objects>
<viewController id="01J-lp-oVM" sceneMemberID="viewController">
<view key="view" contentMode="scaleToFill" id="Ze5-6b-2t3">
<rect key="frame" x="0.0" y="0.0" width="375" height="667"/>
<autoresizingMask key="autoresizingMask" widthSizable="YES" heightSizable="YES"/>
<color key="backgroundColor" xcode11CocoaTouchSystemColor="systemBackgroundColor" cocoaTouchSystemColor="whiteColor"/>
<viewLayoutGuide key="safeArea" id="6Tk-OE-BBY"/>
</view>
</viewController>
<placeholder placeholderIdentifier="IBFirstResponder" id="iYj-Kq-Ea1" userLabel="First Responder" sceneMemberID="firstResponder"/>
</objects>
<point key="canvasLocation" x="53" y="375"/>
</scene>
</scenes>
</document>

21
native_client/swift/deepspeech_ios_test/deepspeech_ios_test/ContentView.swift Normal file
View File

@ -0,0 +1,21 @@
//
// ContentView.swift
// deepspeech_ios_test
//
// Created by Reuben Morais on 15.06.20.
// Copyright © 2020 Mozilla. All rights reserved.
//
import SwiftUI
struct ContentView: View {
var body: some View {
Text("Hello, World!")
}
}
struct ContentView_Previews: PreviewProvider {
static var previews: some View {
ContentView()
}
}

60
native_client/swift/deepspeech_ios_test/deepspeech_ios_test/Info.plist Normal file
View File

@ -0,0 +1,60 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>CFBundleDevelopmentRegion</key>
<string>$(DEVELOPMENT_LANGUAGE)</string>
<key>CFBundleExecutable</key>
<string>$(EXECUTABLE_NAME)</string>
<key>CFBundleIdentifier</key>
<string>$(PRODUCT_BUNDLE_IDENTIFIER)</string>
<key>CFBundleInfoDictionaryVersion</key>
<string>6.0</string>
<key>CFBundleName</key>
<string>$(PRODUCT_NAME)</string>
<key>CFBundlePackageType</key>
<string>$(PRODUCT_BUNDLE_PACKAGE_TYPE)</string>
<key>CFBundleShortVersionString</key>
<string>1.0</string>
<key>CFBundleVersion</key>
<string>1</string>
<key>LSRequiresIPhoneOS</key>
<true/>
<key>UIApplicationSceneManifest</key>
<dict>
<key>UIApplicationSupportsMultipleScenes</key>
<false/>
<key>UISceneConfigurations</key>
<dict>
<key>UIWindowSceneSessionRoleApplication</key>
<array>
<dict>
<key>UISceneConfigurationName</key>
<string>Default Configuration</string>
<key>UISceneDelegateClassName</key>
<string>$(PRODUCT_MODULE_NAME).SceneDelegate</string>
</dict>
</array>
</dict>
</dict>
<key>UILaunchStoryboardName</key>
<string>LaunchScreen</string>
<key>UIRequiredDeviceCapabilities</key>
<array>
<string>armv7</string>
</array>
<key>UISupportedInterfaceOrientations</key>
<array>
<string>UIInterfaceOrientationPortrait</string>
<string>UIInterfaceOrientationLandscapeLeft</string>
<string>UIInterfaceOrientationLandscapeRight</string>
</array>
<key>UISupportedInterfaceOrientations~ipad</key>
<array>
<string>UIInterfaceOrientationPortrait</string>
<string>UIInterfaceOrientationPortraitUpsideDown</string>
<string>UIInterfaceOrientationLandscapeLeft</string>
<string>UIInterfaceOrientationLandscapeRight</string>
</array>
</dict>
</plist>

6
native_client/swift/deepspeech_ios_test/deepspeech_ios_test/Preview Content/Preview Assets.xcassets/Contents.json Normal file
View File

@ -0,0 +1,6 @@
{
"info" : {
"author" : "xcode",
"version" : 1
}
}

64
native_client/swift/deepspeech_ios_test/deepspeech_ios_test/SceneDelegate.swift Normal file
View File

@ -0,0 +1,64 @@
//
// SceneDelegate.swift
// deepspeech_ios_test
//
// Created by Reuben Morais on 15.06.20.
// Copyright © 2020 Mozilla. All rights reserved.
//
import UIKit
import SwiftUI
class SceneDelegate: UIResponder, UIWindowSceneDelegate {
var window: UIWindow?
func scene(_ scene: UIScene, willConnectTo session: UISceneSession, options connectionOptions: UIScene.ConnectionOptions) {
// Use this method to optionally configure and attach the UIWindow `window` to the provided UIWindowScene `scene`.
// If using a storyboard, the `window` property will automatically be initialized and attached to the scene.
// This delegate does not imply the connecting scene or session are new (see `application:configurationForConnectingSceneSession` instead).
// Create the SwiftUI view that provides the window contents.
let contentView = ContentView()
// Use a UIHostingController as window root view controller.
if let windowScene = scene as? UIWindowScene {
let window = UIWindow(windowScene: windowScene)
window.rootViewController = UIHostingController(rootView: contentView)
self.window = window
window.makeKeyAndVisible()
}
}
func sceneDidDisconnect(_ scene: UIScene) {
// Called as the scene is being released by the system.
// This occurs shortly after the scene enters the background, or when its session is discarded.
// Release any resources associated with this scene that can be re-created the next time the scene connects.
// The scene may re-connect later, as its session was not neccessarily discarded (see `application:didDiscardSceneSessions` instead).
}
func sceneDidBecomeActive(_ scene: UIScene) {
// Called when the scene has moved from an inactive state to an active state.
// Use this method to restart any tasks that were paused (or not yet started) when the scene was inactive.
}
func sceneWillResignActive(_ scene: UIScene) {
// Called when the scene will move from an active state to an inactive state.
// This may occur due to temporary interruptions (ex. an incoming phone call).
}
func sceneWillEnterForeground(_ scene: UIScene) {
// Called as the scene transitions from the background to the foreground.
// Use this method to undo the changes made on entering the background.
}
func sceneDidEnterBackground(_ scene: UIScene) {
// Called as the scene transitions from the foreground to the background.
// Use this method to save data, release shared resources, and store enough scene-specific state information
// to restore the scene back to its current state.
}
}

22
native_client/swift/deepspeech_ios_test/deepspeech_ios_testTests/Info.plist Normal file
View File

@ -0,0 +1,22 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>CFBundleDevelopmentRegion</key>
<string>$(DEVELOPMENT_LANGUAGE)</string>
<key>CFBundleExecutable</key>
<string>$(EXECUTABLE_NAME)</string>
<key>CFBundleIdentifier</key>
<string>$(PRODUCT_BUNDLE_IDENTIFIER)</string>
<key>CFBundleInfoDictionaryVersion</key>
<string>6.0</string>
<key>CFBundleName</key>
<string>$(PRODUCT_NAME)</string>
<key>CFBundlePackageType</key>
<string>$(PRODUCT_BUNDLE_PACKAGE_TYPE)</string>
<key>CFBundleShortVersionString</key>
<string>1.0</string>
<key>CFBundleVersion</key>
<string>1</string>
</dict>
</plist>

34
native_client/swift/deepspeech_ios_test/deepspeech_ios_testTests/deepspeech_ios_testTests.swift Normal file
View File

@ -0,0 +1,34 @@
//
// deepspeech_ios_testTests.swift
// deepspeech_ios_testTests
//
// Created by Reuben Morais on 15.06.20.
// Copyright © 2020 Mozilla. All rights reserved.
//
import XCTest
@testable import deepspeech_ios_test
class deepspeech_ios_testTests: XCTestCase {
override func setUpWithError() throws {
// Put setup code here. This method is called before the invocation of each test method in the class.
}
override func tearDownWithError() throws {
// Put teardown code here. This method is called after the invocation of each test method in the class.
}
func testExample() throws {
// This is an example of a functional test case.
// Use XCTAssert and related functions to verify your tests produce the correct results.
}
func testPerformanceExample() throws {
// This is an example of a performance test case.
self.measure {
// Put the code you want to measure the time of here.
}
}
}

22
native_client/swift/deepspeech_ios_test/deepspeech_ios_testUITests/Info.plist Normal file
View File

@ -0,0 +1,22 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>CFBundleDevelopmentRegion</key>
<string>$(DEVELOPMENT_LANGUAGE)</string>
<key>CFBundleExecutable</key>
<string>$(EXECUTABLE_NAME)</string>
<key>CFBundleIdentifier</key>
<string>$(PRODUCT_BUNDLE_IDENTIFIER)</string>
<key>CFBundleInfoDictionaryVersion</key>
<string>6.0</string>
<key>CFBundleName</key>
<string>$(PRODUCT_NAME)</string>
<key>CFBundlePackageType</key>
<string>$(PRODUCT_BUNDLE_PACKAGE_TYPE)</string>
<key>CFBundleShortVersionString</key>
<string>1.0</string>
<key>CFBundleVersion</key>
<string>1</string>
</dict>
</plist>

43
native_client/swift/deepspeech_ios_test/deepspeech_ios_testUITests/deepspeech_ios_testUITests.swift Normal file
View File

@ -0,0 +1,43 @@
//
// deepspeech_ios_testUITests.swift
// deepspeech_ios_testUITests
//
// Created by Reuben Morais on 15.06.20.
// Copyright © 2020 Mozilla. All rights reserved.
//
import XCTest
class deepspeech_ios_testUITests: XCTestCase {
override func setUpWithError() throws {
// Put setup code here. This method is called before the invocation of each test method in the class.
// In UI tests it is usually best to stop immediately when a failure occurs.
continueAfterFailure = false
// In UI tests it’s important to set the initial state - such as interface orientation - required for your tests before they run. The setUp method is a good place to do this.
}
override func tearDownWithError() throws {
// Put teardown code here. This method is called after the invocation of each test method in the class.
}
func testExample() throws {
// UI tests must launch the application that they test.
let app = XCUIApplication()
app.launch()
// Use recording to get started writing UI tests.
// Use XCTAssert and related functions to verify your tests produce the correct results.
}
func testLaunchPerformance() throws {
if #available(macOS 10.15, iOS 13.0, tvOS 13.0, *) {
// This measures how long it takes to launch your application.
measure(metrics: [XCTOSSignpostMetric.applicationLaunch]) {
XCUIApplication().launch()
}
}
}
}