Skip to content

POC: speech api transcripts2 #3186

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 12 commits into
base: trunk
Choose a base branch
from
Draft

POC: speech api transcripts2 #3186

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
3cd46ff
Ask for permission to use speech API right away
leandroalonso Jul 1, 2024
34efd26
Integrates audio read task with speech
leandroalonso Jul 1, 2024
5be9f86
Use a notification to send transcribed text
leandroalonso Jul 1, 2024
b1b403b
First algorithm iteration
leandroalonso Jul 4, 2024
22e2d4b
Make word by word in a BG thread
leandroalonso Jul 8, 2024
770e630
Use levenshtein distance
leandroalonso Jul 8, 2024
e7a25ea
Update packages
SergioEstevao May 21, 2025
3247da7
Update pods
SergioEstevao May 22, 2025
27866d2
Remove unused import
SergioEstevao May 22, 2025
db535e3
Update changes to separate files and extensions
SergioEstevao May 23, 2025
20a0d64
Merge branch 'trunk' into poc/speech-api-transcripts2
SergioEstevao May 23, 2025
98a4a4d
Allow use of SpeechRecognition Task using a FF
SergioEstevao May 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions Modules/Utils/Sources/PocketCastsUtils/Feature Flags/FeatureFlag.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,6 +188,9 @@ public enum FeatureFlag: String, CaseIterable {
/// When replacing an episode list with a new one, use the provided episode instead of Up Next Queue
case replaceSpecificEpisode

/// If we should try to transcript sync with the audio
case transcriptSync

public var enabled: Bool {
if let overriddenValue = FeatureFlagOverrideStore().overriddenValue(for: self) {
return overriddenValue
Expand Down Expand Up @@ -318,6 +321,8 @@ public enum FeatureFlag: String, CaseIterable {
true
case .replaceSpecificEpisode:
true
case .transcriptSync:
true
}
}

Expand Down
30 changes: 30 additions & 0 deletions podcasts.xcodeproj/project.pbxproj
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2043,6 +2043,8 @@
FFC293992B6173400059F3BB /* IAPTypes.swift in Sources */ = {isa = PBXBuildFile; fileRef = FFC293982B6173400059F3BB /* IAPTypes.swift */; };
FFD044192C4FE9F400CCB192 /* TranscriptModelFilterTests.swift in Sources */ = {isa = PBXBuildFile; fileRef = FFD044182C4FE9F400CCB192 /* TranscriptModelFilterTests.swift */; };
FFD3AB8C2BD15E8F00C562CB /* CircleView.swift in Sources */ = {isa = PBXBuildFile; fileRef = FFD3AB8B2BD15E8F00C562CB /* CircleView.swift */; };
FFDB38302DE0B88200911B51 /* AudioReadSpeechRecognitionTask.swift in Sources */ = {isa = PBXBuildFile; fileRef = FFDB382F2DE0B88200911B51 /* AudioReadSpeechRecognitionTask.swift */; };
FFDB38312DE0CFE800911B51 /* AudioReadSpeechRecognitionTask.swift in Sources */ = {isa = PBXBuildFile; fileRef = FFDB382F2DE0B88200911B51 /* AudioReadSpeechRecognitionTask.swift */; };
FFDE41A32DD201AE0065ADDE /* AppClipAppDelegate.swift in Sources */ = {isa = PBXBuildFile; fileRef = FFDE41A22DD201A40065ADDE /* AppClipAppDelegate.swift */; };
FFE794DD2DA443FF005E4D40 /* NotificationsCoordinator.swift in Sources */ = {isa = PBXBuildFile; fileRef = FFE794DC2DA443F8005E4D40 /* NotificationsCoordinator.swift */; };
FFF024CE2B62AC9400457373 /* IAPHelperTests.swift in Sources */ = {isa = PBXBuildFile; fileRef = FFF024CD2B62AC9400457373 /* IAPHelperTests.swift */; };
Expand Down Expand Up @@ -4114,6 +4116,7 @@
FFC293982B6173400059F3BB /* IAPTypes.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = IAPTypes.swift; sourceTree = "<group>"; };
FFD044182C4FE9F400CCB192 /* TranscriptModelFilterTests.swift */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.swift; path = TranscriptModelFilterTests.swift; sourceTree = "<group>"; };
FFD3AB8B2BD15E8F00C562CB /* CircleView.swift */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.swift; path = CircleView.swift; sourceTree = "<group>"; };
FFDB382F2DE0B88200911B51 /* AudioReadSpeechRecognitionTask.swift */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.swift; path = AudioReadSpeechRecognitionTask.swift; sourceTree = "<group>"; };
FFDE41A22DD201A40065ADDE /* AppClipAppDelegate.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = AppClipAppDelegate.swift; sourceTree = "<group>"; };
FFE794DC2DA443F8005E4D40 /* NotificationsCoordinator.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = NotificationsCoordinator.swift; sourceTree = "<group>"; };
FFF024CD2B62AC9400457373 /* IAPHelperTests.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = IAPHelperTests.swift; sourceTree = "<group>"; };
Expand Down Expand Up @@ -6017,6 +6020,7 @@
children = (
BDF15A411B54E088000EC323 /* EffectsPlayer.swift */,
BD4098791B9ECA5F007F36BD /* AudioReadTask.swift */,
FFDB382F2DE0B88200911B51 /* AudioReadSpeechRecognitionTask.swift */,
BD40987F1B9EFE3C007F36BD /* AudioPlayTask.swift */,
BD4098811B9EFF6E007F36BD /* PlayBufferManager.swift */,
BD40987B1B9ED731007F36BD /* SynchronizedAudioStack.swift */,
Expand Down Expand Up @@ -9047,6 +9051,7 @@
8B1762752B6808F700F44450 /* XCRemoteSwiftPackageReference "JLRoutes" */,
8B1762782B684E7100F44450 /* XCRemoteSwiftPackageReference "Kingfisher" */,
FF7F89EB2C2AF53C00FC0ED5 /* XCRemoteSwiftPackageReference "SwiftSubtitles" */,
FFF450222DDF6A8A00272AB8 /* XCRemoteSwiftPackageReference "Ifrit" */,
9A11FC912D91CBF300A1EF3E /* XCRemoteSwiftPackageReference "AppsFlyerFramework-Dynamic" */,
F5FFC2312DBAF0340091429C /* XCRemoteSwiftPackageReference "facebook-ios-sdk" */,
);
Expand Down Expand Up @@ -9821,10 +9826,14 @@
inputFileListPaths = (
"${PODS_ROOT}/Target Support Files/Pods-podcasts/Pods-podcasts-frameworks-${CONFIGURATION}-input-files.xcfilelist",
);
inputPaths = (
);
name = "[CP] Embed Pods Frameworks";
outputFileListPaths = (
"${PODS_ROOT}/Target Support Files/Pods-podcasts/Pods-podcasts-frameworks-${CONFIGURATION}-output-files.xcfilelist",
);
outputPaths = (
);
runOnlyForDeploymentPostprocessing = 0;
shellPath = /bin/sh;
shellScript = "\"${PODS_ROOT}/Target Support Files/Pods-podcasts/Pods-podcasts-frameworks.sh\"\n";
Expand Down Expand Up @@ -9856,10 +9865,14 @@
inputFileListPaths = (
"${PODS_ROOT}/Target Support Files/Pods-PocketCastsTests/Pods-PocketCastsTests-frameworks-${CONFIGURATION}-input-files.xcfilelist",
);
inputPaths = (
);
name = "[CP] Embed Pods Frameworks";
outputFileListPaths = (
"${PODS_ROOT}/Target Support Files/Pods-PocketCastsTests/Pods-PocketCastsTests-frameworks-${CONFIGURATION}-output-files.xcfilelist",
);
outputPaths = (
);
runOnlyForDeploymentPostprocessing = 0;
shellPath = /bin/sh;
shellScript = "\"${PODS_ROOT}/Target Support Files/Pods-PocketCastsTests/Pods-PocketCastsTests-frameworks.sh\"\n";
Expand Down Expand Up @@ -10164,6 +10177,7 @@
BD7C1FFD237D16C600B3353B /* PCAlwaysVisibleCastBtn.swift in Sources */,
BD9324712398BB50004F19A1 /* TourView.swift in Sources */,
FF7F89EA2C2979D900FC0ED5 /* TranscriptViewController.swift in Sources */,
FF7F89EA2C2979D900FC0ED5 /* TranscriptViewController.swift in Sources */,
BDC5360A27C88A5700EFCF31 /* FolderPreviewWrapper.swift in Sources */,
8B5AB48E2901A8BD0018C637 /* StoriesController.swift in Sources */,
BD6D4187200C802900CA8993 /* PodcastViewController+NetworkLoad.swift in Sources */,
Expand Down Expand Up @@ -10283,6 +10297,7 @@
C7318EA42A61E40800EAFA9C /* BookmarkEditTitleView.swift in Sources */,
BDF4D30B2175A9E90086463E /* StarredViewController.swift in Sources */,
C75BB06829B954B100F2DF63 /* EpisodeLoadingController.swift in Sources */,
FFDB38302DE0B88200911B51 /* AudioReadSpeechRecognitionTask.swift in Sources */,
40B118EB2153B8CA000932C9 /* RadioButtonCell.swift in Sources */,
BDEAA1861BB144AD001097D9 /* DisclosureCell.swift in Sources */,
BDD40A1A1FA1AF7900A53AE1 /* TintableImageView.swift in Sources */,
Expand Down Expand Up @@ -11321,6 +11336,7 @@
F5F509382CEBF1FE007D6E39 /* ThemeableLabel.swift in Sources */,
FF0F407C2D5E37250036FFE9 /* ThreadSafeDictionary.swift in Sources */,
F5F509562CEBF62D007D6E39 /* DownloadProgress.swift in Sources */,
FFDB38312DE0CFE800911B51 /* AudioReadSpeechRecognitionTask.swift in Sources */,
F5F509702CEBF8B8007D6E39 /* SJCommonUtils.m in Sources */,
F5ADE2F52CF52AFA00F2CEA7 /* TracksAdapter.swift in Sources */,
F5D5F7BB2CEBE7CE001F492D /* NowPlayingView.swift in Sources */,
Expand Down Expand Up @@ -11745,6 +11761,8 @@
ASSETCATALOG_COMPILER_APPICON_NAME = AppIcon;
CLANG_ENABLE_MODULES = YES;
CODE_SIGN_ENTITLEMENTS = podcasts/podcastsDebug.entitlements;
"CODE_SIGN_IDENTITY[sdk=iphoneos*]" = "iPhone Developer";
"DEVELOPMENT_TEAM[sdk=iphoneos*]" = PZYM8XX95Q;
ENABLE_BITCODE = NO;
FRAMEWORK_SEARCH_PATHS = (
"$(inherited)",
Expand All @@ -11759,6 +11777,7 @@
);
PRODUCT_NAME = "$(TARGET_NAME)";
PROVISIONING_PROFILE_SPECIFIER = "Pocket Casts Development";
"PROVISIONING_PROFILE_SPECIFIER[sdk=iphoneos*]" = "Pocket Casts Development";
SWIFT_OBJC_BRIDGING_HEADER = "podcasts/podcasts-Bridging-Header.h";
WRAPPER_EXTENSION = app;
};
Expand Down Expand Up @@ -13130,6 +13149,8 @@
ASSETCATALOG_COMPILER_APPICON_NAME = AppIcon;
CLANG_ENABLE_MODULES = YES;
CODE_SIGN_ENTITLEMENTS = podcasts/podcastsDebug.entitlements;
"CODE_SIGN_IDENTITY[sdk=iphoneos*]" = "iPhone Developer";
"DEVELOPMENT_TEAM[sdk=iphoneos*]" = PZYM8XX95Q;
ENABLE_BITCODE = NO;
FRAMEWORK_SEARCH_PATHS = (
"$(inherited)",
Expand All @@ -13144,6 +13165,7 @@
);
PRODUCT_NAME = "$(TARGET_NAME)";
PROVISIONING_PROFILE_SPECIFIER = "Pocket Casts Development";
"PROVISIONING_PROFILE_SPECIFIER[sdk=iphoneos*]" = "Pocket Casts Development";
SWIFT_OBJC_BRIDGING_HEADER = "podcasts/podcasts-Bridging-Header.h";
WRAPPER_EXTENSION = app;
};
Expand Down Expand Up @@ -13785,6 +13807,14 @@
minimumVersion = 1.8.2;
};
};
FFF450222DDF6A8A00272AB8 /* XCRemoteSwiftPackageReference "Ifrit" */ = {
isa = XCRemoteSwiftPackageReference;
repositoryURL = "https://github.com/ukushu/Ifrit.git";
requirement = {
branch = main;
kind = branch;
};
};
/* End XCRemoteSwiftPackageReference section */

/* Begin XCSwiftPackageProductDependency section */
Expand Down
9 changes: 9 additions & 0 deletions podcasts.xcworkspace/xcshareddata/swiftpm/Package.resolved
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading