-
-
Notifications
You must be signed in to change notification settings - Fork 194
Add ivrit.ai Hebrew model (Whisper Large v3 Turbo) #415
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.
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
Open
Nitzan94
wants to merge
2
commits into
altic-dev:main
Choose a base branch
from
Nitzan94:nitzan/hebrew-ivrit-ai-model
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
2 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
72 changes: 72 additions & 0 deletions
72
Tests/FluidDictationIntegrationTests/IvritHebrewModelTests.swift
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,72 @@ | ||
| // ABOUTME: Tests for the ivrit.ai Hebrew Whisper model wiring (metadata + catalog routing). | ||
| // ABOUTME: Verifies Hebrew routes to the ivrit model first and forces Hebrew decoding. | ||
| import Foundation | ||
| import XCTest | ||
|
|
||
| @testable import FluidVoice_Debug | ||
|
|
||
| final class IvritHebrewModelTests: XCTestCase { | ||
| private typealias Model = SettingsStore.SpeechModel | ||
|
|
||
| // MARK: - Model metadata | ||
|
|
||
| func testIvritModelLocalFilenameIsDistinctFromGenericWhisper() { | ||
| XCTAssertEqual(Model.whisperIvritV3Turbo.whisperModelFile, "ggml-ivrit-v3-turbo.bin") | ||
| } | ||
|
|
||
| func testIvritModelIsTreatedAsWhisper() { | ||
| XCTAssertTrue(Model.whisperIvritV3Turbo.isWhisperModel) | ||
| } | ||
|
|
||
| func testIvritModelForcesHebrewDecodeLanguage() { | ||
| // "iw" is SwiftWhisper's WhisperLanguage.hebrew raw value (legacy ISO 639 code). | ||
| XCTAssertEqual(Model.whisperIvritV3Turbo.forcedWhisperLanguageCode, "iw") | ||
| } | ||
|
|
||
| func testIvritModelDownloadsFromIvritAIRepoNotGgerganov() { | ||
| let url = Model.whisperIvritV3Turbo.whisperDownloadURL | ||
| XCTAssertNotNil(url) | ||
| XCTAssertEqual(url?.host, "huggingface.co") | ||
| XCTAssertTrue(url?.path.contains("ivrit-ai") ?? false, "Expected ivrit.ai HF repo, got \(String(describing: url))") | ||
| } | ||
|
|
||
| func testGenericWhisperStillDownloadsFromGgerganov() { | ||
| let url = Model.whisperSmall.whisperDownloadURL | ||
| XCTAssertTrue(url?.path.contains("ggerganov/whisper.cpp") ?? false) | ||
| } | ||
|
|
||
| // MARK: - Catalog routing | ||
|
|
||
| func testHebrewRoutesToIvritModelWhenAvailable() { | ||
| let routes = VoiceEngineLanguageCatalog.routes( | ||
| forLanguageID: "he", | ||
| availableModels: [.whisperIvritV3Turbo] | ||
| ) | ||
| XCTAssertTrue( | ||
| routes.contains { $0.model == .whisperIvritV3Turbo }, | ||
| "Hebrew should produce an ivrit.ai route when the model is available" | ||
| ) | ||
| } | ||
|
|
||
| func testIvritModelIsTheRecommendedHebrewEngine() { | ||
| // When several Hebrew-capable engines are available, the ivrit model should rank first. | ||
| let routes = VoiceEngineLanguageCatalog.routes( | ||
| forLanguageID: "he", | ||
| availableModels: [.whisperSmall, .nemotronOffline, .whisperIvritV3Turbo, .appleSpeech] | ||
| ) | ||
| XCTAssertEqual(routes.first?.model, .whisperIvritV3Turbo) | ||
| } | ||
|
|
||
| func testEnglishDoesNotRouteToIvritModel() { | ||
| let routes = VoiceEngineLanguageCatalog.routes( | ||
| forLanguageID: "en", | ||
| availableModels: Model.allCases | ||
| ) | ||
| XCTAssertFalse(routes.contains { $0.model == .whisperIvritV3Turbo }) | ||
| } | ||
|
|
||
| func testHebrewLanguageIsListedWhenIvritModelAvailable() { | ||
| let languages = VoiceEngineLanguageCatalog.allLanguages(availableModels: [.whisperIvritV3Turbo]) | ||
| XCTAssertTrue(languages.contains { $0.id == "he" }) | ||
| } | ||
| } | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This new test class is never compiled or run by the configured test scheme: I checked
Fluid.xcodeproj/project.pbxproj, and theFluidDictationIntegrationTestsPBXSourcesBuildPhasestill lists onlyAudioFixtureLoader.swiftandDictationE2ETests.swift, with no file reference/build file forIvritHebrewModelTests.swift. Because this repo's test target is manually enumerated rather than file-system-synchronized, the ivrit routing/metadata checks added here provide no CI coverage until the file is added to the target.Useful? React with 👍 / 👎.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good catch — fixed in 39232b7. Added IvritHebrewModelTests.swift to the FluidDictationIntegrationTests target (file reference + build file + group membership + Sources build phase), mirroring DictationE2ETests.swift, so the routing/metadata checks are now compiled and run by the test scheme.