Rocky
c2f07bd8d2
Introduce a standalone macOS menu-bar app (OSGKeyboardMac) that reuses the platform-agnostic OSGKeyboardShared core: record -> cloud/local ASR -> polish -> insert. Local mode uses Qwen3-ASR via mlx-swift-asr (macOS 15+, Apple Silicon); iOS targets stay zero-SPM. Harden iCloud sync for multi-device correctness: - Per-field settings merge (appSettings.v2) so concurrent edits no longer clobber each other's unrelated fields. - Per-device usage statistics (G-Counter) that sum instead of max(). - Tombstoned dictionary/history merge so deletes propagate and entries can't resurrect. - API keys replicate via iCloud Keychain, never iCloud KVS JSON; pulling a legacy blob without key fields no longer wipes local Keychain entries. - Add a low-risk "Sync Now" action in Settings. Fix Flow keyboard mic state: stay orange until the host publishes a real ready contract, share a single MicVoiceAvailability gate, and self-heal stale cross-process heartbeat jitter instead of getting stuck. Extract shared storage (SpeechHistoryStore/UsageStatisticsStore, ConfigurationStore) into OSGKeyboardShared and add tests for the new sync/merge logic.
62 lines
2.4 KiB
Swift
62 lines
2.4 KiB
Swift
// MacSpeechLocalASR.swift
|
|
// OSGKeyboard · Mac
|
|
//
|
|
// Apple Speech framework fallback for local engine mode. Writes PCM to a
|
|
// temp WAV and runs `SFSpeechURLRecognitionRequest`.
|
|
|
|
import AVFoundation
|
|
import Foundation
|
|
import Speech
|
|
|
|
enum MacSpeechLocalASR {
|
|
static func transcribe(samples: [Float], locale: Locale) async throws -> String {
|
|
let auth = await requestAuthorization()
|
|
guard auth == .authorized else { throw MacLocalASRError.speechDenied }
|
|
|
|
let wavURL = try writeTemporaryWAV(samples: samples, sampleRate: 16_000)
|
|
defer { try? FileManager.default.removeItem(at: wavURL) }
|
|
|
|
let recognizer = SFSpeechRecognizer(locale: locale) ?? SFSpeechRecognizer()
|
|
guard let recognizer, recognizer.isAvailable else {
|
|
throw MacLocalASRError.speechFailed("Speech recognizer unavailable")
|
|
}
|
|
|
|
return try await withCheckedThrowingContinuation { continuation in
|
|
let request = SFSpeechURLRecognitionRequest(url: wavURL)
|
|
request.shouldReportPartialResults = false
|
|
request.requiresOnDeviceRecognition = true
|
|
|
|
recognizer.recognitionTask(with: request) { result, error in
|
|
if let error {
|
|
continuation.resume(throwing: MacLocalASRError.speechFailed(error.localizedDescription))
|
|
return
|
|
}
|
|
guard let result, result.isFinal else { return }
|
|
let text = result.bestTranscription.formattedString
|
|
.trimmingCharacters(in: .whitespacesAndNewlines)
|
|
if text.isEmpty {
|
|
continuation.resume(throwing: MacLocalASRError.emptyTranscript)
|
|
} else {
|
|
continuation.resume(returning: text)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
private static func requestAuthorization() async -> SFSpeechRecognizerAuthorizationStatus {
|
|
await withCheckedContinuation { continuation in
|
|
SFSpeechRecognizer.requestAuthorization { status in
|
|
continuation.resume(returning: status)
|
|
}
|
|
}
|
|
}
|
|
|
|
private static func writeTemporaryWAV(samples: [Float], sampleRate: Int) throws -> URL {
|
|
let wav = PCMSampleWavEncoder.encode(samples: samples, sampleRate: sampleRate)
|
|
let url = FileManager.default.temporaryDirectory
|
|
.appendingPathComponent("osg-mac-asr-\(UUID().uuidString).wav")
|
|
try wav.write(to: url)
|
|
return url
|
|
}
|
|
}
|