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.
64 lines
2.2 KiB
Swift
64 lines
2.2 KiB
Swift
// MacDictationPipeline.swift
|
|
// OSGKeyboard · Mac
|
|
//
|
|
// Dictation pipeline: samples → ASR (cloud or local) → polish.
|
|
// Cloud path reuses `CloudASRClientFactory`; local path uses Qwen3-ASR (MLX)
|
|
// with Apple Speech fallback when weights are missing.
|
|
|
|
import Foundation
|
|
|
|
enum MacDictationError: Error, LocalizedError {
|
|
case noAudio
|
|
case providerHasNoCloudASR
|
|
case emptyTranscript
|
|
|
|
var errorDescription: String? {
|
|
switch self {
|
|
case .noAudio:
|
|
return MacL10n.string("mac.error.noAudio")
|
|
case .providerHasNoCloudASR:
|
|
return MacL10n.string("mac.error.noCloudASR")
|
|
case .emptyTranscript:
|
|
return MacL10n.string("mac.error.emptyTranscript")
|
|
}
|
|
}
|
|
}
|
|
|
|
enum MacDictationPipeline {
|
|
/// Runs ASR then best-effort polish. Polish failures fall back to raw text.
|
|
static func run(samples: [Float], store: AppGroupStore) async throws -> String {
|
|
guard !samples.isEmpty else { throw MacDictationError.noAudio }
|
|
|
|
let locale = Locale(identifier: store.localeId.isEmpty ? "zh-CN" : store.localeId)
|
|
let raw: String
|
|
|
|
if store.engineMode == "local" {
|
|
raw = try await MacLocalASRService.transcribe(samples: samples, locale: locale)
|
|
} else {
|
|
let strategy = CloudASRModelCatalog.strategy(for: store.providerId)
|
|
guard strategy != .localFallback else { throw MacDictationError.providerHasNoCloudASR }
|
|
|
|
let client = CloudASRClientFactory.make(store: store)
|
|
try? await client.prepare(dictionary: store.personalDictionary)
|
|
raw = try await client.transcribe(
|
|
samples: samples,
|
|
sampleRate: 16_000,
|
|
locale: locale,
|
|
dictionary: store.personalDictionary
|
|
)
|
|
}
|
|
|
|
let trimmed = raw.trimmingCharacters(in: .whitespacesAndNewlines)
|
|
guard !trimmed.isEmpty else { throw MacDictationError.emptyTranscript }
|
|
|
|
if let polished = try? await PolishingService(store: store).polish(
|
|
trimmed,
|
|
mode: store.polishModeForPipeline
|
|
),
|
|
!polished.isEmpty {
|
|
return polished
|
|
}
|
|
return trimmed
|
|
}
|
|
}
|