feat(mac): add Qwen3 MLX streaming dictation

Replace the Sherpa offline pipeline with native MLX streaming, resilient model downloads, live transcript previews, and supporting tests and documentation.
This commit is contained in:
Rocky
2026-07-23 14:34:56 +08:00
parent f1a811fbf0
commit c0c9dad149
35 changed files with 1373 additions and 764 deletions
@@ -5,4 +5,6 @@ import Foundation
enum LocalASRPreferenceKeys {
static let selectedModelId = "mac.localASR.selectedModelId"
/// Persists the user's preferred model download mirror (see `LocalASRDownloadSourcePreference`).
static let downloadSource = "mac.localASR.downloadSource"
}