Add on-device Whisper as a second offline transcription option

sherpa-onnx's native library already reads an offline Whisper config
(verified against sherpa-onnx/jni/offline-recognizer.cc at v1.13.0);
only the Java wrapper was a package-private stub. This adds a public
OfflineWhisperModelConfig builder and wires base.en (int8) in as a
second on-device model next to Moonshine.

- FaceclawVoiceController: setOnboardModelKind() selects the model
  before start("onboard"); defaults to Moonshine. Whisper skips the
  700ms live-partial redecode (each call re-encodes the whole utterance
  plus ~10s of tail padding) and gates near-silent segments before
  decode.
- asr-model.ts: ASR_MODELS registry with per-model download state.
- Settings > Voice: "On-device (Moonshine)", "On-device (Whisper)",
  and "OpenAI (Whisper)" for the existing cloud provider (stored
  value unchanged); one model row per on-device model.
- Microphones live captions pass "moonshine" explicitly (unchanged).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Chris LeeandClaude Sonnet 5 committed 2026-09-14 22:46:22 -04:00
1 parent dcb071621d
commit 2d717a9cdb
9 files changed
+459 -162

No files matched your search

+10 -2
View File
@@ -26,7 +26,12 @@ export type VoiceControlState = {
detail: string;
};
export type VoiceProviderKind = "onboard" | "elevenlabs" | "whisper" | "soniox";
// "whisper" (no "onboard-" prefix) is the OpenAI CLOUD provider (gpt-realtime-whisper,
// see openai-stt.ts) -- an unfortunate pre-existing name collision with the model
// family, not with "onboard-whisper" below, which is the on-device sherpa-onnx
// Whisper backend added alongside "onboard" (Moonshine). Kept as-is rather than
// renamed, since it's a persisted settings value on real installs already.
export type VoiceProviderKind = "onboard" | "onboard-whisper" | "elevenlabs" | "whisper" | "soniox";
export type VoiceTranscriptEvent = CloudSttTranscriptEvent & {
/**
@@ -314,6 +319,9 @@ export class FaceclawVoiceControlBridge {
this.cloudClient = null;
this.started = true;
// Which on-device model to load; a no-op setter for every provider except
// "onboard-whisper" (FaceclawVoiceController defaults to Moonshine).
this.controller?.setOnboardModelKind(options.provider === "onboard-whisper" ? "whisper" : "moonshine");
this.controller?.start("onboard");
}
@@ -323,7 +331,7 @@ export class FaceclawVoiceControlBridge {
* than failing the capture outright.
*/
private createCloudClient(options: PushToTalkOptions): CloudSttClient | null {
if (options.provider === "onboard") return null;
if (options.provider === "onboard" || options.provider === "onboard-whisper") return null;
const sttOptions = {
apiKey: "",
onTranscript: (event: CloudSttTranscriptEvent) =>