Start on live transcription and python sidecar (faster-whisper)

tests/models.test.ts

@@ -6,6 +6,7 @@ import {
   estimateDefaultDownloadBytes,
   estimateDownloadBytes,
   formatModelSize,
+  getFasterWhisperModel,
   getModel,
   resolveDefaultDtype,
 } from "../src/lib/models";
@@ -59,6 +60,21 @@ describe("MODELS catalog", () => {
     expect(getModel(DEFAULT_MODEL_ID)).toBeDefined();
     expect(getModel("onnx-community/whisper-nonexistent")).toBeUndefined();
   });
+
+  test("every model maps to a faster-whisper name for the server engine (D-013)", () => {
+    for (const model of MODELS) {
+      // The onnx-community ids and faster-whisper's aliases share the same
+      // size suffix ("tiny.en", …, "large-v3-turbo"); keeping them aligned is
+      // what lets one catalog drive both engines.
+      expect(model.fasterWhisperModel).toBe(
+        model.id.replace("onnx-community/whisper-", ""),
+      );
+    }
+    expect(getFasterWhisperModel(DEFAULT_MODEL_ID)).toBe("tiny.en");
+    // Unknown ids stay undefined so /api/transcribe can answer 400 instead of
+    // forwarding arbitrary strings to the sidecar.
+    expect(getFasterWhisperModel("someone/some-model")).toBeUndefined();
+  });
 });
 
 describe("resolveDefaultDtype", () => {

tests/protocol.test.ts

@@ -29,6 +29,7 @@ describe("isUiToWorkerMessage", () => {
       { type: "transcribe", audio: new Float32Array(8) },
       { type: "transcribe", audio: new Float32Array(8), language: "da", task: "transcribe" },
       { type: "transcribe", audio: new Float32Array(8), language: "auto", task: "translate" },
+      { type: "transcribe", audio: new Float32Array(8), requestId: "live-3" },
     ];
     for (const message of [...loads, ...transcribes]) {
       expect(isUiToWorkerMessage(message)).toBe(true);
@@ -53,6 +54,9 @@ describe("isUiToWorkerMessage", () => {
     expect(
       isUiToWorkerMessage({ type: "transcribe", audio: new Float32Array(4), task: "detect" }),
     ).toBe(false);
+    expect(
+      isUiToWorkerMessage({ type: "transcribe", audio: new Float32Array(4), requestId: 7 }),
+    ).toBe(false);
     expect(isUiToWorkerMessage({ type: "result", text: "", chunks: [] })).toBe(false);
   });
 });
@@ -74,8 +78,11 @@ describe("isWorkerToUiMessage", () => {
       { type: "load-progress", status: "ready", device: "wasm" },
       { type: "load-progress", status: "ready", device: "webgpu" },
       { type: "partial", text: " hello" },
+      { type: "partial", text: " hello", requestId: "live-1" },
       { type: "result", text: "hello world", chunks: [{ text: "hello world", timestamp: [0, 1.2] }] },
+      { type: "result", text: "hello world", chunks: [], requestId: "live-1" },
       { type: "error", stage: "load", message: "boom" },
+      { type: "error", stage: "transcribe", message: "boom", requestId: "live-2" },
     ];
     for (const message of messages) {
       expect(isWorkerToUiMessage(message)).toBe(true);
@@ -89,6 +96,7 @@ describe("isWorkerToUiMessage", () => {
     expect(isWorkerToUiMessage({ type: "load-progress", status: "ready" })).toBe(false);
     expect(isWorkerToUiMessage({ type: "load-progress", status: "ready", device: "cuda" })).toBe(false);
     expect(isWorkerToUiMessage({ type: "partial" })).toBe(false);
+    expect(isWorkerToUiMessage({ type: "partial", text: "x", requestId: 1 })).toBe(false);
     expect(isWorkerToUiMessage({ type: "result", text: "x", chunks: "nope" })).toBe(false);
     expect(isWorkerToUiMessage({ type: "error", stage: "decode", message: "m" })).toBe(false);
     expect(isWorkerToUiMessage({ type: "load", modelId: "x", device: "wasm" })).toBe(false);