Offer Whisper's Translate to English only on models trained for it (canTranslate)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/App.tsx

@@ -37,6 +37,7 @@ import {
   formatModelSize,
   getModel,
   resolveDefaultDtype,
+  taskForModel,
 } from "./lib/models";
 import { shouldWarnBeforeLoad, type MobileMemoryHint } from "./lib/mobileMemoryGuard";
 import {
@@ -499,6 +500,9 @@ export function App() {
   function handleModelSelect(nextModelId: string) {
     if (busy || liveStatus !== "idle" || nextModelId === modelId) return;
     setModelId(nextModelId);
+    // A "Translate to English" chosen on a model that can translate must not
+    // silently carry over to one that cannot (D-WS4a).
+    setTask((current) => taskForModel(nextModelId, current));
     setActiveDevice(null);
     setActiveThreads(null);
     setPartialText("");
@@ -675,7 +679,7 @@ export function App() {
         // Language/task only apply to multilingual models; `.en` variants
         // take neither. The browser engine ignores modelId (worker holds it).
         modelId,
-        ...(multilingual && { language, task }),
+        ...(multilingual && { language, task: taskForModel(modelId, task) }),
         onPartial: (fragment) => {
           if (fileRun.current === run) setPartialText((text) => text + fragment);
         },
@@ -752,7 +756,10 @@ export function App() {
     setLivePending(0);
     setLiveStatus("starting");
 
-    const options = (getModel(modelId)?.multilingual ?? false) ? { language, task } : {};
+    const options =
+      (getModel(modelId)?.multilingual ?? false)
+        ? { language, task: taskForModel(modelId, task) }
+        : {};
 
     if (useServer) {
       const wsUrl = new URL(`/api/transcribe/live?model=${modelId}`, window.location.href);
@@ -988,6 +995,7 @@ export function App() {
       const allowed = ["onnx-community/whisper-large-v3-turbo", "onnx-community/whisper-medium.en_timestamped"];
       if (!allowed.includes(modelId) && !busy && liveStatus === "idle") {
         setModelId("onnx-community/whisper-large-v3-turbo");
+        setTask((current) => taskForModel("onnx-community/whisper-large-v3-turbo", current));
         setActiveDevice(null);
         setActiveThreads(null);
         setPartialText("");
@@ -1036,8 +1044,9 @@ export function App() {
         <TranscriptionOptions
           language={language}
           onLanguageChange={setLanguage}
-          task={task}
+          task={taskForModel(modelId, task)}
           onTaskChange={setTask}
+          canTranslate={model.canTranslate}
           disabled={busy || liveActive}
         />
       )}

src/components/TranscriptionOptions.tsx

@@ -6,18 +6,26 @@ interface TranscriptionOptionsProps {
   onLanguageChange: (language: string) => void;
   task: WhisperTask;
   onTaskChange: (task: WhisperTask) => void;
+  /**
+   * Whether the model supports Whisper's own speech → English translation
+   * (`WhisperModel.canTranslate`, D-WS4a). When false the Task control is not
+   * rendered at all — transcribing is the only thing such a model does.
+   */
+  canTranslate: boolean;
   disabled?: boolean;
 }
 
 /**
  * Language + task controls for multilingual models. The parent renders this
  * only when the selected model is multilingual — `.en` models take neither.
+ * The task control only appears where the model can translate (D-WS4a).
  */
 export function TranscriptionOptions({
   language,
   onLanguageChange,
   task,
   onTaskChange,
+  canTranslate,
   disabled = false,
 }: TranscriptionOptionsProps) {
   return (
@@ -37,17 +45,19 @@ export function TranscriptionOptions({
           ))}
         </select>
       </label>
-      <label>
-        Task
-        <select
-          value={task}
-          disabled={disabled}
-          onChange={(event) => onTaskChange(event.target.value as WhisperTask)}
-        >
-          <option value="transcribe">Transcribe</option>
-          <option value="translate">Translate to English</option>
-        </select>
-      </label>
+      {canTranslate && (
+        <label>
+          Task
+          <select
+            value={task}
+            disabled={disabled}
+            onChange={(event) => onTaskChange(event.target.value as WhisperTask)}
+          >
+            <option value="transcribe">Transcribe</option>
+            <option value="translate">Translate to English</option>
+          </select>
+        </label>
+      )}
     </div>
   );
 }

src/lib/models.ts

@@ -42,6 +42,15 @@ export interface WhisperModel {
   displayName: string;
   /** False for `.en` (English-only) variants. */
   multilingual: boolean;
+  /**
+   * Whether Whisper's own `task: "translate"` (speech → English text) is
+   * offered (D-WS4a). False for every `.en` model (no task token) and for
+   * large-v3-turbo, which OpenAI did not train for translation — and for any
+   * turbo-based fine-tune not tested for it. The UI hides "Translate to
+   * English" where false; text translation of a finished transcript
+   * (D-WS4b) works for every model regardless.
+   */
+  canTranslate: boolean;
   /** Encoder parameter count, in millions (drives size estimates). */
   encoderParamsM: number;
   /** Decoder parameter count, in millions (drives size estimates). */
@@ -174,6 +183,7 @@ export const MODELS: readonly WhisperModel[] = [
     fasterWhisperModel: "tiny.en",
     displayName: "Whisper Tiny (English)",
     multilingual: false,
+    canTranslate: false,
     encoderParamsM: 8,
     decoderParamsM: 31,
     defaults: {
@@ -188,6 +198,7 @@ export const MODELS: readonly WhisperModel[] = [
     fasterWhisperModel: "tiny",
     displayName: "Whisper Tiny",
     multilingual: true,
+    canTranslate: true,
     encoderParamsM: 8,
     decoderParamsM: 31,
     defaults: { wasm: WASM_Q8, webgpu: WEBGPU_FP32, webnn: WEBNN_FP16 },
@@ -197,6 +208,7 @@ export const MODELS: readonly WhisperModel[] = [
     fasterWhisperModel: "base.en",
     displayName: "Whisper Base (English)",
     multilingual: false,
+    canTranslate: false,
     encoderParamsM: 20,
     decoderParamsM: 54,
     defaults: { wasm: WASM_Q8, webgpu: WEBGPU_FP32, webnn: WEBNN_FP16 },
@@ -206,6 +218,7 @@ export const MODELS: readonly WhisperModel[] = [
     fasterWhisperModel: "base",
     displayName: "Whisper Base",
     multilingual: true,
+    canTranslate: true,
     encoderParamsM: 20,
     decoderParamsM: 54,
     defaults: { wasm: WASM_Q8, webgpu: WEBGPU_FP32, webnn: WEBNN_FP16 },
@@ -215,6 +228,7 @@ export const MODELS: readonly WhisperModel[] = [
     fasterWhisperModel: "small.en",
     displayName: "Whisper Small (English)",
     multilingual: false,
+    canTranslate: false,
     encoderParamsM: 88,
     decoderParamsM: 156,
     defaults: { wasm: WASM_Q8, webgpu: WEBGPU_FP16_Q4, webnn: WEBNN_FP16 },
@@ -224,6 +238,7 @@ export const MODELS: readonly WhisperModel[] = [
     fasterWhisperModel: "small",
     displayName: "Whisper Small",
     multilingual: true,
+    canTranslate: true,
     encoderParamsM: 88,
     decoderParamsM: 156,
     defaults: { wasm: WASM_Q8, webgpu: WEBGPU_FP16_Q4, webnn: WEBNN_FP16 },
@@ -237,6 +252,7 @@ export const MODELS: readonly WhisperModel[] = [
     fasterWhisperModel: "medium.en",
     displayName: "Whisper Medium (English)",
     multilingual: false,
+    canTranslate: false,
     encoderParamsM: 306,
     decoderParamsM: 463,
     defaults: { wasm: WASM_Q4, webgpu: ACCEL_Q4, webnn: ACCEL_Q4 },
@@ -246,6 +262,7 @@ export const MODELS: readonly WhisperModel[] = [
     fasterWhisperModel: "medium",
     displayName: "Whisper Medium",
     multilingual: true,
+    canTranslate: true,
     encoderParamsM: 306,
     decoderParamsM: 463,
     defaults: { wasm: WASM_Q4, webgpu: ACCEL_Q4, webnn: ACCEL_Q4 },
@@ -255,6 +272,9 @@ export const MODELS: readonly WhisperModel[] = [
     fasterWhisperModel: "large-v3-turbo",
     displayName: "Whisper Large v3 Turbo",
     multilingual: true,
+    // Not trained for translation (OpenAI's turbo model card); its
+    // "translate" output is unreliable (D-WS4a).
+    canTranslate: false,
     encoderParamsM: 635,
     decoderParamsM: 174,
     defaults: { wasm: WASM_Q4, webgpu: WEBGPU_FP16_Q4, webnn: WEBNN_FP16 },
@@ -274,6 +294,16 @@ export function getFasterWhisperModel(id: string): string | undefined {
   return getModel(id)?.fasterWhisperModel;
 }
 
+/**
+ * The task a run on `modelId` should actually use (D-WS4a): a "translate"
+ * left over from a model that could translate falls back to "transcribe" on
+ * one that cannot (large-v3-turbo, `.en`, unknown ids). App applies it on
+ * every model switch and again when building each run's options.
+ */
+export function taskForModel(modelId: string, task: WhisperTask): WhisperTask {
+  return task === "translate" && getModel(modelId)?.canTranslate !== true ? "transcribe" : task;
+}
+
 /** Default dtype for a model on a given device. Unknown ids fall back to q8. */
 export function resolveDefaultDtype(
   modelId: string,