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

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

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,