Add Danish fine-tune catalog entries under a single pending Hugging Face owner constant

Co-Authored-By: Claude Opus 5.5 <[email protected]>

docs/Decisions.md

@@ -1224,3 +1224,19 @@ whole-file output is equally bad, which is exactly what the absolute bar
 exists to catch.
 **Consequence:** full `bun test` ≈ 19 min on CPU (en_alien ≈ 20 min of it
 on a cold run); the fast suite excludes this file.
+
+## D-WS6a — Danish fine-tuned Whisper models: our own ONNX + CTranslate2 conversions, unpublished until the owner says go
+**Status:** Proposed (2026-10-29, spec 001 Goal 6)
+**Candidates checked (licence + architecture, from each repo's model card, config and notices):**
+- `thorhojhus/whisper-small-danish` — MIT; plain `WhisperForConditionalGeneration`, whisper-small
+  shapes and tokenizer unchanged (80 mel bins, 12/12 layers, vocab 51865). **Kept.**
+- `thorhojhus/whisper-large-v3-turbo-danish` — MIT; plain large-v3-turbo (128 mel, 32/4 layers,
+  vocab 51866). **Kept.**
+- `danish-foundation-models/edda-v0.2` — **Apache-2.0 confirmed** (licensor: the Alexandra
+  Institute; base model MIT); plain large-v3-turbo architecture, so Transformers.js loads it like the
+  stock turbo. Its `generation_config.json` pins `language: "da"`, `task: "transcribe"` and
+  `num_beams: 5`. **Kept.**
+**Catalog:** three entries with `verified: false` everywhere, ids built from one exported constant
+`DANISH_MODELS_HF_OWNER` (placeholder `"PENDING-OWNER"`): `<owner>/<name>-ONNX` for the browser
+engine and `<owner>/<name>-ct2-int8` as `fasterWhisperModel` (a Hub repo id — faster-whisper accepts
+those as well as its aliases). Publishing under the owner's account is a one-line change.

src/lib/models.ts

@@ -164,6 +164,27 @@ const ACCEL_Q4: DtypeDefault = {
   note: "q4: the medium fp16 conversions fail to load / overflow (D-022).",
 };
 
+// ---------------------------------------------------------------------------
+// Danish fine-tunes (D-WS6a)
+// ---------------------------------------------------------------------------
+
+/**
+ * Hugging Face account that hosts our conversions of the Danish Whisper
+ * fine-tunes (D-WS6a). Both the ONNX repos (browser engine) and the
+ * CTranslate2 int8 repos (server engine) hang off this one value, so
+ * publishing under the owner's account is a one-line change here. Until the
+ * owner confirms the account and the repos exist, it stays a placeholder.
+ */
+export const DANISH_MODELS_HF_OWNER = "PENDING-OWNER";
+
+/** Catalog id + matching faster-whisper repo for one published conversion. */
+function danishRepos(name: string): Pick<WhisperModel, "id" | "fasterWhisperModel"> {
+  return {
+    id: `${DANISH_MODELS_HF_OWNER}/${name}-ONNX`,
+    fasterWhisperModel: `${DANISH_MODELS_HF_OWNER}/${name}-ct2-int8`,
+  };
+}
+
 // ---------------------------------------------------------------------------
 // The catalog (D-006: curated, not exhaustive)
 // ---------------------------------------------------------------------------
@@ -259,6 +280,37 @@ export const MODELS: readonly WhisperModel[] = [
     decoderParamsM: 174,
     defaults: { wasm: WASM_Q4, webgpu: WEBGPU_FP16_Q4, webnn: WEBNN_FP16 },
   },
+  // Danish fine-tunes (D-WS6a): unchanged Whisper architectures, so the
+  // parameter counts are their base models'. Conversions by us, weights by
+  // the original authors (credited in each published repo's model card).
+  {
+    // thorhojhus/whisper-small-danish (MIT), fine-tune of whisper-small.
+    ...danishRepos("whisper-small-danish"),
+    displayName: "Whisper Small (Danish)",
+    multilingual: true,
+    encoderParamsM: 88,
+    decoderParamsM: 156,
+    defaults: { wasm: WASM_Q8, webgpu: WEBGPU_FP16_Q4, webnn: WEBNN_FP16 },
+  },
+  {
+    // thorhojhus/whisper-large-v3-turbo-danish (MIT).
+    ...danishRepos("whisper-large-v3-turbo-danish"),
+    displayName: "Whisper Large v3 Turbo (Danish)",
+    multilingual: true,
+    encoderParamsM: 635,
+    decoderParamsM: 174,
+    defaults: { wasm: WASM_Q4, webgpu: WEBGPU_FP16_Q4, webnn: WEBNN_FP16 },
+  },
+  {
+    // danish-foundation-models/edda-v0.2 (Apache-2.0, Alexandra Institute),
+    // fine-tune of whisper-large-v3-turbo.
+    ...danishRepos("edda-v0.2"),
+    displayName: "Edda v0.2 (Danish)",
+    multilingual: true,
+    encoderParamsM: 635,
+    decoderParamsM: 174,
+    defaults: { wasm: WASM_Q4, webgpu: WEBGPU_FP16_Q4, webnn: WEBNN_FP16 },
+  },
 ];
 
 export function getModel(id: string): WhisperModel | undefined {

tests/models.test.ts

@@ -1,5 +1,6 @@
 import { describe, test, expect } from "bun:test";
 import {
+  DANISH_MODELS_HF_OWNER,
   DEFAULT_MODEL_ID,
   MODELS,
   WHISPER_LANGUAGES,
@@ -32,6 +33,9 @@ describe("MODELS catalog", () => {
       "onnx-community/whisper-medium.en_timestamped",
       "onnx-community/whisper-medium-ONNX",
       "onnx-community/whisper-large-v3-turbo",
+      `${DANISH_MODELS_HF_OWNER}/whisper-small-danish-ONNX`,
+      `${DANISH_MODELS_HF_OWNER}/whisper-large-v3-turbo-danish-ONNX`,
+      `${DANISH_MODELS_HF_OWNER}/edda-v0.2-ONNX`,
     ]);
     expect(new Set(ids).size).toBe(ids.length);
   });
@@ -70,7 +74,9 @@ describe("MODELS catalog", () => {
   });
 
   test("every model maps to a faster-whisper name for the server engine (D-013)", () => {
-    for (const model of MODELS) {
+    // The Danish conversions (D-WS6a) have no faster-whisper alias; their
+    // server-engine name is a Hub repo id — covered by the Danish suite below.
+    for (const model of MODELS.filter((m) => !m.id.startsWith(`${DANISH_MODELS_HF_OWNER}/`))) {
       // The onnx-community ids and faster-whisper's aliases share the same
       // size suffix ("tiny.en", …, "large-v3-turbo") once repo-name
       // decorations ("_timestamped", "-ONNX") are stripped; keeping them
@@ -86,6 +92,51 @@ describe("MODELS catalog", () => {
   });
 });
 
+describe("Danish fine-tune conversions (D-WS6a)", () => {
+  const owner = `${DANISH_MODELS_HF_OWNER}/`;
+  const danish = MODELS.filter((model) => model.id.startsWith(owner));
+
+  test("are published under one owner constant, still a placeholder until the owner confirms", () => {
+    expect(DANISH_MODELS_HF_OWNER).toBe("PENDING-OWNER");
+    expect(danish.map((model) => model.id)).toEqual([
+      `${owner}whisper-small-danish-ONNX`,
+      `${owner}whisper-large-v3-turbo-danish-ONNX`,
+      `${owner}edda-v0.2-ONNX`,
+    ]);
+  });
+
+  test("point the server engine at the matching CTranslate2 int8 conversion under the same owner", () => {
+    for (const model of danish) {
+      const ct2 = model.id.replace(/-ONNX$/, "-ct2-int8");
+      expect(model.fasterWhisperModel).toBe(ct2);
+      expect(getFasterWhisperModel(model.id)).toBe(ct2);
+    }
+  });
+
+  test("are multilingual (language/task are sent) and unverified on every device", () => {
+    for (const model of danish) {
+      expect(model.multilingual).toBe(true);
+      for (const device of ["wasm", "webgpu", "webnn"] as const) {
+        expect(model.defaults[device].verified).toBe(false);
+      }
+    }
+  });
+
+  test("share their base model's parameter counts (unchanged architecture)", () => {
+    const small = getModel("onnx-community/whisper-small")!;
+    const turbo = getModel("onnx-community/whisper-large-v3-turbo")!;
+    const [smallDa, turboDa, edda] = danish;
+    for (const [model, base] of [
+      [smallDa!, small],
+      [turboDa!, turbo],
+      [edda!, turbo],
+    ] as const) {
+      expect(model.encoderParamsM).toBe(base.encoderParamsM);
+      expect(model.decoderParamsM).toBe(base.decoderParamsM);
+    }
+  });
+});
+
 describe("resolveDefaultDtype", () => {
   test("WASM defaults: q8 for small models, q4 for large ones", () => {
     expect(resolveDefaultDtype("onnx-community/whisper-tiny.en", "wasm")).toBe("q8");