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

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Lucas WintherandClaude Opus 5.5 committed 2026-10-29 22:00:33 +01:00
1 parent f8ce3120fe
commit 2a4f5b16a5
3 files changed
+120 -1

No files matched your search

+52 -1
View File
@@ -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");