diff --git a/src/lib/models.ts b/src/lib/models.ts index 1e81c90..ad5702e 100644 --- a/src/lib/models.ts +++ b/src/lib/models.ts @@ -179,12 +179,12 @@ const ACCEL_Q4: DtypeDefault = { /** * 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. + * fine-tunes (D-WS6a). Both the ONNX repo (browser engine) and the + * CTranslate2 int8 repo (server engine) hang off this one value. Only + * whisper-small-danish is published: the turbo fine-tunes (turbo-danish, + * edda-v0.2) showed no clear gain over stock turbo on our Danish clip. */ -export const DANISH_MODELS_HF_OWNER = "PENDING-OWNER"; +export const DANISH_MODELS_HF_OWNER = "lucasw89"; /** * WASM default for the Danish conversions (D-WS6a): measured on our own files @@ -311,8 +311,8 @@ 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 + // Danish fine-tune (D-WS6a): unchanged Whisper architecture, so the + // parameter counts are its base model's. 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. @@ -325,29 +325,6 @@ export const MODELS: readonly WhisperModel[] = [ decoderParamsM: 156, defaults: { wasm: DANISH_WASM_Q4, 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, - // Translation untested on these fine-tunes (spec 001, D-WS4a). - canTranslate: false, - encoderParamsM: 635, - decoderParamsM: 174, - defaults: { wasm: DANISH_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, - // Translation untested on these fine-tunes (spec 001, D-WS4a). - canTranslate: false, - encoderParamsM: 635, - decoderParamsM: 174, - defaults: { wasm: DANISH_WASM_Q4, webgpu: WEBGPU_FP16_Q4, webnn: WEBNN_FP16 }, - }, ]; export function getModel(id: string): WhisperModel | undefined { diff --git a/tests/models.test.ts b/tests/models.test.ts index da7aae4..4110785 100644 --- a/tests/models.test.ts +++ b/tests/models.test.ts @@ -35,8 +35,6 @@ describe("MODELS catalog", () => { "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`, - `${DANISH_MODELS_HF_OWNER}/edda-v0.2-ONNX`, ]); expect(new Set(ids).size).toBe(ids.length); }); @@ -97,13 +95,9 @@ describe("Danish fine-tune conversions (D-WS6a)", () => { const owner = `${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`, - `${owner}edda-v0.2-ONNX`, - ]); + test("only whisper-small-danish is published (the turbo fine-tunes showed no clear gain), under lucasw89", () => { + expect(DANISH_MODELS_HF_OWNER).toBe("lucasw89"); + expect(danish.map((model) => model.id)).toEqual([`${owner}whisper-small-danish-ONNX`]); }); test("point the server engine at the matching CTranslate2 int8 conversion under the same owner", () => { @@ -125,16 +119,9 @@ describe("Danish fine-tune conversions (D-WS6a)", () => { 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); - } + const [smallDa] = danish; + expect(smallDa!.encoderParamsM).toBe(small.encoderParamsM); + expect(smallDa!.decoderParamsM).toBe(small.decoderParamsM); }); test("default to the dtypes measured on the converted files (D-WS6a)", () => {