Run browser file transcription through the long-form pipeline when asked and the VAD model is available
Adds an Advanced "Skip silence in uploaded files" option (off by default pending measurement), the vad/longForm protocol fields, the old-path fallback when the VAD model is missing, and a plain message for files with no speech. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
0c3a83c23c
commit
f55ea6ecf8
14 files changed
+363
-8
No files matched your search
@@ -77,6 +77,15 @@ describe("BrowserEngine", () => {
|
||||
expect("modelId" in message).toBe(false);
|
||||
});
|
||||
|
||||
test("forwards the long-form request only when set (D-WS3a)", () => {
|
||||
const worker = new FakeWorker();
|
||||
const engine = new BrowserEngine(worker);
|
||||
void engine.transcribe(new Float32Array(4), { longForm: true });
|
||||
void engine.transcribe(new Float32Array(4));
|
||||
expect(worker.posted[0]!.message.longForm).toBe(true);
|
||||
expect("longForm" in worker.posted[1]!.message).toBe(false);
|
||||
});
|
||||
|
||||
test("asks the worker to stream only when a consumer listens", () => {
|
||||
const worker = new FakeWorker();
|
||||
const engine = new BrowserEngine(worker);
|
||||
|
||||
@@ -0,0 +1,55 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
import { emptyTranscriptNotice } from "../src/lib/export";
|
||||
import {
|
||||
LONG_FORM_DEFAULT,
|
||||
LONG_FORM_KEY,
|
||||
loadLongFormChoice,
|
||||
saveLongFormChoice,
|
||||
} from "../src/lib/longForm";
|
||||
|
||||
function memoryStorage(initial: Record<string, string> = {}) {
|
||||
const data = { ...initial };
|
||||
return {
|
||||
data,
|
||||
getItem: (key: string) => data[key] ?? null,
|
||||
setItem: (key: string, value: string) => {
|
||||
data[key] = value;
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
describe("long-form setting persistence (D-WS3a)", () => {
|
||||
test("defaults when nothing is stored or storage is unavailable", () => {
|
||||
expect(loadLongFormChoice(memoryStorage())).toBe(LONG_FORM_DEFAULT);
|
||||
expect(loadLongFormChoice(null)).toBe(LONG_FORM_DEFAULT);
|
||||
const throwing = {
|
||||
getItem: () => {
|
||||
throw new Error("denied");
|
||||
},
|
||||
setItem: () => {
|
||||
throw new Error("denied");
|
||||
},
|
||||
};
|
||||
expect(loadLongFormChoice(throwing)).toBe(LONG_FORM_DEFAULT);
|
||||
expect(() => saveLongFormChoice(true, throwing)).not.toThrow();
|
||||
});
|
||||
|
||||
test("round-trips an explicit choice", () => {
|
||||
const storage = memoryStorage();
|
||||
saveLongFormChoice(!LONG_FORM_DEFAULT, storage);
|
||||
expect(storage.data[LONG_FORM_KEY]).toBeDefined();
|
||||
expect(loadLongFormChoice(storage)).toBe(!LONG_FORM_DEFAULT);
|
||||
});
|
||||
});
|
||||
|
||||
describe("emptyTranscriptNotice (plan 001-0 Review Focus 4)", () => {
|
||||
test("a finished transcript with no words says so plainly", () => {
|
||||
expect(emptyTranscriptNotice({ text: "" })).toBe("No speech was found in this recording.");
|
||||
expect(emptyTranscriptNotice({ text: " \n" })).toBe("No speech was found in this recording.");
|
||||
});
|
||||
|
||||
test("no notice while running or when there is text", () => {
|
||||
expect(emptyTranscriptNotice(null)).toBeNull();
|
||||
expect(emptyTranscriptNotice({ text: " Hello." })).toBeNull();
|
||||
});
|
||||
});
|
||||
@@ -4,6 +4,7 @@ import {
|
||||
deviceAttempts,
|
||||
dtypeRequiresF16,
|
||||
initialLoadProgress,
|
||||
choosePipeline,
|
||||
isUiToWorkerMessage,
|
||||
isWorkerToUiMessage,
|
||||
TranscribeProgressTracker,
|
||||
@@ -35,7 +36,9 @@ describe("isUiToWorkerMessage", () => {
|
||||
{ type: "transcribe", audio: new Float32Array(8), requestId: "live-3" },
|
||||
{ type: "transcribe", audio: new Float32Array(8), requestId: "engine-1-1", stream: true },
|
||||
{ type: "transcribe", audio: new Float32Array(8), stream: false },
|
||||
{ type: "transcribe", audio: new Float32Array(8), stream: true, longForm: true },
|
||||
];
|
||||
loads.push({ type: "load", modelId: "onnx-community/whisper-base", device: "auto", vad: true });
|
||||
for (const message of [...loads, ...transcribes]) {
|
||||
expect(isUiToWorkerMessage(message)).toBe(true);
|
||||
}
|
||||
@@ -65,10 +68,26 @@ describe("isUiToWorkerMessage", () => {
|
||||
expect(
|
||||
isUiToWorkerMessage({ type: "transcribe", audio: new Float32Array(4), stream: "yes" }),
|
||||
).toBe(false);
|
||||
expect(
|
||||
isUiToWorkerMessage({ type: "transcribe", audio: new Float32Array(4), longForm: 1 }),
|
||||
).toBe(false);
|
||||
expect(isUiToWorkerMessage({ type: "load", modelId: "x", device: "auto", vad: "yes" })).toBe(
|
||||
false,
|
||||
);
|
||||
expect(isUiToWorkerMessage({ type: "result", text: "", chunks: [] })).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("choosePipeline (D-WS3a/D-WS3b)", () => {
|
||||
test("long-form only when asked for and the VAD model loaded", () => {
|
||||
expect(choosePipeline({ longForm: true, vadReady: true })).toBe("longform");
|
||||
// Offline / never downloaded: the old path, never an error (Review Focus 3).
|
||||
expect(choosePipeline({ longForm: true, vadReady: false })).toBe("chunked");
|
||||
expect(choosePipeline({ longForm: false, vadReady: true })).toBe("chunked");
|
||||
expect(choosePipeline({ longForm: undefined, vadReady: true })).toBe("chunked");
|
||||
});
|
||||
});
|
||||
|
||||
describe("isWorkerToUiMessage", () => {
|
||||
test("accepts every worker → UI message shape", () => {
|
||||
const messages: WorkerToUiMessage[] = [
|
||||
|
||||
Reference in new issue
Block a user