47 lines
1.7 KiB
TypeScript
47 lines
1.7 KiB
TypeScript
import { describe, expect, test } from "bun:test";
|
|
import { deflateSync } from "node:zlib";
|
|
import {
|
|
compressionRatio,
|
|
DEFAULT_FALLBACK,
|
|
needsFallback,
|
|
} from "../src/worker/longform/quality";
|
|
|
|
describe("compressionRatio (faster-whisper get_compression_ratio)", () => {
|
|
test("matches zlib.compress on the same bytes", async () => {
|
|
const text = "The problem I find with AI is that it is probably a bit overhyped.";
|
|
const bytes = new TextEncoder().encode(text);
|
|
expect(await compressionRatio(text)).toBeCloseTo(
|
|
bytes.length / deflateSync(bytes).length,
|
|
5,
|
|
);
|
|
});
|
|
|
|
test("a repetition loop compresses far above 2.4, normal speech below", async () => {
|
|
expect(await compressionRatio("the main clar, ".repeat(40))).toBeGreaterThan(2.4);
|
|
expect(
|
|
await compressionRatio(
|
|
"På Aarhus Festuges sekretariat har vi løbet rigtig stærkt de sidste måneder.",
|
|
),
|
|
).toBeLessThan(2.4);
|
|
});
|
|
|
|
test("empty text is not a loop", async () => {
|
|
expect(await compressionRatio("")).toBe(0);
|
|
});
|
|
});
|
|
|
|
describe("needsFallback", () => {
|
|
test("uses the spec thresholds by default", () => {
|
|
expect(DEFAULT_FALLBACK.compressionRatioThreshold).toBe(2.4);
|
|
expect(DEFAULT_FALLBACK.logProbThreshold).toBe(-1.0);
|
|
expect(DEFAULT_FALLBACK.temperatures).toEqual([0, 0.2, 0.4, 0.6, 0.8, 1.0]);
|
|
});
|
|
|
|
test("rejects a high compression ratio or a low average log-prob", () => {
|
|
expect(needsFallback({ compressionRatio: 3.1, avgLogProb: -0.2 })).toBe(true);
|
|
expect(needsFallback({ compressionRatio: 1.5, avgLogProb: -1.5 })).toBe(true);
|
|
expect(needsFallback({ compressionRatio: 1.5, avgLogProb: -0.3 })).toBe(false);
|
|
expect(needsFallback({ compressionRatio: 1.5, avgLogProb: null })).toBe(false);
|
|
});
|
|
});
|