874e5ef359
Replace the previous whisper.cpp-based word alignment with a fully ONNX-based implementation using onnxruntime-node and @huggingface/tokenizers. Add new Whisper ONNX model management, alignment mapping, and spectral analysis modules. Remove all code and documentation referencing whisper.cpp, update environment variables, Dockerfile, and docs to reflect ONNX-only alignment. Add unit tests for alignment and ONNX model logic.
21 lines
904 B
TypeScript
21 lines
904 B
TypeScript
import { test, expect } from '@playwright/test';
|
|
import {
|
|
mapWordsToSentenceOffsets,
|
|
} from '../../src/lib/server/whisper/alignment-mapping';
|
|
|
|
test.describe('whisper alignment mapping', () => {
|
|
test('maps words to sentence offsets with punctuation and repeated spaces', () => {
|
|
const aligned = mapWordsToSentenceOffsets('Hello, world again.', [
|
|
{ word: 'Hello', start: 0, end: 0.25 },
|
|
{ word: 'world', start: 0.25, end: 0.5 },
|
|
{ word: 'again', start: 0.5, end: 1.0 },
|
|
]);
|
|
|
|
expect(aligned.words).toHaveLength(3);
|
|
expect(aligned.words[0].charStart).toBe(0);
|
|
expect(aligned.words[0].charEnd).toBe(5);
|
|
expect(aligned.words[1].charStart).toBeGreaterThan(aligned.words[0].charEnd);
|
|
expect(aligned.words[2].charStart).toBeGreaterThan(aligned.words[1].charEnd);
|
|
expect(aligned.words[2].charEnd).toBeLessThanOrEqual('Hello, world again.'.length);
|
|
});
|
|
});
|