Function loadTranscript

packages/cli/src/whisper/normalize.ts:448–478

(filePath: string)

 * - Pre-normalized JSON array ([{text, start, end}])
 */
export function loadTranscript(filePath: string): { words: Word[]; format: TranscriptFormat } {
  const ext = extname(filePath).toLowerCase();
  const content = readFileSync(filePath, "utf-8");

  if (ext === ".srt") {
    const words = parseSrt(content).map((w, i) => ({ ...w, id: w.id ?? `w${i}` }));
    return { words, format: "srt" };
  }
  if (ext === ".vtt") {
    const words = parseVtt(content).map((w, i) => ({ ...w, id: w.id ?? `w${i}` }));
    return { words, format: "vtt" };
  }

  // JSON formats — parse once, detect, then extract words
  const parsed = JSON.parse(content);
  const format = detectJsonFormat(parsed);

  const words =
    format === "whisper-cpp"
      ? parseWhisperCpp(parsed)
      : format === "openai"
        ? parseOpenAI(parsed)
        : (parsed as Word[]).map((w) => ({
            id: w.id ?? "",
            text: w.text.trim(),
            start: round3(w.start),
            end: round3(w.end),
          }));

  return { words, format };
}

/**
 * Remove words that fall before the detected speech onset.