Function parseSrt

packages/cli/src/whisper/normalize.ts:186–215

(content: string)

}

function parseSrt(content: string): Word[] {
  // SRT doesn't have word-level timestamps — parse as phrase-level entries.
  // Each cue becomes one "word" entry (the full phrase).
  const blocks = content.trim().split(/\n\n+/);
  const words: Word[] = [];

  for (const block of blocks) {
    const lines = block.trim().split("\n");
    // SRT format: index, timestamp line, text lines
    const timeLine = lines.find((l) => l.includes("-->"));
    if (!timeLine) continue;

    const [startStr, endStr] = timeLine.split("-->").map((s) => s.trim());
    if (!startStr || !endStr) continue;

    const text = lines
      .slice(lines.indexOf(timeLine) + 1)
      .join(" ")
      .replace(/<[^>]+>/g, "") // strip HTML tags
      .trim();
    if (!text) continue;

    words.push({
      text,
      start: parseSrtTimestamp(startStr),
      end: parseSrtTimestamp(endStr),
    });
  }
  return words;
}

function parseVtt(content: string): Word[] {
  // Strip the WEBVTT header and any metadata blocks