Function parseWhisperCpp

packages/cli/src/whisper/normalize.ts:125–168

(data: Record<string, unknown>)

}

function parseWhisperCpp(data: Record<string, unknown>): Word[] {
  const words: Word[] = [];
  const transcription = data.transcription as Array<{
    tokens?: Array<{
      text?: string;
      offsets?: { from?: number; to?: number };
    }>;
  }>;

  for (const seg of transcription ?? []) {
    for (const token of seg.tokens ?? []) {
      const rawText = token.text ?? "";
      const text = rawText.trim();
      if (!text || text.startsWith("[_") || text.startsWith("[BLANK")) continue;

      const lastWord = words[words.length - 1];

      // Merge into previous word when the token is a sub-word continuation,
      // trailing punctuation, or a contraction suffix.
      // Whisper uses leading spaces to mark word boundaries in all languages.
      const shouldMerge =
        lastWord &&
        (!rawText.startsWith(" ") ||
          /^[.,!?;:'")\]}>…–—¡¿-]+$/.test(text) ||
          /^'(t|m|s|ve|re|ll|d)$/i.test(text));
      if (shouldMerge) {
        lastWord.text += text;
        lastWord.end = round3((token.offsets?.to ?? 0) / 1000);
        continue;
      }

      words.push({
        text,
        start: round3((token.offsets?.from ?? 0) / 1000),
        end: round3((token.offsets?.to ?? 0) / 1000),
      });
    }
  }

  mergeFragments(words);
  interpolateZeroDuration(words);

  return words;
}

function parseOpenAI(data: Record<string, unknown>): Word[] {
  const words = (data.words ?? []) as Array<{