QUICKROUTER · AUDIO LAB / 06
Whisper 长音频分块转录:切片清单、时间偏移与边界核对
39.047 秒16000 Hz · 1 声道 · PCM16macOS say 原创练习音频01 / 可下载原始输入
First, copy the recording into a new folder. Keep the original file unchanged. Next, transcribe the second section. If the task fails, save the error message. Finally, combine the sections in order. Check the boundary before publishing. First, copy the recording into a new folder. Keep the original
02 / 本任务执行入口
python chunks.py input.wav --seconds 15 python chunk-run.py chunks.json python check.py
波形读取真实 WAV 样本绘制。原文为人工写作的朗读输入,不能作为模型成功输出。