A transcript pipeline that starts with the audio
loveparade shares a personal transcription workflow: download the audio, transcribe it with Qwen ASR, then use a separate model to clean up and format the result. They report good results at a few cents per video; that is their experience, not a general cost benchmark.
Original excerptOriginal discussionAsk HN: Anyone set up ways to easily obtain and read transcripts from Ted, YT?“I have built my own pipeline for this because in my experience the YouTube auto transcripts are quite bad. I download the raw audio”
Read the full original