whisperx_transcription
Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revision | |||
| whisperx_transcription [2026/10/10 17:18] – external edit (Unknown date) 127.0.0.1 | whisperx_transcription [2026/10/10 17:20] (current) – [Local Speech-to-Text with WhisperX] millerjs | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| ====== Local Speech-to-Text with WhisperX ====== | ====== Local Speech-to-Text with WhisperX ====== | ||
| - | I had a batch of meeting recordings (2-3 speakers, 45-60 minutes each) that I wanted to transcribe with speaker identification — you know, "who said what and when." I didn't want to upload any of it to a cloud service, so I went looking for something that would run entirely locally on my desktop. I found [[https:// | + | This is running on a SFF Optiplex 7070 with an i5-9500 (6 cores / 6 threads, AVX2, 32 GB RAM, Debian 13). No GPU, no cloud, just the CPU. A 50-minute recording takes about 48 minutes end-to-end with the large-v3 model in int8 mode. Not fast, but the machine is usually idle so I just kick it off and walk away. At some point I'd like to put a low profile GPU in here to help with accelerating these kinds of tasks, but this works fine for now. |
| - | + | ||
| - | This is running on my i5-9500 | + | |
| ===== System Prerequisites ===== | ===== System Prerequisites ===== | ||
whisperx_transcription.1791652691.txt.gz · Last modified: by 127.0.0.1