# whisper
- <https://www.swyx.io/whisper-for-podcasts>
- ```
```
cd /Users/codeanand/code/toys/whisper.cpp
./main -m models/ggml-base.en.bin -f samples/jfk.wav --print-colors
```
- to convert to .wav
-
```
ffmpeg -i input.mp3 -ar 16000 -ac 1 -c:a pcm_s16le output.wav
```
more info here
https://github.com/ggerganov/whisper.cpp?tab=readme-ov-file
to get the youtube video
youtube-dl -x --audio-format mp3 'https://www.youtube.com/watch?v=TM9AfKxpYQU'
Fast version when you see
```
whisper_init_state: kv cross size = 18.43 MB
whisper_init_state: loading Core ML model from 'models/ggml-base.en-encoder.mlmodelc'
whisper_init_state: first run on a device may take a while ...
```