https://github.com/ggerganov/whisper.cpp/tree/master/examples/server
- whisper.cpp setup
- server build and run
$ make server
$ ./server -m ./models/ggml-large-v3.bin -l ja
- voice record server
$ python3 -m http.server
// index.html
const wavBuffer = vad.utils.encodeWAV(arr, 1, 16000, 1, 16)
Stream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, 1 channels, s16, 256 kb/s