]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
whisper : add option to speed up the audio tempo by x2
authorGeorgi Gerganov <redacted>
Sat, 12 Nov 2022 16:03:49 +0000 (18:03 +0200)
committerGeorgi Gerganov <redacted>
Sun, 13 Nov 2022 14:25:43 +0000 (16:25 +0200)
commit83c742f1a78a018c4eac790fabab91f174d92c3a
tree2a4d682513f1d63fb5b6d63245cecee70375ae7f
parent41b48ab7f1a0a1f0acd4784f1eec534a235e960f
whisper : add option to speed up the audio tempo by x2

Using a Phase Vocoder for speeding up the audio tempo by scaling down
the frequencies in the frequency domain.

This reduces the computation in the Encoder by a factor of 2.
The transcription accuracy is degraded, but for slow to normal speech -
it seems to be still very good.

I think this can find application for real-time transcription - i.e. the
"stream" example.
examples/main/main.cpp
examples/stream/stream.cpp
whisper.cpp
whisper.h