I’ll introduce how I used the OSS whisper.cpp to automatically transcribe audio files to Japanese text.

Preparation: Prepare a 16kHz .wav File

ffmpeg -i input.m4a -ar 16000 output_16khz.wav

Download whisper.cpp

git clone https://github.com/ggerganov/whisper.cpp.git  
cd whisper.cpp

Download the Whisper Model

bash ./models/download-ggml-model.sh large

Build

make

Transcribe Audio from WAV File to Text

./main -m models/ggml-large.bin -f output_16khz.wav -l ja

That’s all from the Gemba.