Automatic Japanese Text Transcription from Audio Files with whisper.cpp
I’ll introduce how I used the OSS whisper.cpp to automatically transcribe audio files to Japanese text.
ffmpeg -i input.m4a -ar 16000 output_16khz.wav
git clone https://github.com/ggerganov/whisper.cpp.git
cd whisper.cpp
bash ./models/download-ggml-model.sh large
make
./main -m models/ggml-large.bin -f output_16khz.wav -l ja
That’s all from the Gemba.