From cfd6bdda2192558352d04c4086ed838793e9b535 Mon Sep 17 00:00:00 2001 From: Jong Wook Kim Date: Thu, 22 Sep 2022 02:58:56 +0900 Subject: [PATCH] a note on speed-accuracy tradeoffs --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index fa98376..9566a7f 100644 --- a/README.md +++ b/README.md @@ -37,7 +37,7 @@ choco install ffmpeg ## Command-line usage -The following command will transcribe speech in audio files, using the `medium` model: +There are five model sizes, four with English-only versions, offering speed and accuracy tradeoffs. The following command will transcribe speech in audio files, using the `medium` model: whisper audio.flac audio.mp3 audio.wav --model medium @@ -49,7 +49,7 @@ Adding `--task translate` will translate the speech into English: whisper japanese.wav --language Japanese --task translate -Run the following to view all available transcription options: +Run the following to view all available options: whisper --help