From de329b78161d5174d0064872877a5c5936a51354 Mon Sep 17 00:00:00 2001 From: Fujimoto Seiji Date: Fri, 4 Apr 2025 01:21:00 +0000 Subject: [PATCH] Document how to prepare `whisper-cli` and model files Feedback from Daniel Bevenius. This adds a short code example how to prepare the `whisper-cli` command, to make the initial setup step a little bit clearer. Signed-off-by: Fujimoto Seiji --- tests/librispeech/README.md | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tests/librispeech/README.md b/tests/librispeech/README.md index f6ac8c3d..026605ce 100644 --- a/tests/librispeech/README.md +++ b/tests/librispeech/README.md @@ -11,7 +11,14 @@ performance of whisper.cpp on LibriSpeech corpus. 1. (Pre-requirement) Compile `whisper-cli` and prepare the Whisper model in `ggml` format. - - Consult [whisper.cpp/README.md](../../README.md). + ``` + $ # Execute the commands below in the project root dir. + $ cmake -B build + $ cmake --build build --config Release + $ ./models/download-ggml-model.sh tiny + ``` + + Consult [whisper.cpp/README.md](../../README.md) for more details. 2. Download the audio files from LibriSpeech project.