From ddf4c660a2bd859fd1ab73ff9fa6e1064498ed76 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Kristofer=20Rolf=20S=C3=B6derstr=C3=B6m?= Date: Wed, 22 Mar 2023 11:36:02 +0100 Subject: [PATCH] Update README.md --- README.md | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 2605c8f..9b32e4b 100644 --- a/README.md +++ b/README.md @@ -1,2 +1,19 @@ -# transcribe -Simple implementation of OpenAI's whisper model to transcribe audio files from your local folders. +## transcribe +Simple implementation of OpenAI's Whisper to transcribe audio files from your local folders. + +### Instructions +#### Using the script +1. This package was made and tested in an Anaconda environment, if you're not familiar with python I would recommend this method. +See [here](https://docs.anaconda.com/anaconda/install/index.html) for instructions. +2. This is a simple script with no installation. Simply download the .py file into your work folder. Then you can either import it to another script or notebook for use. I recommend jupyter notebook for new users. +#### Requirements +1. Whisper requires some additional libraries. The [setup](https://github.com/openai/whisper#setup) page states: "The codebase also depends on a few Python packages, most notably HuggingFace Transformers for their fast tokenizer implementation and ffmpeg-python for reading audio files." +Users might not need to specifically install Transfomers. However, a conda installation might be needed for ffmepg, which takes care of setting up PATH variables. Install with: +´´´ + conda install -c conda-forge ffmpeg-python + ´´ +3. The main functionality comes from openai-whisper. See their [page](https://github.com/openai/whisper) for details. As of 2023-03-22 you can install via: +´´´ +pip install -U openai-whisper +´´´ +