kobim/whisper-local-transcribe
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Kristofer Rolf Söderström
2023-03-22 13:24:41 +01:00
committed by GitHub
parent 476547af7d
commit 03fcd5798f
1 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@@ -3,19 +3,20 @@ Simple implementation of OpenAI's Whisper to transcribe audio files from your lo
### Instructions ### Instructions
#### Requirements #### 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." 1. This script was made and tested in an Anaconda environment with python 3.10, if you're not familiar with python I would recommend this method.
See [here](https://docs.anaconda.com/anaconda/install/index.html) for instructions. You might need administrator rights.
2. 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: 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 conda install -c conda-forge ffmpeg-python
``` ```
More advanced users can use ```pip install ffmpeg-python``` but be ready to deal with some [PATH issues](https://stackoverflow.com/questions/65836756/python-ffmpeg-wont-accept-path-why), which I encountered in Windows 11.
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: 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 pip install -U openai-whisper
``` ```
#### Using the script #### 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. 1. This is a simple script with no installation. You can either clone the repository with
See [here](https://docs.anaconda.com/anaconda/install/index.html) for instructions. You might need administrator rights.
2. This is a simple script with no installation. You can either clone the repository with
``` ```
git clone https://github.com/soderstromkr/transcribe.git git clone https://github.com/soderstromkr/transcribe.git
``` ```