From 314e8e4cd13a65f5448eb22baccb8cc2f44964cd Mon Sep 17 00:00:00 2001 From: BBC-Esq Date: Fri, 27 Oct 2023 12:24:58 -0400 Subject: [PATCH] Update README.md --- README.md | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index e762c34..6ab89e9 100644 --- a/README.md +++ b/README.md @@ -2,12 +2,13 @@ ### Record audio and save a transcription to your system's clipboard with ctranslate2 and faster-whisper. ## Prerequisites -> Tested on [Python 3.10.11](https://www.python.org/downloads/release/python-31011/). -> You must have both [Git](https://git-scm.com/downloads) and [git-lfs](https://git-lfs.com/) installed.
-> If you intend to use CUDA acceleration, you must also install [CUDA 11.8](https://developer.nvidia.com/cuda-11-8-0-download-archive). - > * Unfortunately, Ctranslate2 does not currently support GPU-acceleration on AMD GPUs or Apple's Metal/MPS. However, CPU acceleration still works. +### Tested on [Python 3.10.11](https://www.python.org/downloads/release/python-31011/). +### You must have both [Git](https://git-scm.com/downloads) and [git-lfs](https://git-lfs.com/) installed. +### If you intend to use CUDA acceleration, you must also install [CUDA 11.8](https://developer.nvidia.com/cuda-11-8-0-download-archive). +* Unfortunately, Ctranslate2 does not currently support GPU-acceleration on AMD GPUs or Apple's Metal/MPS. However, CPU acceleration still works for Intel, AMD, and Apple CPUs. ## Installation +> NOTE: For any ```python``` or ```pip``` commands in these instructions, if you still have Python 2 installed, make sure and run ```python3``` and ```pip3``` instead to make sure the correct Python interpreter is used. Step 1 - Download the latest release and unzip the files to your chosen directory. @@ -15,7 +16,6 @@ Step 2 - Navigate to the folder with ```ct2_main.py``` in it, open a command pro ``` python -m venv . ``` - > NOTE: For any ```python``` or ```pip``` commands in these instructions, if you still have Python 2 installed, make sure and run ```python3``` and ```pip3``` instead to make sure the correct Python interpreter is used. Step 3 - Activate the virtual environment: ``` @@ -46,8 +46,8 @@ Within the virtual environment run this command: ``` python ct2_main.py ``` -The first time using the program, I recommend using the default settings and clicking "Update Settings" button to download the model. After that, simply change the settings and click "Update Settings" for them to take effect.

-Now just use ```control + v``` or right click "paste" after the transcription is saved to the clipboard; for example, into the chat box for your LLM! +The first time using the program, click "Update Settings" button to download the model. After that, you can change the model and quantization (and device) by simply changing the settings and clicking "Update Settings" again.

+Click start recording, speak, then stop recording. Then just use ```control + v``` or right click "paste" the transcription into wherever you want; for example, into the chat box for your LLM!

Remember, anytime you want to restart the program, make sure to activate the virtual environment first! ## Contact