https://github.com/BBC-Esq/ctranslate2-faster-whisper-transcriber
Record audio and save a transcription to your system's clipboard with ctranslate2 and faster-whisper.
https://github.com/BBC-Esq/ctranslate2-faster-whisper-transcriber
audio-recorder audio-transcribing audio-transcription ctranslate2 faster-whisper transcribe transcriber
Last synced: 8 months ago
JSON representation
Record audio and save a transcription to your system's clipboard with ctranslate2 and faster-whisper.
- Host: GitHub
- URL: https://github.com/BBC-Esq/ctranslate2-faster-whisper-transcriber
- Owner: BBC-Esq
- Created: 2023-10-02T17:14:45.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-10-16T03:30:29.000Z (about 1 year ago)
- Last Synced: 2024-10-17T17:06:48.107Z (about 1 year ago)
- Topics: audio-recorder, audio-transcribing, audio-transcription, ctranslate2, faster-whisper, transcribe, transcriber
- Language: Python
- Homepage:
- Size: 225 KB
- Stars: 58
- Watchers: 4
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Record and Transcribe Audio Using Ctranslate2!
1. Transcribe voice to clipbord.
2. Paste into your favorite LLM.
3. Save time.
## Requirments
1) [Python 3.11](https://www.python.org/downloads/release/python-3119/) or [Python 3.12](https://www.python.org/downloads/release/python-3129/)
2) [Git](https://git-scm.com/downloads)
3) [git-lfs](https://git-lfs.com/)
4) Windows
> I am open to Linux and MacOS support but would need someone to help me test it.
# Installation
### Step 1
Download the latest release (i.e. the .zip file) and extract its contents to your computer. Then navigate to the folder containing ```ct2_main.py``` and create a virtual environment.
```
python -m venv .
```
### Step 2
Activate the virtual environment.
```
.\Scripts\activate
```
### Step 3
Run the installation script.
```
python setup.py
```
# Usage
### Step 1
Activate the virtual environment and start the program:
```
python ct2_main.py
```
### Step 2
Choose the Whisper model you want to use and click "Update Settings". The first time you choose a particular model it will automatically download it.
### Step 3
Start recording...speak...stop recording, then use ```control + v``` or right-click and "paste" the transcription into whatever program you want; for example, into the browser window for ChatGPT.
# Creating an .exe file
```
pyinstaller --onefile ct2_main.py
```