Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/franckferman/whisper_transcriber
A tool to transcribe audio files using OpenAI's Whisper API.
https://github.com/franckferman/whisper_transcriber
audio audio-transcription openai openai-python openai-whisper python python-3 python-openai python-script python-wrapper python3 python3-wrapper transcription-processing transcription-tool whisper-ai whisper-integration whisper-transcriber
Last synced: 8 days ago
JSON representation
A tool to transcribe audio files using OpenAI's Whisper API.
- Host: GitHub
- URL: https://github.com/franckferman/whisper_transcriber
- Owner: franckferman
- License: agpl-3.0
- Created: 2024-11-09T04:02:48.000Z (11 days ago)
- Default Branch: main
- Last Pushed: 2024-11-09T04:04:55.000Z (11 days ago)
- Last Synced: 2024-11-09T05:18:27.448Z (11 days ago)
- Topics: audio, audio-transcription, openai, openai-python, openai-whisper, python, python-3, python-openai, python-script, python-wrapper, python3, python3-wrapper, transcription-processing, transcription-tool, whisper-ai, whisper-integration, whisper-transcriber
- Language: Python
- Homepage: https://github.com/franckferman/whisper_transcriber
- Size: 29.3 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Whisper Transcriber
**Whisper Transcriber** is a command-line application designed to transcribe audio files using OpenAI's Whisper API.
It includes features for language selection, logging, and cleanup of temporary files, with built-in checks for file validity and size before processing.
---
## Features
- Transcribe audio files using OpenAI's Whisper API.
- Language selection for transcription (`fr` for French, `en` for English).
- Logging for debugging and tracking transcription activities.
- Automatic cleanup of temporary files such as `.pyc`, `__pycache__`, etc.
---
## Installation
### Prerequisites
1. Clone the repository:
```bash
git clone https://github.com/franckferman/whisper-transcriber.git
cd whisper-transcriber
```
2. Install dependencies with [Poetry](https://python-poetry.org/):
```bash
poetry install
```
3. Alternatively, you can use pip:
```bash
pip install -r requirements.txt
```
---
## Usage
### Transcription
To transcribe an audio file, use the following command:
```bash
poetry run whisper-transcriber transcribe -f -k -l
```
#### Example
```bash
poetry run whisper-transcriber transcribe -f "audio/sample.mp3" -k "your_openai_api_key" -l "en"
```
#### Options
- `-f`, `--file`: Path to the audio file to transcribe.
- `-k`, `--key`: OpenAI API key for authentication.
- `-l`, `--lang`: Language code for transcription (`fr` or `en`).
- `-o`, `--output`: File path to save the transcription output as JSON.
- `--debug`: Enable debug logging, which creates a log file `transcription.log`.
### Cleanup
To remove temporary files and logs from the project directory:
```bash
poetry run whisper-transcriber clean --log
```
#### Options
- `--log`: Enable logging for the cleanup process.
---
## Development
### Running Tests
To test the transcription and cleanup functions, ensure all necessary dependencies are installed:
```bash
poetry install --with dev
```
Then, run tests using your preferred test runner.
### Formatting
- The project uses `black`, `flake8`, and `mypy` for formatting, linting, and type-checking.
- Format code with: `black .`
- Lint code with: `flake8 .`
- Type-check code with: `mypy .`
---
## License
This project is licensed under the GNU AGPLv3. See the `LICENSE` file for details.