https://github.com/ajxv/rtstt
Real time speech to text transcription using OpenAi whisper
https://github.com/ajxv/rtstt
live-transcription openai openai-whisper python3 transcription whisper
Last synced: 6 months ago
JSON representation
Real time speech to text transcription using OpenAi whisper
- Host: GitHub
- URL: https://github.com/ajxv/rtstt
- Owner: ajxv
- License: mit
- Created: 2024-11-04T10:47:34.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2024-11-18T16:51:11.000Z (11 months ago)
- Last Synced: 2025-02-14T11:51:53.761Z (8 months ago)
- Topics: live-transcription, openai, openai-whisper, python3, transcription, whisper
- Language: HTML
- Homepage:
- Size: 25.4 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Real Time Speech To Text (Using OpenAi Whisper)
## Requirements
- Python 3.1x
## Setting Up
- Install requirements using `pip install -r requirements.txt`
## Running the Application
- Run the flask app using `python3 app.py`
## Selecting the Appropriate Model
Whisper offers several models that balance speed and accuracy:
- `tiny`: Fastest but least accurate
- `base`: A balance between speed and accuracy
- `small`: More accurate, slower than base
- `medium`: Even more accurate, slower than small
- `large`: Most accurate but slowest
You can select a model by specifying it when loading the Whisper model. For example:
```python
self.model = whisper.load_model("medium")
```
## Demo
## To-Dos
- [ ] Improve accuracy of transcription
- [ ] Add support for multiple languages
- [ ] Optimize performance for low-latency environments
- [ ] Implement speaker recognition
- [ ] Webohook - Create separate sessions(?) for each connected client
## Contribution Guidelines
Contributions are welcome! Please follow these steps to contribute:
1. Fork the repository.
2. Create a new branch (`git checkout -b feature-branch`).
3. Make your changes.
4. Commit your changes (`git commit -m 'Add new feature'`).
5. Push to the branch (`git push origin feature-branch`).
6. Create a pull request.
## License
This project is licensed under the MIT License.