Software for Audio Transcription - Speech To Text
See the requirements file for all the packages used in this project.
- Import audio files
- Record audio ( in .wav )
- Translate audio files
- Play / Replay audio files
Download the latest release and launch the app
- Choose a langage
- Choose either to Record or Import your File
π You can see the translation on your screen after a few seconds !
- ( Optional ) You can play or replay the audio imported or recorded within the app
| Name | Supported OS | version |
|---|---|---|
ASR_REC_Windows |
Windows | v1.0.0 |
ASR_REC_Mac-arm64 |
Mac | v1.0.1 |
- Add models to the software
- Add langages
- Create the config.json file ( Choose the model to use ; Control the deletion of the files )
- Create Docu ( doc file + Demo + Gif + App view )
- Update ReadME
- Deployment ( Docker , Update .EXE releases )
- Supports 3 default languages: French, English, and Arabic (Morocco).
- Requires an internet access.
- Uses the "Google Speech Recognition" neural network.
- The
Import Filebutton allows you to transcribe audio files < ~1 minute. - The
Recordbutton allows you to record audio from your PC's microphone. The transcription is then generated in theTEXTarea. - 'Recording' starts IMMEDIATELY when you press the
Recordbutton. - The recording duration is limited to 10 seconds by default.
- The "Listen" button allows you to listen to your recording, whether it is imported or recorded within the application.
| Audio type | Supported |
|---|---|
.wav |
β |
.mp3 |
β |
Contributions are always welcome !
See contributing.md for ways to get started.
This project is under the GNU LICENSE
If you like this project feel free to let a π !
