Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/flaviodelgrosso/whisper-transcriber
Use OpenAI's Whisper to transcribe audio files and diariaze speakers of the transcribed text
https://github.com/flaviodelgrosso/whisper-transcriber
ai audio-to-text diarization openai torch whisper
Last synced: 14 days ago
JSON representation
Use OpenAI's Whisper to transcribe audio files and diariaze speakers of the transcribed text
- Host: GitHub
- URL: https://github.com/flaviodelgrosso/whisper-transcriber
- Owner: flaviodelgrosso
- License: mit
- Created: 2024-06-04T16:39:49.000Z (5 months ago)
- Default Branch: master
- Last Pushed: 2024-06-11T07:38:35.000Z (5 months ago)
- Last Synced: 2024-10-16T22:49:05.417Z (29 days ago)
- Topics: ai, audio-to-text, diarization, openai, torch, whisper
- Language: Python
- Homepage:
- Size: 8.79 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# :ear: Whisper Transcriber
This is a Python project that uses the OpenAI open source Whisper [library](https://github.com/openai/whisper.git) to transcribe audio files and detect the language of the transcribed text.
## Getting Started
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
### Run in Google Colab
### Running with DevContainers in Visual Studio Code
If you have the [Remote - Containers](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers) extension installed in Visual Studio Code, you can open this project in a development container. This will automatically install all the necessary dependencies and set up the environment for you in an isolated Docker container.
Follow these steps:
1. Clone the repository.
2. Open the project in Visual Studio Code.
3. When prompted to "Reopen in Container", select "Reopen in Container". If you're not prompted, you can press `F1` to open the command palette, then select "Remote-Containers: Reopen Folder in Container".
The first time you open the container, it may take a few minutes to build. Once the container is built, the terminal will connect to the running container.
To run the script, use the terminal in Visual Studio Code:
```sh
python app.py
```
### Usage
Run the app.py script to transcribe the audio files in the audio directory:
```sh
python app.py
```
The transcribed text will be saved in the transcriptions directory.
#### Speakers Diarization
If you have an audio file with multiple speakers, you can perform speaker diarization by adding your Hugging Face authentication token in your `.env` file
```sh
HF_AUTH_TOKEN=
```