petersvenning/norwegian-whisper-transcriber

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Instructions

• —Create a venv, also known as virtual environment by running python3 -m venv .venv
• —Activate the environment by running source .venv/bin/activate in the same directory
• —Install all the required packages with pip3 install -r requirements.txt
• —Set your ElevenLabs API key in a .env file: ELEVENLABS_API_KEY=your_key_here
• —Run the app with python3 app.py: this will start the Gradio server on host 0.0.0.0:7860

Platform Instructions

• —Upload audio/video from your local machine in .mp3, .mp4, .wav, .mov or other audio/video formats
• —Click "Transcribe Audio/Video", this will start the ElevenLabs transcription
• —After completion click on "Download Transcript", this will download the entire audio transcript with timestamps