Hugging Face's logo

Spaces:
h2oai
/
h2o_wave_whisper
Running

App Files Community
1
h2o_wave_whisper / README.md
MartinT's picture
MartinT
chore: Update config
f743b8c
preview code
|
raw
history blame
1.51 kB
metadata
title: H2O Wave Whisper
emoji: 📝
colorFrom: yellow
colorTo: gray
sdk: docker
app_port: 7860

WaveTon

💯 Wave applications

License GitHub Twitter

Whisper 🖥️

Speech to text using OpenAI's Whisper model.

Setup ⚙️

  1. Check the version of Python, must be Python 3.9+ but recommended to use Python 3.10+ for best experience
python3 --version
  1. Clone the repository
git clone https://github.com/vopani/waveton.git
  1. Create a virtual environment
cd waveton/apps/deeplearning_apps/whisper
python3 -m venv venv
source venv/bin/activate
  1. Install ffmpeg

On Linux:

sudo apt update && sudo apt install ffmpeg

On Mac:

brew install ffmpeg
  1. Install the packages
python3 -m pip install -U pip
python3 -m pip install -r requirements.txt
  1. Run the application
wave run app
  1. View the application on your local browser: http://localhost:10101