![Open In Colab](https://camo.githubusercontent.com/f5e0d0538a9c2972b5d413e0ace04cecd8efd828d133133933dfffec282a4e1b/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667)
git clone https://github.com/jerinka/whisper_gradio_demo
cd whisper_gradio_demo
python3 -m venv env
source env/bin/activate
pip install git+https://github.com/openai/whisper.git
pip install gradio
python A_audio_file_stt.py -s (-s for sharing, avoid for local alone)
python B_record_stream_stt.py (record and submit)
python C_live_stream_stt.py (TODO: not good, need to improve)
- YouTube Video Tutorial link
- This repo is part of Deep Learning with Tensorflow and Pytorch Udemy Course: enroll -
link
- GitLab CICD Udemy Course: enroll - link