This repository aims to collect available open soure ASR model, and share the code on how to generate the transcript using the corresponding third-party ASR systems. We have also shared the code how to use Google API ASR and more recent Whisper OpenAI ASR systems.
First, you have to install the following package before able to run the code
pip install SpeechRecognition
Then the code can be executed by using the following command
python google_asr.py
The installation of Whisper can be done using the following procedure
pip install -U openai-whisper
For running the code, please use the following command
python whisper_asr_all.py