This Is a Domain Specified Speech Translation Script. It helps in trancripting a audio into text by saving time. It uses Whisper Algorithm, which was Developed by OpenAI, Whisper is a speech recognition model designed for robustness and accuracy across a wide variety of audio data. It has the lowest CER, which is tested and fine tuned using huge amount of LibriSpeech Datasets. [ test-clean Dataset CER - 0.000312535 ] [ test-other Dataset CER - 0.000821592 ] [ train-clean-100 Dataset CER - 0.0001720000 ] [ NPTEL Dataset CER - 0.278767957 ] For Verifying the results, You can run the script by changing the directory according to own setup.