dwil2444 / AudioTranscription

Python Scripts which utilize the low latency streaming transcription of the Watson Speech to Text service to generate transcripts of audio files.

Python Speech-To-Text Transcription

1. Create a Lite plan instance of the Watson Speech to text service: https://www.ibm.com/watson/services/speech-to-text/

2. Populate the IBM_USERNAME and IBM_PASSWORD variables in the Speech_To_Text.py with the appropriate values from the Speech To Text service

3. Specify the audio file to be transcribed by providing the appropriate file path

4. Navigate to the directory of the project and run the application using : python Loader.py

5. The transcripts will be populated in the 'transcript.txt' file.