Development of a fully functional, real-time speech-to-text application where audio captured from the user’s browser is streamed to the backend for transcription. All processing must operate on CPU-only using open-source speech recognition models.
https://colab.research.google.com/drive/1inZzjMHV0B5pFI8-RniLyp062XqX-ziI#scrollTo=d56438da-8ec5-46ed-91d5-a46bde1b18bb
For Frontend and Backend work --