Bangla Voice Banking System

We have developed a voice banking system in Bangla language at Celloscope. It is a speech-to-speech system that allows users to do regular banking tasks (such as balance transfer and balance inquiry) just by using their voice. Our system generates synthetic voice as output in order to provide a voice-to-voice conversation experience. This system is currently integrated into the voice banking app of Agrani Bank. We have integrated numerous SOTA AI systems to ensure safe and secure banking experience for the users. Demo is available here.
Additional notebooks related to this project are available here:
Finetune Whisper ASR on Bangla
Training Bangla ESPNET ASR from scratch with custom data
Training Bangla ESPNET TTS from scratch