Finyasy/Sheng_Speaker

This project uses OpenAI's Whisper Large-v3 model for automatic speech recognition (ASR) to transcribe Sheng audio, which is then translated to English,Swahili and viceversa. The system is designed to work with spoken Sheng and can be deployed on Azure Cloud. # Sheng_Speaker This project uses OpenAI's Whisper Large-v3 model for automatic speech recognition (ASR) to transcribe Sheng audio, which is then translated to English,Swahili and viceversa. The system is designed to work with spoken Sheng and can be deployed on Azure Cloud.