Whisper Small Model for Bengali ASR

Model Description

This model is a Whisper Small ASR model trained on the Bengali OpenSLR dataset. It's designed for Automatic Speech Recognition (ASR) tasks in the Bengali language. Whisper is an ASR system developed by Facebook AI that can be fine-tuned for various languages and domains.

Model Information

• Model architecture: Whisper Small
• Training data: Bengali OpenSLR dataset
• Training hardware: Colab

Model Performance

• wer: 1.333 with 25 training instances

Example Use Cases

• Bengali speech recognition applications