Finetuned Whisper Mr
A Whisper small speech recognition model fine-tuned on the Common Voice 17.0 Marathi dataset, based on simran14/mr-model-h
Downloads 38
Release Time : 9/2/2024
Model Overview
This is an optimized automatic speech recognition (ASR) model for Marathi, based on the Whisper small architecture and fine-tuned on the Common Voice 17.0 dataset
Model Features
Low word error rate
Achieved a low word error rate of 0.0323 on the evaluation set
Marathi optimization
Specially optimized for Marathi speech recognition
Efficient training
Requires only 2 training rounds to achieve good results
Model Capabilities
Marathi speech recognition
Audio to text conversion
Speech transcription
Use Cases
Speech transcription
Marathi speech to text
Convert Marathi speech content into accurate text
Word error rate 0.0323
Voice assistant
Marathi voice assistant
Intelligent assistant supporting Marathi voice interaction
Featured Recommended AI Models