W

Whisper Large V2 Hindi 2.5k Steps

Developed by DrishtiSharma
This is a Hindi automatic speech recognition (ASR) model fine-tuned based on OpenAI Whisper Large V2, trained on the Common Voice 11.0 dataset with a word error rate (WER) of 10.05%.
Downloads 52
Release Time : 12/18/2022

Model Overview

This model is specifically designed for Hindi speech recognition tasks, optimized for Hindi based on the open-source Whisper Large V2 model.

Model Features

Low Word Error Rate
Achieves a word error rate of 10.05% on the Common Voice 11.0 Hindi test set.
Specifically Optimized for Hindi
Fine-tuned specifically for Hindi based on the large-scale multilingual Whisper model.
Based on High-Quality Dataset
Trained using the Mozilla Common Voice 11.0 dataset.

Model Capabilities

Hindi Speech Recognition
Speech-to-Text

Use Cases

Speech Transcription
Hindi Speech Transcription
Convert Hindi speech content into text
10.05% word error rate
Voice Assistants
Hindi Voice Assistant
Provide voice interaction capabilities for Hindi users
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase