AIbase
EN
Home
Whisper Large V2 Hungarian
W

Whisper Large V2 Hungarian

Developed by DrishtiSharma
A speech recognition model fine-tuned on the Hungarian Common Voice dataset based on OpenAI Whisper Large-V2
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Hungarian speech recognition#Low word error rate#Multilingual support
Downloads 21
Release Time : 12/20/2022

Model Overview

This is an automatic speech recognition (ASR) model optimized for Hungarian, fine-tuned on the Common Voice 11.0 Hungarian dataset with a word error rate (WER) of 17.45%.

Model Features

Hungarian optimization
Specifically fine-tuned for Hungarian speech recognition, offering better localized performance compared to the original Whisper model
Low word error rate
Achieves a word error rate (WER) of 17.45% on the Common Voice test set
Based on Whisper architecture
Inherits the powerful speech recognition capabilities and robustness of the Whisper model

Model Capabilities

Hungarian speech recognition
Speech-to-text
Long audio processing

Use Cases

Speech transcription
Hungarian meeting minutes
Automatically transcribe Hungarian meeting recordings into text records
Accuracy approximately 82.5% (based on WER calculation)
Voice assistant
Hungarian voice command recognition
Provide speech recognition capabilities for Hungarian voice assistants
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase