W

Whisper Large V2 Cv11 German

Developed by bofenghuang
An automatic speech recognition model fine-tuned on the Common Voice 11.0 German dataset based on openai/whisper-large-v2, supporting German speech-to-text with a word error rate of 5.76
Downloads 179
Release Time : 12/18/2022

Model Overview

This model is a fine-tuned version of whisper-large-v2 on German datasets, specifically designed for German automatic speech recognition tasks, capable of predicting capitalization and punctuation.

Model Features

Low Word Error Rate
Achieves a WER of 5.76 on the Common Voice 11.0 German test set, outperforming other models in the same series
Punctuation Prediction
Automatically predicts capitalization and punctuation, improving the readability of transcribed text
16kHz Sampling Rate Support
Optimized for speech input with a 16kHz sampling rate

Model Capabilities

German Speech Recognition
Speech-to-Text
Punctuation Prediction

Use Cases

Speech Transcription
German Meeting Minutes
Automatically transcribe German meeting recordings into text records
Highly accurate transcribed text including punctuation
German Media Subtitle Generation
Automatically generate subtitles for German videos or podcasts
Accurate time-aligned subtitles
Voice Assistants
German Voice Command Recognition
Recognize user commands in German voice assistants
Highly accurate command recognition
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase