AIbase
EN
Home
Whisper Large V3 Ft Cv16 Mn
W

Whisper Large V3 Ft Cv16 Mn

Developed by sanchit-gandhi
A speech recognition model fine-tuned on the Common Voice 16.0 dataset based on OpenAI Whisper Large V3
Speech Recognition
Transformers
Open Source License:Apache-2.0#Multilingual speech recognition#Low word error rate#Large-scale pretraining
Downloads 34
Release Time : 1/22/2024

Model Overview

This model is a fine-tuned version of OpenAI Whisper Large V3, focusing on automatic speech recognition (ASR) tasks, achieving a 35.22% word error rate on the Common Voice dataset.

Model Features

High-precision speech recognition
Achieves a 35.22% word error rate on the Common Voice test set, demonstrating excellent performance.
Multilingual support
Based on the Whisper architecture, capable of processing multiple languages.
Efficient fine-tuning
Targeted training on the base model improves recognition accuracy in specific domains.

Model Capabilities

Speech-to-text
Multilingual speech recognition
Long audio processing

Use Cases

Speech transcription
Automatic meeting minutes generation
Automatically convert meeting recordings into text transcripts
Approximately 65% accuracy (inferred based on WER metric)
Podcast subtitle generation
Automatically generate subtitles for podcast content
Assistive technology
Hearing impairment assistance
Real-time speech-to-text assistance for the hearing impaired
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