D

D L Dl

Developed by bkh6722
This model is a speech recognition model fine-tuned based on facebook/wav2vec2-base-960h, achieving a word error rate (WER) of 1.0 on the evaluation set.
Downloads 25
Release Time : 5/17/2022

Model Overview

An automatic speech recognition (ASR) model for speech-to-text tasks, fine-tuned based on the wav2vec2 architecture

Model Features

Based on wav2vec2 architecture
Uses facebook's open-source wav2vec2-base-960h model as the base architecture
Low Word Error Rate
Achieves a word error rate (WER) of 1.0 on the evaluation set

Model Capabilities

Speech-to-text
English speech recognition

Use Cases

Speech Transcription
Meeting Minutes Transcription
Automatically convert meeting recordings into text transcripts
Voice Note Conversion
Convert voice memos into editable text
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase