A

Asr Wav2vec2 Dvoice Amharic

Developed by speechbrain
This is an automatic speech recognition model for Amharic, trained using wav2vec 2.0 architecture with CTC/Attention mechanism
Downloads 96
Release Time : 6/9/2022

Model Overview

This model is an end-to-end automatic speech recognition system specifically designed for Amharic speech transcription tasks. It combines a pre-trained wav2vec 2.0 model with a CTC decoder, fine-tuned on the DVoice Amharic dataset.

Model Features

Pre-trained model fine-tuning
Fine-tuned based on facebook/wav2vec2-large-xlsr-53 pre-trained model, improving recognition capability for Amharic
End-to-end system
Provides a complete end-to-end solution including tokenizer and acoustic model
Multi-platform support
Supports both CPU and GPU inference, flexible deployment across different hardware environments

Model Capabilities

Amharic speech recognition
Audio transcription
Speech-to-text

Use Cases

Speech transcription
Amharic speech transcription
Convert Amharic speech to text
Validation set CER 6.71%, WER 25.50%
Voice assistant
Amharic voice assistant
Build voice interaction systems supporting Amharic
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase