AIbase
EN
Home
Wav2vec2 Xls R 300m Gn Cv8 4
W

Wav2vec2 Xls R 300m Gn Cv8 4

Developed by lgris
This is an automatic speech recognition (ASR) model fine-tuned on the Common Voice 8.0 dataset based on the facebook/wav2vec2-xls-r-300m model, specifically optimized for the Guarani language (gn).
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Guarani speech recognition#Low-resource language ASR#XLS-R architecture
Downloads 17
Release Time : 3/2/2022

Model Overview

This model is designed for automatic speech recognition tasks in Guarani, capable of converting speech into text.

Model Features

Optimized for Guarani
Fine-tuned specifically on Guarani speech datasets, making it suitable for speech recognition tasks in this language.
Based on XLS-R architecture
Uses facebook's wav2vec2-xls-r-300m as the base model, featuring robust speech feature extraction capabilities.
Medium-sized model
With 300M parameters, it strikes a balance between accuracy and computational efficiency.

Model Capabilities

Guarani speech recognition
Speech-to-text

Use Cases

Speech transcription
Guarani speech transcription
Convert Guarani speech content into text
Achieved a 68.45% Word Error Rate (WER) on the Common Voice 8.0 test set.
Voice assistants
Guarani voice command recognition
Used for understanding voice commands in Guarani
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase