W

Wav2vec2 Large Xls R 300m Gn K1

Developed by DrishtiSharma
This model is an automatic speech recognition model fine-tuned on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - GN dataset based on Facebook's wav2vec2-xls-r-300m model, supporting Guarani (gn).
Downloads 22
Release Time : 3/2/2022

Model Overview

This is a model for automatic speech recognition in Guarani (gn), fine-tuned based on the wav2vec2-xls-r-300m architecture, suitable for speech-to-text tasks.

Model Features

Multilingual support
Speech recognition capabilities specifically optimized for Guarani
Large-scale pre-training
Fine-tuned based on the 300 million parameter wav2vec2-xls-r-300m model
High performance
Achieved a word error rate (WER) of 0.6631 on the Common Voice 8 test set

Model Capabilities

Speech-to-text
Guarani speech recognition
Automatic speech recognition

Use Cases

Speech transcription
Guarani speech transcription
Convert Guarani speech to text
Achieved a word error rate of 0.6631 on the test set
Speech-assisted technology
Voice control applications
Develop voice control interfaces for Guarani-speaking users
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase