W

Wav2vec2 Xls R 1b Italian

Developed by jonatasgrosman
This is an Italian automatic speech recognition model based on the XLS-R 1B architecture, fine-tuned on multiple Italian datasets
Downloads 2,703
Release Time : 3/2/2022

Model Overview

This model is specifically optimized for Italian speech recognition tasks, capable of converting Italian speech to text

Model Features

High-performance Italian recognition
Achieves 9.04% WER and 2.2% CER on the Common Voice 8.0 test set
Language model enhancement support
With language model integration, WER can be reduced to 6.75% and CER to 1.76%
Multi-dataset training
Trained on multiple datasets including Common Voice 8.0, Multilingual TEDx, Multilingual LibriSpeech, and Voxpopuli
16kHz sampling rate support
Optimized for 16kHz sampled speech input

Model Capabilities

Italian speech recognition
Speech-to-text
Language model enhancement support

Use Cases

Speech transcription
Italian speech transcription
Convert Italian speech content to text
Achieves 9.04% WER on the Common Voice 8.0 test set
Voice assistants
Italian voice command recognition
Used for voice command recognition in Italian voice assistant systems
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase