W

Wav2vec2 Large 100k Voxpopuli Catala

Developed by ccoreilly
A Catalan speech recognition model fine-tuned based on facebook/wav2vec2-large-100k-voxpopuli
Downloads 56
Release Time : 3/2/2022

Model Overview

This is an automatic speech recognition (ASR) model for Catalan, fine-tuned using the Common Voice and ParlamentParla datasets, capable of converting Catalan speech to text.

Model Features

Multi-dataset training
Trained using both Common Voice and ParlamentParla datasets to enhance model generalization
Low word error rate
Achieves a word error rate (WER) of 5.98% on the test set, demonstrating excellent performance
16kHz sampling rate support
Specially optimized to support 16kHz sampling rate audio input

Model Capabilities

Catalan speech recognition
Speech-to-text
Automatic speech recognition

Use Cases

Speech transcription
Parliament speech transcription
Convert recordings of Catalan parliament speeches into text transcripts
Performs well on the ParlamentParla dataset
Voice assistants
Provide speech recognition capabilities for Catalan voice assistants
Education
Language learning applications
Used for pronunciation assessment features in Catalan language learning apps
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase