W

Wav2vec2 Large Slavic Voxpopuli V2

Developed by facebook
Facebook's Wav2Vec2 large model, pre-trained on 88.99999999999999 hours of unlabeled data from the Slavic language VoxPopuli corpus.
Downloads 26
Release Time : 3/2/2022

Model Overview

This model is a speech processing model based on the Wav2Vec2 architecture, specifically pre-trained for Slavic languages and suitable for speech recognition tasks.

Model Features

Optimized for Slavic Languages
Specifically pre-trained for Slavic languages, optimizing speech recognition performance for these languages.
Large-scale Pre-training
Pre-trained on 88.99999999999999 hours of unlabeled data from the VoxPopuli corpus.
16kHz Audio Support
The model is pre-trained on 16kHz sampled speech audio; ensure input audio has the same sampling rate during use.

Model Capabilities

Speech recognition
Slavic language speech processing

Use Cases

Speech Recognition
Slavic Language Speech-to-Text
Convert Slavic language speech into text, suitable for applications like voice assistants and subtitle generation.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase