W

Wav2vec2 Xls R 2b En To 15

Developed by facebook
Facebook's Wav2Vec2 XLS-R model, fine-tuned for speech translation tasks in 15 languages, capable of translating spoken English into multiple written languages.
Downloads 27
Release Time : 3/2/2022

Model Overview

This is a speech translation model based on SpeechEncoderDecoderModel, capable of translating spoken English into 15 different written languages. The model combines a powerful speech encoder with a text decoder, suitable for multilingual translation scenarios.

Model Features

Multilingual support
Supports translating spoken English into 15 different written languages
Large-scale pretraining
Based on the 2-billion-parameter Wav2Vec2-XLS-R-2B model, with powerful speech understanding capabilities
End-to-end translation
Direct translation from speech to text without intermediate transcription steps
High-quality translation
Performs excellently on the Covost2 dataset, providing accurate translation results

Model Capabilities

English speech recognition
Multilingual text translation
End-to-end speech translation
Supports 15 target languages

Use Cases

Speech translation
Real-time speech translation
Translates spoken English into written text of the target language in real-time
Performs excellently on the Covost2 dataset
Multilingual meeting minutes
Automatically translates English meeting content into meeting minutes in multiple languages
Educational applications
Language learning aid
Helps learners understand spoken English and translate it into their native language
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase