AIbase
EN
Home
Wav2vec2 Large Xls R 300m Ru
W

Wav2vec2 Large Xls R 300m Ru

Developed by NLPVladimir
This model is a Russian automatic speech recognition (ASR) model fine-tuned on the common_voice_17_0 dataset based on facebook/wav2vec2-xls-r-300m, with a word error rate (WER) of 0.195.
Speech Recognition
Transformers
Open Source License:Apache-2.0#Russian speech recognition#Low word error rate#Multilingual transfer learning
Downloads 56
Release Time : 1/30/2025

Model Overview

This is a model for Russian automatic speech recognition, based on the wav2vec2 architecture and fine-tuned on the Common Voice dataset.

Model Features

Low word error rate
Achieves a word error rate (WER) of 0.195 on the Common Voice Russian test set
Based on large-scale pretrained model
Fine-tuned from the facebook/wav2vec2-xls-r-300m pretrained model
Efficient training
Optimized training efficiency using mixed precision training and gradient accumulation techniques

Model Capabilities

Russian speech recognition
Speech-to-text
Audio content analysis

Use Cases

Speech transcription
Russian speech transcription
Convert Russian speech to text
Word error rate 0.195
Voice assistants
Russian voice command recognition
Basic recognition capability for Russian voice assistants
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase