Wav2vec2 Large Xls R 300m Turkish Colab
W
Wav2vec2 Large Xls R 300m Turkish Colab
Developed by izzy-lazerson
This is a speech recognition model fine-tuned on the Common Voice Turkish dataset based on the facebook/wav2vec2-xls-r-300m model
Downloads 34
Release Time : 3/2/2022
Model Overview
This model is specifically designed for Turkish automatic speech recognition (ASR) tasks, achieving a word error rate of 0.3363 on the Common Voice evaluation set
Model Features
Turkish language optimization
Specially fine-tuned for Turkish, performing well on the Common Voice Turkish dataset
Based on XLS-R architecture
Utilizes facebook's wav2vec2-xls-r-300m pretrained model as the foundation, with powerful speech feature extraction capabilities
Low word error rate
Achieved a word error rate of 0.3363 on the evaluation set, demonstrating excellent performance
Model Capabilities
Turkish speech recognition
Speech-to-text
Audio content understanding
Use Cases
Speech transcription
Turkish speech transcription
Convert Turkish speech content into text
Word error rate 0.3363
Voice assistants
Turkish voice command recognition
Used for voice command recognition in Turkish voice assistants or smart home devices
Featured Recommended AI Models
Š 2025AIbase