Wav2vec2 Large Xls R 300m Turkish Colab Common Voice 8 6
This is a Turkish speech recognition model based on the wav2vec2 architecture, fine-tuned on the common_voice dataset
Downloads 21
Release Time : 5/10/2022
Model Overview
This model is a fine-tuned version of husnu/wav2vec2-large-xls-r-300m-turkish-colab_common_voice-8_5 on the common_voice dataset, primarily used for Turkish speech recognition tasks
Model Features
High-performance Turkish recognition
Achieved a word error rate (WER) of 0.3478 on the common_voice evaluation set
Based on large-scale pre-trained models
Built on the wav2vec2-large-xls-r-300m architecture with powerful feature extraction capabilities
Fine-tuned optimization
Undergone multiple rounds of fine-tuning on the Turkish common_voice dataset
Model Capabilities
Turkish speech recognition
Audio-to-text conversion
Use Cases
Speech transcription
Turkish speech transcription
Convert Turkish speech to text
Word error rate 0.3478
Voice assistants
Turkish voice command recognition
Used for command recognition in Turkish voice assistant systems
Featured Recommended AI Models
Š 2025AIbase