W

Wav2vec2 Large Xlsr Turkish

Developed by cahya
This is an automatic speech recognition model fine-tuned on the Turkish Common Voice dataset based on the facebook/wav2vec2-large-xlsr-53 model, achieving a test WER of 21.13%.
Downloads 61
Release Time : 3/2/2022

Model Overview

This model is designed for automatic speech recognition tasks in Turkish, supporting 16kHz sampling rate audio input.

Model Features

High Accuracy Turkish Recognition
Achieves 21.13% WER on the Common Voice Turkish test set.
Based on XLSR Pre-trained Model
Fine-tuned from the facebook/wav2vec2-large-xlsr-53 model, featuring robust speech feature extraction capabilities.
16kHz Sampling Rate Support
Supports standard 16kHz sampling rate audio input.

Model Capabilities

Turkish speech recognition
Automatic speech-to-text

Use Cases

Speech Transcription
Turkish Speech to Text
Convert Turkish speech content into text
21.13% WER
Voice Assistants
Turkish Voice Command Recognition
Used for command recognition in Turkish voice assistants or smart home devices
Featured Recommended AI Models
ยฉ 2025AIbase