AIbase
EN
Home
Wav2vec2 Xls R 300m Tr Med CommonVoice8 Tr Med CommonVoice8
W

Wav2vec2 Xls R 300m Tr Med CommonVoice8 Tr Med CommonVoice8

Developed by emre
Turkish speech recognition model based on XLS-R architecture, fine-tuned on Common Voice 8 dataset
Speech Recognition
Transformers
Open Source License:Apache-2.0#Turkish speech recognition#XLS-R architecture#CommonVoice dataset
Downloads 16
Release Time : 3/2/2022

Model Overview

This model is an automatic speech recognition (ASR) model optimized specifically for Turkish, based on Facebook's wav2vec2-xls-r-300m architecture. Fine-tuned on the Common Voice 8 Turkish dataset, it can convert Turkish audio into text.

Model Features

Turkish language optimization
Speech recognition model specifically optimized for Turkish language characteristics
Large-scale pretraining
Based on XLS-R 300M parameter large-scale pretrained model
Common Voice dataset fine-tuning
Finely tuned on the Common Voice 8 Turkish dataset

Model Capabilities

Turkish audio to text conversion
Speech recognition
Speech transcription

Use Cases

Speech transcription
Turkish meeting minutes
Automatically convert Turkish meeting recordings into text transcripts
Word error rate 0.5010
Voice assistant
Provide speech recognition capability for Turkish voice assistants
Education
Language learning applications
Help Turkish language learners check pronunciation accuracy
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase