AIbase
EN
Home
Wav2vec2 Large Xls R 300m Tr
W

Wav2vec2 Large Xls R 300m Tr

Developed by resul-ai
This model is a speech recognition model fine-tuned on the CommonVoice Turkish dataset based on facebook/wav2vec2-xls-r-300m, achieving a word error rate of 29.04% on the evaluation set.
Speech Recognition
Transformers
Open Source License:Apache-2.0#Turkish speech recognition#XLS-R architecture#Low word error rate
Downloads 117
Release Time : 6/28/2022

Model Overview

This is a model for Turkish (tr-TR) automatic speech recognition (ASR), fine-tuned based on the wav2vec2-xls-r-300m architecture.

Model Features

Fine-tuned from large-scale pre-trained model
Fine-tuned from facebook's wav2vec2-xls-r-300m model, inheriting its powerful speech feature extraction capabilities
Turkish speech recognition
Speech recognition model specifically optimized for Turkish
Relatively high recognition accuracy
Achieves a word error rate of 29.04% on the CommonVoice evaluation set

Model Capabilities

Turkish speech-to-text
Continuous speech recognition

Use Cases

Speech transcription
Turkish speech transcription
Convert Turkish speech content to text
Word error rate 29.04%
Voice assistants
Turkish voice command recognition
Used for voice command recognition in Turkish voice assistant systems
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