AIbase
EN
Home
Wav2vec2 Xls R 300m Cv8 Turkish
W

Wav2vec2 Xls R 300m Cv8 Turkish

Developed by Baybars
This is an automatic speech recognition (ASR) model fine-tuned on the Turkish Common Voice 8 dataset based on Facebook's wav2vec2-xls-r-300m model.
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Turkish speech recognition#Low word error rate#Common Voice fine-tuning
Downloads 16
Release Time : 3/2/2022

Model Overview

This model is specifically designed for Turkish speech recognition tasks, trained on the Common Voice 8 dataset, and has achieved good word error rate and character error rate performance.

Model Features

High-performance Turkish recognition
Achieved a word error rate of 30.98% and a character error rate of 7.64% on the Common Voice test set
Based on large-scale pre-trained model
Fine-tuned from Facebook's wav2vec2-xls-r-300m model with powerful speech feature extraction capabilities
Incorporates N-gram language model
Uses an N-gram language model trained on Turkish Wikipedia for decoding to improve recognition accuracy

Model Capabilities

Turkish speech recognition
Long audio processing (supports chunking)
High-accuracy character-level recognition

Use Cases

Speech-to-text
Turkish speech transcription
Convert Turkish speech content into text
30.98% WER on Common Voice test set
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