AIbase
EN
Home
Wav2vec2 Large Xls R 300m Turkish Colab
W

Wav2vec2 Large Xls R 300m Turkish Colab

Developed by krirk
A speech recognition model fine-tuned on the Common Voice Turkish dataset based on facebook/wav2vec2-xls-r-300m
Speech Recognition
Transformers
Open Source License:Apache-2.0#Turkish speech recognition#Multilingual support#Low word error rate
Downloads 17
Release Time : 3/2/2022

Model Overview

This is a Turkish-optimized speech recognition model, fine-tuned on the wav2vec2-xls-r-300m architecture and trained on the Common Voice dataset, capable of converting Turkish speech to text.

Model Features

High-performance Turkish recognition
Achieves a 31.49% word error rate on the Common Voice Turkish test set
Based on large-scale pretrained model
Fine-tuned on facebook's wav2vec2-xls-r-300m model, inheriting its powerful speech feature extraction capabilities
End-to-end training
Learns directly from raw audio to text output mapping without complex feature engineering

Model Capabilities

Turkish speech recognition
Speech-to-text
Continuous speech recognition

Use Cases

Speech transcription
Turkish speech transcription
Convert Turkish speech content into text transcripts
Achieves a 31.49% word error rate on the test set
Voice assistant
Turkish voice command recognition
Used for understanding voice commands in Turkish voice assistants
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