AIbase
EN
Home
Wav2vec2 Xls R 100m Common Voice Tr Ft
W

Wav2vec2 Xls R 100m Common Voice Tr Ft

Developed by patrickvonplaten
This model is an automatic speech recognition (ASR) model fine-tuned on the COMMON_VOICE - TR Turkish dataset based on facebook/wav2vec2-xls-r-100m.
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Turkish speech recognition#Low word error rate#Multi-GPU training
Downloads 16
Release Time : 3/2/2022

Model Overview

This is an automatic speech recognition model for Turkish, fine-tuned on the Common Voice Turkish dataset using the wav2vec2-xls-r-100m architecture.

Model Features

High-precision Turkish recognition
Achieved a word error rate (WER) and character error rate (CER) of 1.0 on the Common Voice Turkish evaluation set.
Based on XLS-R architecture
Utilizes facebook's wav2vec2-xls-r-100m pre-trained model as the foundation, offering robust speech feature extraction capabilities.
Multi-GPU training optimization
Distributed training across 8 GPUs with a total batch size of 64, improving training efficiency.

Model Capabilities

Turkish speech recognition
Speech-to-text
Audio content transcription

Use Cases

Speech transcription
Turkish speech to text
Convert Turkish speech content into text
Highly accurate transcription results
Voice assistants
Turkish voice command recognition
Used for voice command recognition in Turkish voice assistants or smart home devices
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