wav2vec2-common_voice-tr-demo Open-Source Speech Recognition Model

Wav2vec2 Common Voice Tr Demo

Developed by YiTian

This model is a speech recognition model fine-tuned on the Turkish Common Voice dataset based on facebook/wav2vec2-large-xlsr-53

Downloads 30

Release Time : 3/31/2022

Model Overview

An automatic speech recognition (ASR) model for Turkish, fine-tuned on the Common Voice dataset using the wav2vec2 architecture

Turkish speech recognition

Speech recognition capabilities specifically optimized for Turkish

Based on Common Voice dataset

Trained using the publicly available Turkish Common Voice dataset

wav2vec2 architecture

Fine-tuned based on facebook's wav2vec2-large-xlsr-53 model

Turkish speech-to-text

Automatic speech recognition

Speech transcription

Turkish speech transcription

Convert Turkish speech content into text

Voice assistants

Turkish voice command recognition

Speech recognition component for Turkish voice assistants or voice control systems

Training Loss	Epoch	Step	Validation Loss	Wer
No log	7.14	100	3.6689	1.0
No log	14.29	200	3.0280	0.9999

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base