wav2vec2-xls-r-300m-Turkish-Tr-small Open-source Model - Accurately Implement Turkish Speech Recognition

Wav2vec2 Xls R 300m Turkish Tr Small

Developed by emre

This is a Turkish speech recognition model fine-tuned on the Common Voice dataset based on the facebook/wav2vec2-xls-r-300m model

Speech Recognition

Transformers

Open Source License:Apache-2.0 #Turkish speech recognition #Robust speech processing #Low-resource optimization

Downloads 19

Release Time : 3/2/2022

Model Overview

This model is an automatic speech recognition (ASR) model optimized for Turkish, fine-tuned on the Common Voice dataset, with good speech recognition capabilities

Model Features

Turkish optimization

Specially fine-tuned for Turkish speech recognition tasks

Based on wav2vec2-xls-r architecture

Utilizes the powerful wav2vec2-xls-r-300m pre-trained model as the foundation

Medium scale

300M parameter size, achieving a balance between performance and resource consumption

Model Capabilities

Turkish speech recognition

Speech-to-text

Use Cases

Speech transcription

Turkish meeting minutes

Automatically convert Turkish meeting recordings into text transcripts

Word Error Rate (WER) of 0.5050

Voice assistant

Used as the speech recognition module for Turkish voice assistants

Training Loss	Epoch	Step	Validation Loss	Wer
4.8735	4.21	400	2.8173	1.0002
1.0073	8.42	800	0.4981	0.6717
0.3395	12.63	1200	0.4470	0.5866
0.2254	16.84	1600	0.4349	0.5491
0.1648	21.05	2000	0.4454	0.5284
0.1325	25.26	2400	0.4552	0.5131
0.1102	29.47	2800	0.4375	0.5050

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Wav2vec2 Xls R 300m Turkish Tr Small

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 wav2vec2-xls-r-300m-Turkish-Tr-small

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License