wav2vec2-xls-r-300m-bas-CV8-v2 Open-source Model - Support for Automatic Speech Recognition in Basque

Wav2vec2 Xls R 300m Bas CV8 V2

Developed by emre

An automatic speech recognition model fine-tuned on the Common Voice 8 dataset based on facebook/wav2vec2-xls-r-300m, supporting Basque (bas).

Speech Recognition

Transformers

OtherOpen Source License:Apache-2.0 #Low-resource speech recognition #XLS-R architecture #Common Voice fine-tuning

Downloads 18

Release Time : 3/2/2022

Model Overview

This model is an automatic speech recognition (ASR) model for Basque, fine-tuned on the Common Voice 8 dataset, and can be used to convert Basque speech into text.

Model Features

Based on XLS-R architecture

Utilizes Facebook's wav2vec2-xls-r-300m architecture with powerful speech feature extraction capabilities.

Optimized for Basque

Specifically fine-tuned for Basque, adapting to the phonetic characteristics of the language.

Trained on Common Voice dataset

Trained using Mozilla Common Voice 8 dataset, ensuring reliable data quality.

Model Capabilities

Basque speech recognition

Speech-to-text

Automatic speech recognition

Use Cases

Speech transcription

Basque speech transcription

Convert Basque speech content into text.

Word Error Rate (WER) 56.97%

Voice assistants

Basque voice command recognition

Used for voice command recognition in Basque voice assistants or smart devices.

Training Loss	Epoch	Step	Validation Loss	Wer
6.5211	16.13	500	1.2661	0.9153
0.7026	32.25	1000	0.6245	0.6516
0.3752	48.38	1500	0.6039	0.6148
0.2752	64.51	2000	0.6080	0.5808
0.2155	80.63	2500	0.6121	0.5697

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 Bas CV8 V2

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 wav2vec2-xls-r-300m-bas-CV8-v2

🚀 Quick Start

✨ Features

🔧 Technical Details

Training hyperparameters

Training results

Framework versions

📄 License

📚 Documentation

Model Index