wav2vec2-large-xls-r-300m-finnish Open Source Model - Accurately Achieve Finnish Speech Recognition

Wav2vec2 Large Xls R 300m Finnish

Developed by bekirbakar

This model is a Finnish speech recognition model fine-tuned from facebook/wav2vec2-xls-r-300m on a general speech dataset.

Downloads 18

Release Time : 6/6/2022

Model Overview

A speech recognition model optimized for Finnish, based on the wav2vec2 architecture, suitable for converting Finnish speech to text.

Finnish Optimization

Specifically fine-tuned for Finnish, improving the accuracy of Finnish speech recognition.

Based on Large-scale Pre-trained Model

Fine-tuned from the facebook/wav2vec2-xls-r-300m model, inheriting its powerful speech feature extraction capabilities.

Medium-sized Parameters

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

Finnish speech recognition

Speech-to-text

Automatic speech transcription

Speech Transcription

Finnish Meeting Minutes

Automatically transcribe Finnish meeting recordings into text records.

Word Error Rate 0.5143

Voice Assistant

Provide speech recognition capabilities for Finnish voice assistants.

Training Loss	Epoch	Step	Validation Loss	Wer
0.1666	14.8	400	0.4747	0.5143
0.0875	29.62	800	0.4747	0.5143

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base