Open-source wav2vec2-base toy training data with 0.1 random noise speech recognition model

Wav2vec2 Base Toy Train Data Random Noise 0.1

Developed by scasutt

A speech recognition model fine-tuned on a random noise dataset based on the facebook/wav2vec2-base model

Downloads 22

Release Time : 3/26/2022

Model Overview

This model is a fine-tuned version of wav2vec2-base, primarily used for speech recognition tasks, trained on a dataset with added random noise.

Noise Robustness

Trained on a dataset with added random noise, providing a certain degree of noise robustness

Based on wav2vec2 Architecture

Utilizes Facebook's wav2vec2-base architecture with excellent speech feature extraction capabilities

Speech Recognition

Speech processing in noisy environments

Speech Recognition

Speech Transcription in Noisy Environments

Recognize and transcribe speech in environments with background noise

Word Error Rate (WER) of 0.7213

Training Loss	Epoch	Step	Validation Loss	Wer
3.1296	2.1	250	3.5088	1.0
3.0728	4.2	500	3.1694	1.0
1.8686	6.3	750	1.3414	0.9321
1.1241	8.4	1000	1.0196	0.8321
0.8704	10.5	1250	0.9387	0.7962
0.6734	12.6	1500	0.9309	0.7640
0.5832	14.7	1750	0.9329	0.7346
0.5207	16.8	2000	0.9060	0.7247
0.4857	18.9	2250	0.9263	0.7213

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base