Open-source Automatic Speech Recognition Model of ai-light-dance_stepmania_ft_wav2vec2

Ai Light Dance Stepmania Ft Wav2vec2 Large Xlsr 53 V1

Developed by gary109

This model is an automatic speech recognition model fine-tuned from wav2vec2-large-xlsr-53 on the GARY109/AI_LIGHT_DANCE - ONSET-STEPMANIA2 dataset.

Downloads 48

Release Time : 6/23/2022

Model Overview

This is a model for automatic speech recognition (ASR), specifically optimized for voice commands in the rhythm game StepMania.

Fine-tuned from wav2vec2-large-xlsr-53

Fine-tuned from the powerful wav2vec2-large-xlsr-53 model, providing solid foundational speech recognition capabilities

Optimized for StepMania

Specifically trained and optimized for voice commands in the rhythm game StepMania

Low word error rate

Achieved a word error rate (WER) of 0.7344 on the evaluation set

Speech recognition

Music game command recognition

Gaming

StepMania voice control

Recognizing voice commands in the rhythm game StepMania

Word error rate 0.7344

Voice interaction

Game voice command recognition

Recognizing voice commands in specific gaming scenarios

Training Loss	Epoch	Step	Validation Loss	Wer
1.1632	1.0	150	1.2007	0.9875
1.1615	2.0	300	1.1912	0.9875
1.1487	3.0	450	1.1942	0.9875
1.1207	4.0	600	1.1753	0.9875
1.0638	5.0	750	1.1345	0.8214
1.0174	6.0	900	1.1541	0.7665
0.9946	7.0	1050	1.0799	0.7716
0.9694	8.0	1200	1.0848	0.7418
0.9566	9.0	1350	1.0763	0.7344
0.9466	10.0	1500	1.0791	0.7240

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base