---
license: apache-2.0
tags:
- automatic-speech-recognition
- gary109/AI_Light_Dance
- generated_from_trainer
model-index:
- name: ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v2
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v2

This model is a fine-tuned version of [gary109/ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v1](https://huggingface.co/gary109/ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v1) on the GARY109/AI_LIGHT_DANCE - ONSET-STEPMANIA2 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0753
- Wer: 0.7017

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 160
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.945         | 1.0   | 150  | 1.0767          | 0.7282 |
| 0.9445        | 2.0   | 300  | 1.0773          | 0.7165 |
| 0.9392        | 3.0   | 450  | 1.0813          | 0.7141 |
| 0.933         | 4.0   | 600  | 1.0858          | 0.7032 |
| 0.921         | 5.0   | 750  | 1.0753          | 0.7017 |
| 0.9241        | 6.0   | 900  | 1.0787          | 0.6976 |
| 0.9282        | 7.0   | 1050 | 1.0825          | 0.6959 |
| 0.9184        | 8.0   | 1200 | 1.0760          | 0.6930 |
| 0.915         | 9.0   | 1350 | 1.0773          | 0.6906 |
| 0.9094        | 10.0  | 1500 | 1.0786          | 0.6900 |


### Framework versions

- Transformers 4.21.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.3.3.dev0
- Tokenizers 0.12.1