---
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
  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

This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the GARY109/AI_LIGHT_DANCE - ONSET-STEPMANIA dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4089
- Wer: 0.6472

## 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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 10.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.5255        | 1.0   | 753  | 0.5928          | 0.9878 |
| 0.4897        | 2.0   | 1506 | 0.5564          | 0.9878 |
| 0.4926        | 3.0   | 2259 | 0.5204          | 0.9852 |
| 0.4533        | 4.0   | 3012 | 0.5061          | 0.9637 |
| 0.3557        | 5.0   | 3765 | 0.4360          | 0.6618 |
| 0.314         | 6.0   | 4518 | 0.4089          | 0.6472 |
| 0.284         | 7.0   | 5271 | 0.4130          | 0.5322 |
| 0.2762        | 8.0   | 6024 | 0.4108          | 0.5005 |
| 0.2646        | 9.0   | 6777 | 0.4176          | 0.4966 |
| 0.2637        | 10.0  | 7530 | 0.4158          | 0.4998 |


### Framework versions

- Transformers 4.20.0.dev0
- Pytorch 1.9.1+cu102
- Datasets 2.3.3.dev0
- Tokenizers 0.12.1