---
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-STEPMANIA2 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2034
- Wer: 0.9875

## 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: 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: 500
- num_epochs: 10.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 2.5631        | 1.0   | 150  | 2.4894          | 1.0    |
| 1.9443        | 2.0   | 300  | 1.8861          | 1.0    |
| 1.7618        | 3.0   | 450  | 1.6731          | 1.0    |
| 1.2354        | 4.0   | 600  | 1.2471          | 0.9875 |
| 1.2333        | 5.0   | 750  | 1.2253          | 0.9875 |
| 1.2037        | 6.0   | 900  | 1.2168          | 0.9875 |
| 1.2184        | 7.0   | 1050 | 1.2120          | 0.9875 |
| 1.1932        | 8.0   | 1200 | 1.2080          | 0.9875 |
| 1.179         | 9.0   | 1350 | 1.2039          | 0.9875 |
| 1.1722        | 10.0  | 1500 | 1.2034          | 0.9875 |


### Framework versions

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