---
license: apache-2.0
tags:
- automatic-speech-recognition
- gary109/AI_Light_Dance
- generated_from_trainer
model-index:
- name: ai-light-dance_singing3_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_singing3_ft_wav2vec2-large-xlsr-53

This model is a fine-tuned version of [gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53](https://huggingface.co/gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53) on the GARY109/AI_LIGHT_DANCE - ONSET-SINGING3 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0093
- Wer: 0.6919

## 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: 2.5e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 30.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 0.9731        | 1.0   | 1154  | 1.1499          | 0.7921 |
| 0.8422        | 2.0   | 2308  | 1.1470          | 0.7660 |
| 0.8401        | 3.0   | 3462  | 1.1128          | 0.7647 |
| 0.9094        | 4.0   | 4616  | 1.1060          | 0.7371 |
| 0.8339        | 5.0   | 5770  | 1.0808          | 0.7513 |
| 0.8394        | 6.0   | 6924  | 1.0556          | 0.7367 |
| 0.8187        | 7.0   | 8078  | 1.0714          | 0.7257 |
| 0.7501        | 8.0   | 9232  | 1.0586          | 0.7339 |
| 0.7654        | 9.0   | 10386 | 1.0541          | 0.7168 |
| 0.7902        | 10.0  | 11540 | 1.0216          | 0.7172 |
| 0.7572        | 11.0  | 12694 | 1.0404          | 0.7159 |
| 0.6609        | 12.0  | 13848 | 1.0318          | 0.7205 |
| 0.6602        | 13.0  | 15002 | 1.0353          | 0.7008 |
| 0.6401        | 14.0  | 16156 | 1.0307          | 0.7161 |
| 0.7059        | 15.0  | 17310 | 1.0093          | 0.6919 |
| 0.6832        | 16.0  | 18464 | 1.0379          | 0.7006 |
| 0.6653        | 17.0  | 19618 | 1.0230          | 0.6979 |
| 0.6931        | 18.0  | 20772 | 1.0222          | 0.6869 |
| 0.6438        | 19.0  | 21926 | 1.0265          | 0.6954 |
| 0.6072        | 20.0  | 23080 | 1.0189          | 0.6839 |
| 0.6643        | 21.0  | 24234 | 1.0244          | 0.6821 |
| 0.6858        | 22.0  | 25388 | 1.0180          | 0.6903 |
| 0.6395        | 23.0  | 26542 | 1.0225          | 0.6788 |
| 0.566         | 24.0  | 27696 | 1.0225          | 0.6716 |
| 0.6353        | 25.0  | 28850 | 1.0324          | 0.6792 |
| 0.7075        | 26.0  | 30004 | 1.0266          | 0.6829 |
| 0.5473        | 27.0  | 31158 | 1.0232          | 0.6742 |
| 0.6265        | 28.0  | 32312 | 1.0253          | 0.6747 |
| 0.5805        | 29.0  | 33466 | 1.0262          | 0.6724 |
| 0.6567        | 30.0  | 34620 | 1.0278          | 0.6756 |


### Framework versions

- Transformers 4.21.0.dev0
- Pytorch 1.9.1+cu102
- Datasets 2.3.3.dev0
- Tokenizers 0.12.1