---
tags:
- automatic-speech-recognition
- gary109/AI_Light_Dance
- generated_from_trainer
model-index:
- name: ai-light-dance_singing_ft_pretrain_wav2vec2-large-lv60
  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_singing_ft_pretrain_wav2vec2-large-lv60

This model is a fine-tuned version of [gary109/ai-light-dance_pretrain_wav2vec2-large-lv60](https://huggingface.co/gary109/ai-light-dance_pretrain_wav2vec2-large-lv60) on the GARY109/AI_LIGHT_DANCE - ONSET-SINGING dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4961
- Wer: 0.9206

## 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
- num_epochs: 10.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 1.6096        | 1.0   | 552  | 1.7650          | 1.0053 |
| 1.6294        | 2.0   | 1104 | 1.6735          | 0.9591 |
| 1.5509        | 3.0   | 1656 | 1.6170          | 0.9852 |
| 1.5175        | 4.0   | 2208 | 1.6312          | 0.9626 |
| 1.5267        | 5.0   | 2760 | 1.5032          | 0.9249 |
| 1.4055        | 6.0   | 3312 | 1.6107          | 0.9438 |
| 1.3267        | 7.0   | 3864 | 1.5386          | 0.9378 |
| 1.312         | 8.0   | 4416 | 1.4961          | 0.9206 |
| 1.3245        | 9.0   | 4968 | 1.5158          | 0.9182 |
| 1.2885        | 10.0  | 5520 | 1.5296          | 0.9230 |


### Framework versions

- Transformers 4.20.0.dev0
- Pytorch 1.9.1+cu102
- Datasets 2.2.3.dev0
- Tokenizers 0.12.1