---
tags:
- automatic-speech-recognition
- gary109/AI_Light_Dance
- generated_from_trainer
datasets:
- ai_light_dance
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: 1.5096
- Wer: 0.9207

## 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: 12
- eval_batch_size: 12
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 96
- 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    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 1.8237        | 1.0   | 184  | 1.9362          | 1.0743 |
| 1.6396        | 2.0   | 368  | 1.7375          | 1.0047 |
| 1.593         | 3.0   | 552  | 1.5942          | 0.9464 |
| 1.5281        | 4.0   | 736  | 1.6037          | 0.9526 |
| 1.5243        | 5.0   | 920  | 1.5292          | 0.9407 |
| 1.4443        | 6.0   | 1104 | 1.5465          | 0.9457 |
| 1.4801        | 7.0   | 1288 | 1.5965          | 0.9207 |
| 1.4104        | 8.0   | 1472 | 1.5224          | 0.9211 |
| 1.3828        | 9.0   | 1656 | 1.5400          | 0.9107 |
| 1.3966        | 10.0  | 1840 | 1.5545          | 0.9289 |
| 1.3481        | 11.0  | 2024 | 1.7372          | 0.9772 |
| 1.3437        | 12.0  | 2208 | 1.5096          | 0.9207 |
| 1.3207        | 13.0  | 2392 | 1.5559          | 0.9221 |
| 1.3103        | 14.0  | 2576 | 1.5285          | 0.9242 |
| 1.3032        | 15.0  | 2760 | 1.5297          | 0.8983 |
| 1.2549        | 16.0  | 2944 | 1.5481          | 0.9075 |
| 1.2484        | 17.0  | 3128 | 1.5886          | 0.9191 |
| 1.2282        | 18.0  | 3312 | 1.6611          | 0.9231 |
| 1.2168        | 19.0  | 3496 | 1.6368          | 0.9150 |
| 1.2093        | 20.0  | 3680 | 1.7357          | 0.9135 |
| 1.1951        | 21.0  | 3864 | 1.6973          | 0.9076 |
| 1.1835        | 22.0  | 4048 | 1.7049          | 0.9170 |
| 1.1554        | 23.0  | 4232 | 1.7663          | 0.9182 |
| 1.1418        | 24.0  | 4416 | 1.6814          | 0.9134 |
| 1.1391        | 25.0  | 4600 | 1.6740          | 0.8958 |
| 1.1142        | 26.0  | 4784 | 1.7445          | 0.9015 |
| 1.0598        | 27.0  | 4968 | 1.8278          | 0.9002 |
| 1.0423        | 28.0  | 5152 | 1.8642          | 0.9042 |
| 1.025         | 29.0  | 5336 | 1.9265          | 0.9078 |
| 1.02          | 30.0  | 5520 | 1.9589          | 0.9056 |


### Framework versions

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