metadata
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-v1
results: []
ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v1
This model is a fine-tuned version of gary109/ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53 on the GARY109/AI_LIGHT_DANCE - ONSET-STEPMANIA2 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0763
- Wer: 0.7344
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: 4e-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: 100
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1632 | 1.0 | 150 | 1.2007 | 0.9875 |
| 1.1615 | 2.0 | 300 | 1.1912 | 0.9875 |
| 1.1487 | 3.0 | 450 | 1.1942 | 0.9875 |
| 1.1207 | 4.0 | 600 | 1.1753 | 0.9875 |
| 1.0638 | 5.0 | 750 | 1.1345 | 0.8214 |
| 1.0174 | 6.0 | 900 | 1.1541 | 0.7665 |
| 0.9946 | 7.0 | 1050 | 1.0799 | 0.7716 |
| 0.9694 | 8.0 | 1200 | 1.0848 | 0.7418 |
| 0.9566 | 9.0 | 1350 | 1.0763 | 0.7344 |
| 0.9466 | 10.0 | 1500 | 1.0791 | 0.7240 |
Framework versions
- Transformers 4.21.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.3.3.dev0
- Tokenizers 0.12.1