metadata
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-v1
results: []
ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1
This model is a fine-tuned version of gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1 on the GARY109/AI_LIGHT_DANCE - ONSET-SINGING3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5352
- Wer: 0.2490
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: 2e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 50.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3818 | 1.0 | 72 | 0.5569 | 0.2535 |
| 0.3686 | 2.0 | 144 | 0.5535 | 0.2501 |
| 0.3562 | 3.0 | 216 | 0.5526 | 0.2501 |
| 0.3506 | 4.0 | 288 | 0.5460 | 0.2520 |
| 0.369 | 5.0 | 360 | 0.5390 | 0.2484 |
| 0.3683 | 6.0 | 432 | 0.5426 | 0.2474 |
| 0.3541 | 7.0 | 504 | 0.5452 | 0.2495 |
| 0.369 | 8.0 | 576 | 0.5468 | 0.2490 |
| 0.358 | 9.0 | 648 | 0.5471 | 0.2453 |
| 0.3765 | 10.0 | 720 | 0.5376 | 0.2459 |
| 0.3654 | 11.0 | 792 | 0.5407 | 0.2486 |
| 0.373 | 12.0 | 864 | 0.5390 | 0.2475 |
| 0.3606 | 13.0 | 936 | 0.5441 | 0.2472 |
| 0.369 | 14.0 | 1008 | 0.5388 | 0.2490 |
| 0.3762 | 15.0 | 1080 | 0.5389 | 0.2497 |
| 0.3821 | 16.0 | 1152 | 0.5352 | 0.2490 |
| 0.3605 | 17.0 | 1224 | 0.5434 | 0.2492 |
| 0.3703 | 18.0 | 1296 | 0.5415 | 0.2500 |
| 0.3667 | 19.0 | 1368 | 0.5499 | 0.2487 |
| 0.3703 | 20.0 | 1440 | 0.5482 | 0.2494 |
| 0.369 | 21.0 | 1512 | 0.5418 | 0.2504 |
| 0.3708 | 22.0 | 1584 | 0.5437 | 0.2479 |
| 0.3609 | 23.0 | 1656 | 0.5453 | 0.2480 |
| 0.3534 | 24.0 | 1728 | 0.5393 | 0.2484 |
| 0.3656 | 25.0 | 1800 | 0.5363 | 0.2477 |
| 0.3713 | 26.0 | 1872 | 0.5406 | 0.2461 |
| 0.3572 | 27.0 | 1944 | 0.5369 | 0.2465 |
| 0.3665 | 28.0 | 2016 | 0.5375 | 0.2466 |
| 0.3748 | 29.0 | 2088 | 0.5367 | 0.2480 |
| 0.3769 | 30.0 | 2160 | 0.5359 | 0.2459 |
| 0.3634 | 31.0 | 2232 | 0.5417 | 0.2471 |
| 0.3627 | 32.0 | 2304 | 0.5398 | 0.2473 |
| 0.3497 | 33.0 | 2376 | 0.5428 | 0.2483 |
| 0.3479 | 34.0 | 2448 | 0.5390 | 0.2481 |
| 0.363 | 35.0 | 2520 | 0.5388 | 0.2478 |
| 0.3622 | 36.0 | 2592 | 0.5396 | 0.2490 |
| 0.3685 | 37.0 | 2664 | 0.5408 | 0.2479 |
| 0.356 | 38.0 | 2736 | 0.5385 | 0.2459 |
| 0.3529 | 39.0 | 2808 | 0.5389 | 0.2467 |
| 0.3702 | 40.0 | 2880 | 0.5392 | 0.2482 |
| 0.3645 | 41.0 | 2952 | 0.5408 | 0.2467 |
| 0.3489 | 42.0 | 3024 | 0.5406 | 0.2474 |
| 0.3556 | 43.0 | 3096 | 0.5402 | 0.2472 |
| 0.356 | 44.0 | 3168 | 0.5386 | 0.2468 |
| 0.3632 | 45.0 | 3240 | 0.5402 | 0.2463 |
| 0.3693 | 46.0 | 3312 | 0.5401 | 0.2472 |
| 0.3593 | 47.0 | 3384 | 0.5390 | 0.2463 |
| 0.3515 | 48.0 | 3456 | 0.5399 | 0.2468 |
| 0.3485 | 49.0 | 3528 | 0.5392 | 0.2461 |
| 0.3591 | 50.0 | 3600 | 0.5403 | 0.2461 |
Framework versions
- Transformers 4.21.0.dev0
- Pytorch 1.9.1+cu102
- Datasets 2.3.3.dev0
- Tokenizers 0.12.1