update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- ai_light_dance
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-13k_onset-drums_fold_1
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-13k_onset-drums_fold_1
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [gary109/ai-light-dance_drums_pretrain_wav2vec2-base-new-13k](https://huggingface.co/gary109/ai-light-dance_drums_pretrain_wav2vec2-base-new-13k) on the ai_light_dance dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.6307
|
| 19 |
+
- Wer: 0.1917
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0003
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 100
|
| 47 |
+
- num_epochs: 50.0
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 54 |
+
| 3.0614 | 0.99 | 69 | 5.1275 | 1.0 |
|
| 55 |
+
| 1.8291 | 1.99 | 138 | 2.2008 | 1.0 |
|
| 56 |
+
| 1.4664 | 2.99 | 207 | 1.6821 | 1.0 |
|
| 57 |
+
| 1.287 | 3.99 | 276 | 1.5681 | 1.0 |
|
| 58 |
+
| 1.2642 | 4.99 | 345 | 1.5074 | 1.0 |
|
| 59 |
+
| 1.2702 | 5.99 | 414 | 1.4650 | 1.0 |
|
| 60 |
+
| 1.2245 | 6.99 | 483 | 1.3027 | 1.0 |
|
| 61 |
+
| 1.3461 | 7.99 | 552 | 1.3109 | 1.0 |
|
| 62 |
+
| 1.2903 | 8.99 | 621 | 1.3107 | 1.0 |
|
| 63 |
+
| 1.2741 | 9.99 | 690 | 1.1842 | 1.0 |
|
| 64 |
+
| 1.1446 | 10.99 | 759 | 1.1754 | 1.0 |
|
| 65 |
+
| 1.0746 | 11.99 | 828 | 1.1469 | 0.9999 |
|
| 66 |
+
| 0.8203 | 12.99 | 897 | 0.9071 | 0.6202 |
|
| 67 |
+
| 0.5996 | 13.99 | 966 | 0.7047 | 0.4234 |
|
| 68 |
+
| 0.5672 | 14.99 | 1035 | 0.5369 | 0.2567 |
|
| 69 |
+
| 0.4965 | 15.99 | 1104 | 0.4644 | 0.2861 |
|
| 70 |
+
| 0.5639 | 16.99 | 1173 | 0.4630 | 0.2145 |
|
| 71 |
+
| 0.6272 | 17.99 | 1242 | 0.6848 | 0.2667 |
|
| 72 |
+
| 0.6764 | 18.99 | 1311 | 0.6074 | 0.2508 |
|
| 73 |
+
| 0.7205 | 19.99 | 1380 | 0.6452 | 0.2184 |
|
| 74 |
+
| 0.346 | 20.99 | 1449 | 0.5962 | 0.2457 |
|
| 75 |
+
| 0.2212 | 21.99 | 1518 | 0.5236 | 0.2068 |
|
| 76 |
+
| 0.1646 | 22.99 | 1587 | 0.6130 | 0.2198 |
|
| 77 |
+
| 0.3148 | 23.99 | 1656 | 0.5592 | 0.2620 |
|
| 78 |
+
| 0.3061 | 24.99 | 1725 | 0.5577 | 0.2560 |
|
| 79 |
+
| 0.3137 | 25.99 | 1794 | 0.5247 | 0.2227 |
|
| 80 |
+
| 0.389 | 26.99 | 1863 | 0.5799 | 0.2081 |
|
| 81 |
+
| 0.4168 | 27.99 | 1932 | 0.5850 | 0.1818 |
|
| 82 |
+
| 0.4403 | 28.99 | 2001 | 0.5687 | 0.2053 |
|
| 83 |
+
| 0.4936 | 29.99 | 2070 | 0.5511 | 0.2065 |
|
| 84 |
+
| 0.2196 | 30.99 | 2139 | 0.5438 | 0.1706 |
|
| 85 |
+
| 0.1683 | 31.99 | 2208 | 0.6066 | 0.1855 |
|
| 86 |
+
| 0.1552 | 32.99 | 2277 | 0.5248 | 0.1930 |
|
| 87 |
+
| 0.1682 | 33.99 | 2346 | 0.5440 | 0.1783 |
|
| 88 |
+
| 0.2162 | 34.99 | 2415 | 0.6079 | 0.1778 |
|
| 89 |
+
| 0.3041 | 35.99 | 2484 | 0.5608 | 0.1834 |
|
| 90 |
+
| 0.3188 | 36.99 | 2553 | 0.6039 | 0.2007 |
|
| 91 |
+
| 0.3692 | 37.99 | 2622 | 0.5437 | 0.1769 |
|
| 92 |
+
| 0.4446 | 38.99 | 2691 | 0.6475 | 0.1881 |
|
| 93 |
+
| 0.386 | 39.99 | 2760 | 0.6468 | 0.1894 |
|
| 94 |
+
| 0.1995 | 40.99 | 2829 | 0.6398 | 0.1906 |
|
| 95 |
+
| 0.1174 | 41.99 | 2898 | 0.5987 | 0.1936 |
|
| 96 |
+
| 0.1288 | 42.99 | 2967 | 0.6133 | 0.1871 |
|
| 97 |
+
| 0.1857 | 43.99 | 3036 | 0.6976 | 0.1995 |
|
| 98 |
+
| 0.2025 | 44.99 | 3105 | 0.6356 | 0.1902 |
|
| 99 |
+
| 0.2922 | 45.99 | 3174 | 0.6324 | 0.2055 |
|
| 100 |
+
| 0.3575 | 46.99 | 3243 | 0.6338 | 0.1862 |
|
| 101 |
+
| 0.4019 | 47.99 | 3312 | 0.6113 | 0.1898 |
|
| 102 |
+
| 0.4211 | 48.99 | 3381 | 0.6320 | 0.1948 |
|
| 103 |
+
| 0.4323 | 49.99 | 3450 | 0.6307 | 0.1917 |
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
### Framework versions
|
| 107 |
+
|
| 108 |
+
- Transformers 4.24.0.dev0
|
| 109 |
+
- Pytorch 1.12.1+cu113
|
| 110 |
+
- Datasets 2.6.1
|
| 111 |
+
- Tokenizers 0.13.1
|