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_3
|
| 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_3
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [gary109/ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-13k_onset-drums_fold_2](https://huggingface.co/gary109/ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-13k_onset-drums_fold_2) on the ai_light_dance dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.7655
|
| 19 |
+
- Wer: 0.1076
|
| 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 |
+
| 0.4557 | 1.0 | 70 | 0.5794 | 0.1197 |
|
| 55 |
+
| 0.6796 | 2.0 | 140 | 0.5726 | 0.1388 |
|
| 56 |
+
| 0.4511 | 3.0 | 210 | 0.6290 | 0.1242 |
|
| 57 |
+
| 0.609 | 4.0 | 280 | 0.7112 | 0.1187 |
|
| 58 |
+
| 0.4082 | 5.0 | 350 | 0.8275 | 0.1965 |
|
| 59 |
+
| 0.4638 | 6.0 | 420 | 0.4767 | 0.1524 |
|
| 60 |
+
| 0.4446 | 7.0 | 490 | 0.5091 | 0.1376 |
|
| 61 |
+
| 0.4337 | 8.0 | 560 | 0.6622 | 0.1170 |
|
| 62 |
+
| 0.4604 | 9.0 | 630 | 0.7242 | 0.1600 |
|
| 63 |
+
| 0.4462 | 10.0 | 700 | 0.7298 | 0.1383 |
|
| 64 |
+
| 0.4201 | 11.0 | 770 | 0.8058 | 0.1362 |
|
| 65 |
+
| 0.4204 | 12.0 | 840 | 0.6255 | 0.1099 |
|
| 66 |
+
| 0.461 | 13.0 | 910 | 0.5204 | 0.1109 |
|
| 67 |
+
| 0.3779 | 14.0 | 980 | 0.6911 | 0.1125 |
|
| 68 |
+
| 0.3403 | 15.0 | 1050 | 0.5863 | 0.1188 |
|
| 69 |
+
| 0.6223 | 16.0 | 1120 | 0.6367 | 0.1147 |
|
| 70 |
+
| 0.3827 | 17.0 | 1190 | 0.6266 | 0.1293 |
|
| 71 |
+
| 0.3055 | 18.0 | 1260 | 0.4866 | 0.1095 |
|
| 72 |
+
| 0.3917 | 19.0 | 1330 | 0.4093 | 0.1250 |
|
| 73 |
+
| 0.3912 | 20.0 | 1400 | 0.4514 | 0.1077 |
|
| 74 |
+
| 0.3861 | 21.0 | 1470 | 0.5043 | 0.1156 |
|
| 75 |
+
| 0.3659 | 22.0 | 1540 | 0.5680 | 0.1091 |
|
| 76 |
+
| 0.3536 | 23.0 | 1610 | 0.7940 | 0.1029 |
|
| 77 |
+
| 0.3559 | 24.0 | 1680 | 0.5877 | 0.1101 |
|
| 78 |
+
| 0.3274 | 25.0 | 1750 | 0.4461 | 0.1059 |
|
| 79 |
+
| 0.5232 | 26.0 | 1820 | 1.2051 | 0.1068 |
|
| 80 |
+
| 0.3241 | 27.0 | 1890 | 0.8716 | 0.1099 |
|
| 81 |
+
| 0.3169 | 28.0 | 1960 | 0.6752 | 0.1082 |
|
| 82 |
+
| 0.2938 | 29.0 | 2030 | 0.6023 | 0.1071 |
|
| 83 |
+
| 0.3022 | 30.0 | 2100 | 0.6122 | 0.1146 |
|
| 84 |
+
| 0.4245 | 31.0 | 2170 | 0.5735 | 0.1102 |
|
| 85 |
+
| 0.3095 | 32.0 | 2240 | 0.4476 | 0.1042 |
|
| 86 |
+
| 0.4062 | 33.0 | 2310 | 0.6339 | 0.1130 |
|
| 87 |
+
| 0.3202 | 34.0 | 2380 | 0.4101 | 0.1077 |
|
| 88 |
+
| 0.2952 | 35.0 | 2450 | 0.4825 | 0.1076 |
|
| 89 |
+
| 0.2945 | 36.0 | 2520 | 0.4998 | 0.1058 |
|
| 90 |
+
| 0.336 | 37.0 | 2590 | 0.5490 | 0.1061 |
|
| 91 |
+
| 0.2912 | 38.0 | 2660 | 0.4804 | 0.1038 |
|
| 92 |
+
| 0.282 | 39.0 | 2730 | 0.4776 | 0.1022 |
|
| 93 |
+
| 0.4359 | 40.0 | 2800 | 0.4376 | 0.1044 |
|
| 94 |
+
| 0.2698 | 41.0 | 2870 | 0.5609 | 0.1098 |
|
| 95 |
+
| 0.3004 | 42.0 | 2940 | 0.5258 | 0.1083 |
|
| 96 |
+
| 0.2873 | 43.0 | 3010 | 0.4810 | 0.1069 |
|
| 97 |
+
| 0.3413 | 44.0 | 3080 | 0.4961 | 0.1080 |
|
| 98 |
+
| 0.2802 | 45.0 | 3150 | 0.6850 | 0.1076 |
|
| 99 |
+
| 0.2584 | 46.0 | 3220 | 0.7210 | 0.1082 |
|
| 100 |
+
| 0.3282 | 47.0 | 3290 | 0.6179 | 0.1053 |
|
| 101 |
+
| 0.2666 | 48.0 | 3360 | 0.7673 | 0.1075 |
|
| 102 |
+
| 0.2989 | 49.0 | 3430 | 0.7710 | 0.1079 |
|
| 103 |
+
| 0.2676 | 50.0 | 3500 | 0.7655 | 0.1076 |
|
| 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
|