update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- zeroth_korean_asr
|
| 7 |
+
model-index:
|
| 8 |
+
- name: ''
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
#
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the zeroth_korean_asr dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2088
|
| 20 |
+
- Wer: 0.2954
|
| 21 |
+
- Cer: 0.0953
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 7.5e-05
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 2000
|
| 49 |
+
- num_epochs: 50.0
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
|
| 56 |
+
| 19.7138 | 0.72 | 500 | 19.6427 | 1.0 | 1.0 |
|
| 57 |
+
| 4.8039 | 1.44 | 1000 | 4.7842 | 1.0 | 1.0 |
|
| 58 |
+
| 4.5619 | 2.16 | 1500 | 4.5608 | 0.9992 | 0.9598 |
|
| 59 |
+
| 4.254 | 2.88 | 2000 | 4.2729 | 0.9955 | 0.9063 |
|
| 60 |
+
| 4.1905 | 3.6 | 2500 | 4.2257 | 0.9903 | 0.8758 |
|
| 61 |
+
| 4.0683 | 4.32 | 3000 | 3.9294 | 0.9937 | 0.7911 |
|
| 62 |
+
| 3.486 | 5.04 | 3500 | 2.7045 | 1.0012 | 0.5934 |
|
| 63 |
+
| 2.946 | 5.75 | 4000 | 1.9691 | 0.9425 | 0.4634 |
|
| 64 |
+
| 2.634 | 6.47 | 4500 | 1.5212 | 0.8807 | 0.3850 |
|
| 65 |
+
| 2.4066 | 7.19 | 5000 | 1.2551 | 0.8177 | 0.3601 |
|
| 66 |
+
| 2.2651 | 7.91 | 5500 | 1.0423 | 0.7650 | 0.3039 |
|
| 67 |
+
| 2.1828 | 8.63 | 6000 | 0.9599 | 0.7273 | 0.3106 |
|
| 68 |
+
| 2.1023 | 9.35 | 6500 | 0.9482 | 0.7161 | 0.3063 |
|
| 69 |
+
| 2.0536 | 10.07 | 7000 | 0.8242 | 0.6767 | 0.2860 |
|
| 70 |
+
| 1.9803 | 10.79 | 7500 | 0.7643 | 0.6563 | 0.2637 |
|
| 71 |
+
| 1.9468 | 11.51 | 8000 | 0.7319 | 0.6441 | 0.2505 |
|
| 72 |
+
| 1.9178 | 12.23 | 8500 | 0.6937 | 0.6320 | 0.2489 |
|
| 73 |
+
| 1.8515 | 12.95 | 9000 | 0.6443 | 0.6053 | 0.2196 |
|
| 74 |
+
| 1.8083 | 13.67 | 9500 | 0.6286 | 0.6122 | 0.2148 |
|
| 75 |
+
| 1.819 | 14.39 | 10000 | 0.6015 | 0.5986 | 0.2074 |
|
| 76 |
+
| 1.7684 | 15.11 | 10500 | 0.5682 | 0.5741 | 0.1982 |
|
| 77 |
+
| 1.7195 | 15.83 | 11000 | 0.5385 | 0.5592 | 0.2007 |
|
| 78 |
+
| 1.7044 | 16.55 | 11500 | 0.5362 | 0.5524 | 0.2097 |
|
| 79 |
+
| 1.6879 | 17.27 | 12000 | 0.5119 | 0.5489 | 0.2083 |
|
| 80 |
+
| 1.656 | 17.98 | 12500 | 0.4990 | 0.5362 | 0.1968 |
|
| 81 |
+
| 1.6122 | 18.7 | 13000 | 0.4561 | 0.5092 | 0.1900 |
|
| 82 |
+
| 1.5919 | 19.42 | 13500 | 0.4778 | 0.5225 | 0.1975 |
|
| 83 |
+
| 1.5896 | 20.14 | 14000 | 0.4563 | 0.5098 | 0.1859 |
|
| 84 |
+
| 1.5589 | 20.86 | 14500 | 0.4362 | 0.4940 | 0.1725 |
|
| 85 |
+
| 1.5353 | 21.58 | 15000 | 0.4140 | 0.4826 | 0.1580 |
|
| 86 |
+
| 1.5441 | 22.3 | 15500 | 0.4031 | 0.4742 | 0.1550 |
|
| 87 |
+
| 1.5116 | 23.02 | 16000 | 0.3916 | 0.4748 | 0.1545 |
|
| 88 |
+
| 1.4731 | 23.74 | 16500 | 0.3841 | 0.4810 | 0.1542 |
|
| 89 |
+
| 1.4647 | 24.46 | 17000 | 0.3752 | 0.4524 | 0.1475 |
|
| 90 |
+
| 1.4328 | 25.18 | 17500 | 0.3587 | 0.4476 | 0.1461 |
|
| 91 |
+
| 1.4129 | 25.9 | 18000 | 0.3429 | 0.4242 | 0.1366 |
|
| 92 |
+
| 1.4062 | 26.62 | 18500 | 0.3450 | 0.4251 | 0.1355 |
|
| 93 |
+
| 1.3928 | 27.34 | 19000 | 0.3297 | 0.4145 | 0.1322 |
|
| 94 |
+
| 1.3906 | 28.06 | 19500 | 0.3210 | 0.4185 | 0.1336 |
|
| 95 |
+
| 1.358 | 28.78 | 20000 | 0.3131 | 0.3970 | 0.1275 |
|
| 96 |
+
| 1.3445 | 29.5 | 20500 | 0.3069 | 0.3920 | 0.1276 |
|
| 97 |
+
| 1.3159 | 30.22 | 21000 | 0.3035 | 0.3961 | 0.1255 |
|
| 98 |
+
| 1.3044 | 30.93 | 21500 | 0.2952 | 0.3854 | 0.1242 |
|
| 99 |
+
| 1.3034 | 31.65 | 22000 | 0.2966 | 0.3772 | 0.1227 |
|
| 100 |
+
| 1.2963 | 32.37 | 22500 | 0.2844 | 0.3706 | 0.1208 |
|
| 101 |
+
| 1.2765 | 33.09 | 23000 | 0.2841 | 0.3567 | 0.1173 |
|
| 102 |
+
| 1.2438 | 33.81 | 23500 | 0.2734 | 0.3552 | 0.1137 |
|
| 103 |
+
| 1.2487 | 34.53 | 24000 | 0.2703 | 0.3502 | 0.1118 |
|
| 104 |
+
| 1.2249 | 35.25 | 24500 | 0.2650 | 0.3484 | 0.1142 |
|
| 105 |
+
| 1.2229 | 35.97 | 25000 | 0.2584 | 0.3374 | 0.1097 |
|
| 106 |
+
| 1.2374 | 36.69 | 25500 | 0.2568 | 0.3337 | 0.1095 |
|
| 107 |
+
| 1.2153 | 37.41 | 26000 | 0.2494 | 0.3327 | 0.1071 |
|
| 108 |
+
| 1.1925 | 38.13 | 26500 | 0.2518 | 0.3366 | 0.1077 |
|
| 109 |
+
| 1.1908 | 38.85 | 27000 | 0.2437 | 0.3272 | 0.1057 |
|
| 110 |
+
| 1.1858 | 39.57 | 27500 | 0.2396 | 0.3265 | 0.1044 |
|
| 111 |
+
| 1.1808 | 40.29 | 28000 | 0.2373 | 0.3156 | 0.1028 |
|
| 112 |
+
| 1.1842 | 41.01 | 28500 | 0.2356 | 0.3152 | 0.1026 |
|
| 113 |
+
| 1.1668 | 41.73 | 29000 | 0.2319 | 0.3188 | 0.1025 |
|
| 114 |
+
| 1.1448 | 42.45 | 29500 | 0.2293 | 0.3099 | 0.0995 |
|
| 115 |
+
| 1.1327 | 43.17 | 30000 | 0.2265 | 0.3047 | 0.0979 |
|
| 116 |
+
| 1.1307 | 43.88 | 30500 | 0.2222 | 0.3078 | 0.0989 |
|
| 117 |
+
| 1.1419 | 44.6 | 31000 | 0.2215 | 0.3038 | 0.0981 |
|
| 118 |
+
| 1.1231 | 45.32 | 31500 | 0.2193 | 0.3013 | 0.0972 |
|
| 119 |
+
| 1.139 | 46.04 | 32000 | 0.2162 | 0.3007 | 0.0968 |
|
| 120 |
+
| 1.1114 | 46.76 | 32500 | 0.2122 | 0.2982 | 0.0960 |
|
| 121 |
+
| 1.111 | 47.48 | 33000 | 0.2125 | 0.2946 | 0.0948 |
|
| 122 |
+
| 1.0982 | 48.2 | 33500 | 0.2099 | 0.2957 | 0.0953 |
|
| 123 |
+
| 1.109 | 48.92 | 34000 | 0.2092 | 0.2955 | 0.0955 |
|
| 124 |
+
| 1.0905 | 49.64 | 34500 | 0.2088 | 0.2954 | 0.0953 |
|
| 125 |
+
|
| 126 |
+
|
| 127 |
+
### Framework versions
|
| 128 |
+
|
| 129 |
+
- Transformers 4.17.0.dev0
|
| 130 |
+
- Pytorch 1.10.2+cu102
|
| 131 |
+
- Datasets 1.18.2.dev0
|
| 132 |
+
- Tokenizers 0.10.3
|
nohup.out
CHANGED
|
@@ -5697,3 +5697,24 @@ Saving model checkpoint to ./
|
|
| 5697 |
Configuration saved in ./config.json
|
| 5698 |
Model weights saved in ./pytorch_model.bin
|
| 5699 |
Configuration saved in ./preprocessor_config.json
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5697 |
Configuration saved in ./config.json
|
| 5698 |
Model weights saved in ./pytorch_model.bin
|
| 5699 |
Configuration saved in ./preprocessor_config.json
|
| 5700 |
+
Several commits (2) will be pushed upstream.
|
| 5701 |
+
{'eval_loss': 0.20883652567863464, 'eval_wer': 0.2953790395650861, 'eval_cer': 0.09526058888364038, 'eval_runtime': 40.602, 'eval_samples_per_second': 11.231, 'eval_steps_per_second': 1.404, 'epoch': 49.64}
|
| 5702 |
+
{'loss': 1.0961, 'learning_rate': 3.778625954198473e-07, 'epoch': 49.78}
|
| 5703 |
+
{'loss': 1.095, 'learning_rate': 1.4885496183206107e-07, 'epoch': 49.93}
|
| 5704 |
+
{'train_runtime': 114311.9751, 'train_samples_per_second': 9.737, 'train_steps_per_second': 0.304, 'train_loss': 2.2316733406121783, 'epoch': 50.0}
|
| 5705 |
+
02/01/2022 15:04:50 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
|
| 5706 |
+
The progress bars may be unreliable.
|
| 5707 |
+
02/01/2022 15:04:50 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
|
| 5708 |
+
|
| 5709 |
+
|
| 5710 |
+
816ebc3..024e2da main -> main
|
| 5711 |
+
|
| 5712 |
+
02/01/2022 15:05:46 - WARNING - huggingface_hub.repository - To https://huggingface.co/w11wo/wav2vec2-xls-r-300m-korean
|
| 5713 |
+
816ebc3..024e2da main -> main
|
| 5714 |
+
|
| 5715 |
+
|
| 5716 |
+
|
| 5717 |
+
|
| 5718 |
+
|
| 5719 |
+
Dropping the following result as it does not have all the necessary fields:
|
| 5720 |
+
{'dataset': {'name': 'zeroth_korean_asr', 'type': 'zeroth_korean_asr', 'args': 'clean'}}
|