bigmorning's picture
Upload TFWhisperForConditionalGeneration
0893863
|
raw
history blame
11.9 kB
metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_keras_callback
model-index:
  - name: whisper_syl_cv12_pad_lob100__0090
    results: []

whisper_syl_cv12_pad_lob100__0090

This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.0012
  • Train Accuracy: 0.0362
  • Train Wermet: 0.0793
  • Validation Loss: 0.6028
  • Validation Accuracy: 0.0240
  • Validation Wermet: 0.2110
  • Epoch: 89

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:

  • optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Train Accuracy Train Wermet Validation Loss Validation Accuracy Validation Wermet Epoch
5.0233 0.0115 1.6383 3.8616 0.0117 0.9516 0
4.4412 0.0127 0.8560 3.5410 0.0125 0.8971 1
4.0719 0.0138 0.8366 3.2944 0.0132 0.8706 2
3.8091 0.0146 0.8133 3.1691 0.0134 0.8487 3
3.6239 0.0152 0.7866 3.0647 0.0136 0.8282 4
3.4749 0.0156 0.7589 2.9835 0.0139 0.8049 5
3.3444 0.0161 0.7359 2.9351 0.0140 0.7979 6
3.2215 0.0165 0.7138 2.8468 0.0145 0.7589 7
3.0754 0.0172 0.6873 2.7530 0.0148 0.7413 8
2.8713 0.0181 0.6484 2.5226 0.0157 0.7017 9
2.5469 0.0197 0.5934 2.1931 0.0168 0.6285 10
2.0233 0.0225 0.4997 1.6411 0.0189 0.5215 11
1.3808 0.0264 0.3852 1.2401 0.0205 0.4238 12
0.9722 0.0290 0.3123 1.0195 0.0215 0.3682 13
0.7388 0.0305 0.2828 0.8773 0.0221 0.3322 14
0.5787 0.0317 0.2751 0.7970 0.0225 0.3083 15
0.4642 0.0325 0.2878 0.7315 0.0227 0.2964 16
0.3752 0.0332 0.4217 0.6897 0.0229 0.3297 17
0.3042 0.0338 0.7294 0.6572 0.0231 0.4453 18
0.2444 0.0343 1.1298 0.6369 0.0232 0.6637 19
0.1949 0.0348 1.6370 0.6180 0.0233 1.6119 20
0.1544 0.0352 1.6151 0.6149 0.0233 1.6843 21
0.1212 0.0355 1.3832 0.6066 0.0233 0.8721 22
0.0931 0.0357 1.2799 0.6034 0.0234 0.5109 23
0.0725 0.0359 1.0940 0.6102 0.0234 1.0111 24
0.0551 0.0361 1.2865 0.6000 0.0234 1.1393 25
0.0411 0.0361 1.8511 0.6037 0.0235 2.0574 26
0.0311 0.0362 1.7179 0.6018 0.0235 1.4847 27
0.0253 0.0362 0.9801 0.6010 0.0235 0.4457 28
0.0231 0.0362 0.9376 0.6046 0.0235 0.9247 29
0.0196 0.0362 0.6466 0.6078 0.0235 0.5271 30
0.0177 0.0362 0.4041 0.6155 0.0235 0.4352 31
0.0139 0.0362 0.4202 0.6037 0.0236 0.5585 32
0.0137 0.0362 0.8151 0.6015 0.0236 1.8476 33
0.0122 0.0362 3.4515 0.6043 0.0236 3.8210 34
0.0098 0.0362 1.1787 0.5985 0.0236 0.8094 35
0.0071 0.0362 0.9920 0.5992 0.0236 0.8755 36
0.0055 0.0362 2.4665 0.6047 0.0236 2.0127 37
0.0124 0.0362 4.2468 0.6089 0.0236 2.8886 38
0.0109 0.0362 2.0177 0.6097 0.0236 0.3417 39
0.0073 0.0362 0.9927 0.6057 0.0237 2.5519 40
0.0080 0.0362 1.7341 0.6099 0.0236 1.3119 41
0.0063 0.0362 2.4288 0.6058 0.0237 1.3465 42
0.0038 0.0362 1.4535 0.6022 0.0237 1.6804 43
0.0028 0.0362 2.2629 0.6001 0.0238 3.4388 44
0.0021 0.0362 3.5877 0.6018 0.0238 2.6165 45
0.0017 0.0362 3.0080 0.6043 0.0238 2.6827 46
0.0061 0.0362 2.5182 0.6545 0.0235 0.2316 47
0.0126 0.0362 0.2097 0.6206 0.0236 0.6194 48
0.0071 0.0362 0.3045 0.6047 0.0237 0.7476 49
0.0053 0.0362 1.2045 0.6010 0.0238 0.6553 50
0.0040 0.0362 0.2626 0.5964 0.0238 0.7027 51
0.0021 0.0362 0.5023 0.5950 0.0238 0.3812 52
0.0014 0.0362 0.7108 0.6233 0.0237 1.4647 53
0.0017 0.0362 0.3475 0.6087 0.0238 0.2213 54
0.0011 0.0362 0.1825 0.5984 0.0239 0.2391 55
0.0021 0.0362 1.0757 0.6211 0.0238 7.3766 56
0.0078 0.0362 2.1996 0.6349 0.0237 5.2774 57
0.0071 0.0362 1.2499 0.6225 0.0237 0.9927 58
0.0045 0.0362 5.3986 0.6088 0.0238 27.5186 59
0.0027 0.0362 9.4813 0.6035 0.0239 0.2741 60
0.0015 0.0362 20.4251 0.6005 0.0239 73.4792 61
0.0012 0.0362 17.1227 0.6148 0.0238 4.2506 62
0.0024 0.0362 3.7081 0.6249 0.0238 5.8937 63
0.0050 0.0362 2.2590 0.6136 0.0238 9.6813 64
0.0026 0.0362 3.1954 0.6060 0.0239 15.4541 65
0.0032 0.0362 5.1838 0.6233 0.0238 10.2566 66
0.0053 0.0362 3.1310 0.6178 0.0239 1.4216 67
0.0030 0.0362 1.1169 0.6106 0.0239 0.9273 68
0.0018 0.0362 0.9183 0.6034 0.0239 1.7868 69
0.0011 0.0362 0.3862 0.6116 0.0239 0.5909 70
0.0014 0.0362 0.6235 0.6143 0.0239 0.9794 71
0.0025 0.0362 0.5583 0.6510 0.0237 0.3524 72
0.0058 0.0362 1.9614 0.6179 0.0239 1.2838 73
0.0029 0.0362 0.6039 0.6222 0.0239 3.0512 74
0.0013 0.0362 0.8265 0.6088 0.0239 1.1328 75
0.0008 0.0362 0.9354 0.6003 0.0240 4.7201 76
0.0008 0.0362 2.7001 0.6041 0.0240 6.5868 77
0.0005 0.0362 1.6010 0.6025 0.0240 3.0820 78
0.0003 0.0362 1.0294 0.6021 0.0240 2.5022 79
0.0003 0.0362 0.9028 0.6031 0.0240 2.7805 80
0.0003 0.0362 0.8890 0.6031 0.0240 2.9622 81
0.0002 0.0362 0.7687 0.6042 0.0240 1.8820 82
0.0002 0.0362 0.6602 0.6069 0.0240 1.7499 83
0.0002 0.0362 0.5823 0.6069 0.0240 1.3208 84
0.0003 0.0362 0.6356 0.6419 0.0239 0.7779 85
0.0156 0.0361 2.3703 0.6126 0.0239 1.5274 86
0.0062 0.0362 1.5064 0.6147 0.0239 0.9636 87
0.0025 0.0362 0.3498 0.6036 0.0240 0.3860 88
0.0012 0.0362 0.0793 0.6028 0.0240 0.2110 89

Framework versions

  • Transformers 4.33.0.dev0
  • TensorFlow 2.13.0
  • Tokenizers 0.13.3