Hugging Face's logo

8688chris
/
helldivers2-jarvis-asr

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Community
8688chris commited on
Commit
f1be435
·
verified ·
1 Parent(s): 0568b19

Model save

Browse files
Files changed (3) hide show
  1. README.md +39 -54
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 27.9738
22
- - Wer: 0.2748
23
- - Cer: 0.8162
24
 
25
  ## Model description
26
 
@@ -46,62 +46,47 @@ The following hyperparameters were used during training:
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 50
49
- - num_epochs: 50
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
55
- | 567.6252 | 1.0 | 29 | 265.1855 | 0.5115 | 0.8359 |
56
- | 446.7473 | 2.0 | 58 | 166.1305 | 0.4198 | 0.8276 |
57
- | 356.9441 | 3.0 | 87 | 153.3023 | 0.4198 | 0.8267 |
58
- | 324.2485 | 4.0 | 116 | 130.9727 | 0.3931 | 0.8259 |
59
- | 289.06 | 5.0 | 145 | 119.9216 | 0.3893 | 0.8251 |
60
- | 272.9291 | 6.0 | 174 | 109.9049 | 0.3779 | 0.8243 |
61
- | 266.9849 | 7.0 | 203 | 102.6553 | 0.3702 | 0.8227 |
62
- | 240.1825 | 8.0 | 232 | 94.2803 | 0.3740 | 0.8225 |
63
- | 239.1444 | 9.0 | 261 | 88.5568 | 0.3817 | 0.8225 |
64
- | 225.3515 | 10.0 | 290 | 77.9165 | 0.3626 | 0.8215 |
65
- | 209.4354 | 11.0 | 319 | 67.2266 | 0.3397 | 0.8206 |
66
- | 211.1932 | 12.0 | 348 | 69.1964 | 0.3397 | 0.8208 |
67
- | 203.8638 | 13.0 | 377 | 70.6125 | 0.3244 | 0.8198 |
68
- | 200.9149 | 14.0 | 406 | 68.4602 | 0.3168 | 0.8198 |
69
- | 201.0955 | 15.0 | 435 | 65.2835 | 0.3244 | 0.8194 |
70
- | 188.8404 | 16.0 | 464 | 56.8926 | 0.3053 | 0.8190 |
71
- | 192.3149 | 17.0 | 493 | 55.7907 | 0.3092 | 0.8188 |
72
- | 177.7656 | 18.0 | 522 | 52.2180 | 0.3053 | 0.8180 |
73
- | 187.5363 | 19.0 | 551 | 50.1185 | 0.3015 | 0.8180 |
74
- | 176.8395 | 20.0 | 580 | 45.1555 | 0.2977 | 0.8176 |
75
- | 165.1503 | 21.0 | 609 | 46.3892 | 0.3015 | 0.8182 |
76
- | 167.2915 | 22.0 | 638 | 41.7496 | 0.2939 | 0.8170 |
77
- | 173.7115 | 23.0 | 667 | 38.6539 | 0.2748 | 0.8168 |
78
- | 158.6305 | 24.0 | 696 | 41.3843 | 0.2748 | 0.8170 |
79
- | 163.5118 | 25.0 | 725 | 43.4713 | 0.2786 | 0.8170 |
80
- | 156.5214 | 26.0 | 754 | 37.1832 | 0.2786 | 0.8170 |
81
- | 149.6598 | 27.0 | 783 | 39.2282 | 0.2710 | 0.8164 |
82
- | 162.3566 | 28.0 | 812 | 35.9909 | 0.2672 | 0.8160 |
83
- | 147.1838 | 29.0 | 841 | 36.8487 | 0.2672 | 0.8163 |
84
- | 161.0397 | 30.0 | 870 | 33.8363 | 0.2786 | 0.8166 |
85
- | 145.6303 | 31.0 | 899 | 31.7479 | 0.2786 | 0.8163 |
86
- | 143.5628 | 32.0 | 928 | 31.2131 | 0.2748 | 0.8164 |
87
- | 141.3279 | 33.0 | 957 | 33.3119 | 0.2748 | 0.8164 |
88
- | 139.9798 | 34.0 | 986 | 33.9929 | 0.2748 | 0.8167 |
89
- | 146.7861 | 35.0 | 1015 | 30.2105 | 0.2748 | 0.8162 |
90
- | 143.4238 | 36.0 | 1044 | 30.6071 | 0.2748 | 0.8162 |
91
- | 144.0004 | 37.0 | 1073 | 31.6426 | 0.2710 | 0.8164 |
92
- | 132.4875 | 38.0 | 1102 | 31.5941 | 0.2672 | 0.8163 |
93
- | 136.6988 | 39.0 | 1131 | 31.4831 | 0.2786 | 0.8160 |
94
- | 140.3245 | 40.0 | 1160 | 30.7406 | 0.2748 | 0.8163 |
95
- | 134.9336 | 41.0 | 1189 | 27.2539 | 0.2710 | 0.8159 |
96
- | 137.4191 | 42.0 | 1218 | 31.5850 | 0.2710 | 0.8163 |
97
- | 127.3477 | 43.0 | 1247 | 30.0975 | 0.2710 | 0.8160 |
98
- | 131.8254 | 44.0 | 1276 | 29.5515 | 0.2710 | 0.8160 |
99
- | 141.5767 | 45.0 | 1305 | 30.7776 | 0.2748 | 0.8160 |
100
- | 131.8489 | 46.0 | 1334 | 30.3350 | 0.2748 | 0.8160 |
101
- | 131.7956 | 47.0 | 1363 | 27.0517 | 0.2748 | 0.8160 |
102
- | 132.2804 | 48.0 | 1392 | 27.6437 | 0.2710 | 0.8159 |
103
- | 137.8569 | 49.0 | 1421 | 29.0478 | 0.2672 | 0.8160 |
104
- | 131.7815 | 50.0 | 1450 | 27.9738 | 0.2748 | 0.8162 |
105
 
106
 
107
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 59.4560
22
+ - Wer: 0.2597
23
+ - Cer: 0.8461
24
 
25
  ## Model description
26
 
 
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 50
49
+ - num_epochs: 35
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
55
+ | 592.8701 | 1.0 | 33 | 309.4361 | 0.4890 | 0.8633 |
56
+ | 451.2683 | 2.0 | 66 | 203.9322 | 0.3950 | 0.8575 |
57
+ | 379.4145 | 3.0 | 99 | 167.4042 | 0.3591 | 0.8544 |
58
+ | 336.9402 | 4.0 | 132 | 150.8170 | 0.3398 | 0.8525 |
59
+ | 321.581 | 5.0 | 165 | 134.3422 | 0.3232 | 0.8515 |
60
+ | 286.1988 | 6.0 | 198 | 118.7198 | 0.3232 | 0.8504 |
61
+ | 275.0421 | 7.0 | 231 | 98.2645 | 0.3232 | 0.8503 |
62
+ | 271.4439 | 8.0 | 264 | 96.4090 | 0.3149 | 0.8501 |
63
+ | 257.0019 | 9.0 | 297 | 90.3913 | 0.3094 | 0.8490 |
64
+ | 237.0949 | 10.0 | 330 | 86.4160 | 0.2928 | 0.8484 |
65
+ | 245.8697 | 11.0 | 363 | 86.0826 | 0.2901 | 0.8485 |
66
+ | 237.8742 | 12.0 | 396 | 84.3617 | 0.2901 | 0.8478 |
67
+ | 234.2587 | 13.0 | 429 | 78.6872 | 0.2845 | 0.8481 |
68
+ | 209.8943 | 14.0 | 462 | 81.1480 | 0.2873 | 0.8478 |
69
+ | 226.1856 | 15.0 | 495 | 86.4198 | 0.2790 | 0.8481 |
70
+ | 200.5639 | 16.0 | 528 | 73.4982 | 0.2735 | 0.8473 |
71
+ | 206.5734 | 17.0 | 561 | 70.4848 | 0.2735 | 0.8473 |
72
+ | 190.7183 | 18.0 | 594 | 69.2320 | 0.2818 | 0.8474 |
73
+ | 224.0161 | 19.0 | 627 | 63.0107 | 0.2680 | 0.8467 |
74
+ | 202.4105 | 20.0 | 660 | 69.8898 | 0.2790 | 0.8467 |
75
+ | 189.4804 | 21.0 | 693 | 64.9169 | 0.2790 | 0.8469 |
76
+ | 194.0889 | 22.0 | 726 | 73.2138 | 0.2735 | 0.8464 |
77
+ | 177.1985 | 23.0 | 759 | 69.4830 | 0.2735 | 0.8464 |
78
+ | 179.883 | 24.0 | 792 | 67.9310 | 0.2624 | 0.8462 |
79
+ | 184.1469 | 25.0 | 825 | 65.2100 | 0.2735 | 0.8464 |
80
+ | 180.9639 | 26.0 | 858 | 65.6959 | 0.2707 | 0.8465 |
81
+ | 161.8609 | 27.0 | 891 | 64.2684 | 0.2597 | 0.8461 |
82
+ | 176.6417 | 28.0 | 924 | 64.3977 | 0.2652 | 0.8459 |
83
+ | 162.5974 | 29.0 | 957 | 61.5234 | 0.2597 | 0.8458 |
84
+ | 174.1075 | 30.0 | 990 | 64.5171 | 0.2597 | 0.8459 |
85
+ | 165.3279 | 31.0 | 1023 | 64.0766 | 0.2597 | 0.8458 |
86
+ | 174.7633 | 32.0 | 1056 | 70.9056 | 0.2680 | 0.8464 |
87
+ | 166.3098 | 33.0 | 1089 | 61.5759 | 0.2707 | 0.8460 |
88
+ | 176.9802 | 34.0 | 1122 | 59.8946 | 0.2652 | 0.8461 |
89
+ | 161.3542 | 35.0 | 1155 | 59.4560 | 0.2597 | 0.8461 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90
 
91
 
92
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1781d715476195d4d180fc7bb2ed3e256d7d471b5bd53e7b5ce2ce4a6d4dff5f
3
  size 377611120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8df061d5e2eb218f900f5be4802618f3c4ab7f42caaff5b997914fcfcf231b
3
  size 377611120
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75fe1115f0937efec64857565249fbf5a365ca25b910579e59d70cd36e2975c3
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8387dd332dd698d6e2be38dc5e85b847e3f507e7b37f766e16d54a8f68ad5331
3
  size 5368