Hugging Face's logo

8688chris
/
Helldivers2ASR_V2

Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
8688chris commited on
Commit
286055e
·
verified ·
1 Parent(s): 224bb0f

Model save

Browse files
Files changed (4) hide show
  1. README.md +33 -33
  2. config.json +4 -4
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 600.7576
21
- - Wer: 0.1781
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 5e-05
41
  - train_batch_size: 32
42
  - eval_batch_size: 32
43
  - seed: 42
@@ -50,36 +50,36 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
- | 1606.3359 | 1.0 | 220 | 1090.8248 | 0.5061 |
54
- | 1121.8479 | 2.0 | 440 | 865.5970 | 0.4061 |
55
- | 946.2823 | 3.0 | 660 | 820.0260 | 0.3625 |
56
- | 783.6905 | 4.0 | 880 | 707.9121 | 0.3211 |
57
- | 695.3827 | 5.0 | 1100 | 838.1756 | 0.3111 |
58
- | 622.7798 | 6.0 | 1320 | 742.3585 | 0.2847 |
59
- | 553.7608 | 7.0 | 1540 | 716.7022 | 0.2676 |
60
- | 491.1993 | 8.0 | 1760 | 761.7335 | 0.2603 |
61
- | 473.3195 | 9.0 | 1980 | 567.7379 | 0.2178 |
62
- | 437.2569 | 10.0 | 2200 | 702.8529 | 0.2387 |
63
- | 399.1445 | 11.0 | 2420 | 606.8059 | 0.2159 |
64
- | 365.5832 | 12.0 | 2640 | 668.2637 | 0.2218 |
65
- | 352.0708 | 13.0 | 2860 | 618.1540 | 0.2013 |
66
- | 345.8254 | 14.0 | 3080 | 605.1513 | 0.2025 |
67
- | 301.8691 | 15.0 | 3300 | 534.0126 | 0.1824 |
68
- | 306.2117 | 16.0 | 3520 | 525.6846 | 0.1769 |
69
- | 276.5106 | 17.0 | 3740 | 588.5739 | 0.1812 |
70
- | 278.9943 | 18.0 | 3960 | 586.8976 | 0.1856 |
71
- | 254.1533 | 19.0 | 4180 | 565.0082 | 0.1785 |
72
- | 264.3702 | 20.0 | 4400 | 636.0349 | 0.1922 |
73
- | 246.2727 | 21.0 | 4620 | 574.8817 | 0.1783 |
74
- | 237.4068 | 22.0 | 4840 | 525.9941 | 0.1700 |
75
- | 229.2964 | 23.0 | 5060 | 583.3613 | 0.1751 |
76
- | 228.483 | 24.0 | 5280 | 625.8549 | 0.1804 |
77
- | 225.443 | 25.0 | 5500 | 592.6890 | 0.1779 |
78
- | 223.0987 | 26.0 | 5720 | 610.0046 | 0.1781 |
79
- | 211.6382 | 27.0 | 5940 | 600.6169 | 0.1783 |
80
- | 215.4619 | 28.0 | 6160 | 598.9771 | 0.1787 |
81
- | 220.9056 | 29.0 | 6380 | 600.8087 | 0.1783 |
82
- | 222.1433 | 30.0 | 6600 | 600.7576 | 0.1781 |
83
 
84
 
85
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 403.7162
21
+ - Wer: 0.1140
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 7e-05
41
  - train_batch_size: 32
42
  - eval_batch_size: 32
43
  - seed: 42
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 1549.7986 | 1.0 | 239 | 1010.8287 | 0.4509 |
54
+ | 1073.833 | 2.0 | 478 | 847.1273 | 0.3799 |
55
+ | 863.4314 | 3.0 | 717 | 669.3406 | 0.3011 |
56
+ | 735.351 | 4.0 | 956 | 701.8651 | 0.3046 |
57
+ | 646.4708 | 5.0 | 1195 | 516.7015 | 0.2290 |
58
+ | 555.7994 | 6.0 | 1434 | 563.6837 | 0.2194 |
59
+ | 511.6518 | 7.0 | 1673 | 463.4145 | 0.1902 |
60
+ | 442.7085 | 8.0 | 1912 | 473.8917 | 0.1862 |
61
+ | 419.5254 | 9.0 | 2151 | 513.1998 | 0.1893 |
62
+ | 372.6168 | 10.0 | 2390 | 424.3353 | 0.1622 |
63
+ | 321.958 | 11.0 | 2629 | 430.3576 | 0.1550 |
64
+ | 321.6388 | 12.0 | 2868 | 422.5235 | 0.1624 |
65
+ | 293.641 | 13.0 | 3107 | 359.6511 | 0.1239 |
66
+ | 270.1068 | 14.0 | 3346 | 455.4551 | 0.1461 |
67
+ | 258.8057 | 15.0 | 3585 | 466.8189 | 0.1465 |
68
+ | 256.9584 | 16.0 | 3824 | 402.8066 | 0.1282 |
69
+ | 231.2268 | 17.0 | 4063 | 456.3300 | 0.1415 |
70
+ | 222.786 | 18.0 | 4302 | 329.8922 | 0.1127 |
71
+ | 213.7656 | 19.0 | 4541 | 463.8095 | 0.1426 |
72
+ | 188.9466 | 20.0 | 4780 | 337.8596 | 0.1132 |
73
+ | 199.4221 | 21.0 | 5019 | 390.5159 | 0.1212 |
74
+ | 189.1897 | 22.0 | 5258 | 384.9171 | 0.1190 |
75
+ | 182.3199 | 23.0 | 5497 | 375.2046 | 0.1143 |
76
+ | 180.674 | 24.0 | 5736 | 426.1663 | 0.1223 |
77
+ | 160.5728 | 25.0 | 5975 | 411.1659 | 0.1204 |
78
+ | 161.0371 | 26.0 | 6214 | 417.6654 | 0.1158 |
79
+ | 169.4026 | 27.0 | 6453 | 412.9657 | 0.1141 |
80
+ | 162.3533 | 28.0 | 6692 | 407.0595 | 0.1143 |
81
+ | 169.8538 | 29.0 | 6931 | 404.1884 | 0.1143 |
82
+ | 187.099 | 30.0 | 7170 | 403.7162 | 0.1140 |
83
 
84
 
85
  ### Framework versions
config.json CHANGED
@@ -9,7 +9,7 @@
9
  "architectures": [
10
  "Wav2Vec2ForCTC"
11
  ],
12
- "attention_dropout": 0.1,
13
  "bos_token_id": 1,
14
  "classifier_proj_size": 256,
15
  "codevector_dim": 256,
@@ -50,12 +50,12 @@
50
  "feat_extract_activation": "gelu",
51
  "feat_extract_dropout": 0.0,
52
  "feat_extract_norm": "group",
53
- "feat_proj_dropout": 0.1,
54
  "feat_quantizer_dropout": 0.0,
55
- "final_dropout": 0.1,
56
  "gradient_checkpointing": false,
57
  "hidden_act": "gelu",
58
- "hidden_dropout": 0.1,
59
  "hidden_dropout_prob": 0.1,
60
  "hidden_size": 768,
61
  "initializer_range": 0.02,
 
9
  "architectures": [
10
  "Wav2Vec2ForCTC"
11
  ],
12
+ "attention_dropout": 0.15,
13
  "bos_token_id": 1,
14
  "classifier_proj_size": 256,
15
  "codevector_dim": 256,
 
50
  "feat_extract_activation": "gelu",
51
  "feat_extract_dropout": 0.0,
52
  "feat_extract_norm": "group",
53
+ "feat_proj_dropout": 0.15,
54
  "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.15,
56
  "gradient_checkpointing": false,
57
  "hidden_act": "gelu",
58
+ "hidden_dropout": 0.15,
59
  "hidden_dropout_prob": 0.1,
60
  "hidden_size": 768,
61
  "initializer_range": 0.02,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe6446293ae0a7864146c962bd7a254f44c6cd554d7d8ed1187db4e4cecb7df5
3
  size 377611120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773293c3bae0a76839e8985759ccd76c699d4f1a95ffe0594d407c3ba961f6a8
3
  size 377611120
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9a5ac5f909ac46ee0cff8e56b7936b98549642616256a1eb1094ac9e1361878
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c68cb2889e77e32ab791419f8cfa4bcb55308617ff51465c82b2b80c64448509
3
  size 5240