HF中国镜像站's logo

ekunish
/
wav2vec2-pretraining-demo

Transformers
TensorBoard
Safetensors
wav2vec2
pretraining
Generated from Trainer
Model card Files Metrics Community
ekunish commited on
Commit
66ed59c
·
verified ·
1 Parent(s): 8235997

End of training

Browse files
Files changed (1) hide show
  1. README.md +34 -38
README.md CHANGED
@@ -1,9 +1,9 @@
1
  ---
2
  library_name: transformers
3
- license: apache-2.0
4
- base_model: facebook/wav2vec2-base-960h
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: wav2vec2-pretraining-demo
9
  results: []
@@ -14,11 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # wav2vec2-pretraining-demo
16
 
17
- This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 451.3242
20
- - Constrast Loss: 443.2349
21
- - Div Loss: 80.8922
22
 
23
  ## Model description
24
 
@@ -49,38 +49,34 @@ The following hyperparameters were used during training:
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Constrast Loss | Div Loss |
53
- |:-------------:|:-----:|:----:|:---------------:|:--------------:|:--------:|
54
- | 478.7255 | 0.5 | 100 | 420.3063 | 412.4319 | 78.7440 |
55
- | 555.9113 | 1.0 | 200 | 407.1626 | 399.2634 | 78.9919 |
56
- | 555.9113 | 1.0 | 200 | 433.5689 | 425.1757 | 83.9328 |
57
- | 445.2046 | 1.5 | 300 | 390.8622 | 383.1959 | 76.6634 |
58
- | 480.6411 | 2.0 | 400 | 439.1803 | 430.9575 | 82.2276 |
59
- | 480.6411 | 2.0 | 400 | 403.2052 | 395.3518 | 78.5338 |
60
- | 484.0212 | 2.5 | 500 | 418.4225 | 410.3823 | 80.4012 |
61
- | 442.1686 | 3.0 | 600 | 410.6022 | 402.7102 | 78.9197 |
62
- | 442.1686 | 3.0 | 600 | 454.8314 | 446.3063 | 85.2508 |
63
- | 404.1281 | 3.5 | 700 | 423.5104 | 415.3885 | 81.2197 |
64
- | 479.2968 | 4.0 | 800 | 422.7674 | 414.8620 | 79.0535 |
65
- | 479.2968 | 4.0 | 800 | 433.8821 | 425.6849 | 81.9722 |
66
- | 482.9329 | 4.5 | 900 | 465.1997 | 456.7795 | 84.2019 |
67
- | 480.0253 | 5.0 | 1000 | 475.0238 | 466.5422 | 84.8163 |
68
- | 480.0253 | 5.0 | 1000 | 427.2379 | 419.3205 | 79.1747 |
69
- | 408.0809 | 5.5 | 1100 | 453.6945 | 445.3407 | 83.5376 |
70
- | 484.2443 | 6.0 | 1200 | 414.2449 | 406.5308 | 77.1410 |
71
- | 484.2443 | 6.0 | 1200 | 448.2039 | 439.9778 | 82.2607 |
72
- | 518.4024 | 6.5 | 1300 | 451.1086 | 442.8609 | 82.4774 |
73
- | 449.2522 | 7.0 | 1400 | 382.4106 | 375.1262 | 72.8438 |
74
- | 449.2522 | 7.0 | 1400 | 431.2335 | 423.1804 | 80.5309 |
75
- | 448.0326 | 7.5 | 1500 | 416.1967 | 408.4327 | 77.6399 |
76
- | 441.6883 | 8.0 | 1600 | 434.1829 | 426.2272 | 79.5572 |
77
- | 441.6883 | 8.0 | 1600 | 440.8153 | 432.5998 | 82.1544 |
78
- | 408.1424 | 8.5 | 1700 | 403.8840 | 396.4740 | 74.1004 |
79
- | 442.7975 | 9.0 | 1800 | 392.1655 | 384.8187 | 73.4681 |
80
- | 442.7975 | 9.0 | 1800 | 443.3363 | 435.3478 | 79.8843 |
81
- | 512.9667 | 9.5 | 1900 | 389.8308 | 382.4903 | 73.4044 |
82
- | 485.8844 | 10.0 | 2000 | 446.7708 | 438.7427 | 80.2811 |
83
- | 485.8844 | 10.0 | 2000 | 451.3242 | 443.2349 | 80.8922 |
84
 
85
 
86
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  tags:
4
  - generated_from_trainer
5
+ datasets:
6
+ - librispeech_asr
7
  model-index:
8
  - name: wav2vec2-pretraining-demo
9
  results: []
 
14
 
15
  # wav2vec2-pretraining-demo
16
 
17
+ This model is a fine-tuned version of [](https://huggingface.co/) on the librispeech_asr dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: nan
20
+ - Constrast Loss: 749.5483
21
+ - Div Loss: nan
22
 
23
  ## Model description
24
 
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Constrast Loss | Div Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|:--------------:|:--------:|
54
+ | 219.8029 | 0.3745 | 100 | nan | 761.2074 | nan |
55
+ | 363.6002 | 0.7491 | 200 | nan | 745.2168 | nan |
56
+ | 410.9734 | 1.1236 | 300 | nan | 736.6247 | nan |
57
+ | 516.6896 | 1.4981 | 400 | nan | 729.1328 | nan |
58
+ | 447.1916 | 1.8727 | 500 | nan | 724.2535 | nan |
59
+ | 991.6509 | 2.2472 | 600 | nan | 744.3330 | nan |
60
+ | 921.3181 | 2.6217 | 700 | nan | 741.7556 | nan |
61
+ | 453.8343 | 2.9963 | 800 | nan | 729.1232 | nan |
62
+ | 349.1257 | 3.3708 | 900 | nan | 727.2217 | nan |
63
+ | 342.4185 | 3.7453 | 1000 | nan | 730.2246 | nan |
64
+ | 524.263 | 4.1199 | 1100 | nan | 722.7736 | nan |
65
+ | 559.5258 | 4.4944 | 1200 | nan | 741.2823 | nan |
66
+ | 585.7782 | 4.8689 | 1300 | nan | 747.9285 | nan |
67
+ | 960.5108 | 5.2434 | 1400 | nan | 732.7294 | nan |
68
+ | 1073.0346 | 5.6180 | 1500 | nan | 764.7153 | nan |
69
+ | 449.7951 | 5.9925 | 1600 | nan | 743.8020 | nan |
70
+ | 371.2964 | 6.3670 | 1700 | nan | 739.3767 | nan |
71
+ | 359.0735 | 6.7416 | 1800 | nan | 746.6442 | nan |
72
+ | 632.9437 | 7.1161 | 1900 | nan | 754.3399 | nan |
73
+ | 517.3832 | 7.4906 | 2000 | nan | 711.9412 | nan |
74
+ | 482.2333 | 7.8652 | 2100 | nan | 706.3737 | nan |
75
+ | 939.8626 | 8.2397 | 2200 | nan | 757.2895 | nan |
76
+ | 992.2978 | 8.6142 | 2300 | nan | 741.9764 | nan |
77
+ | 517.6842 | 8.9888 | 2400 | nan | 744.0576 | nan |
78
+ | 365.4458 | 9.3633 | 2500 | nan | 749.9068 | nan |
79
+ | 375.0039 | 9.7378 | 2600 | nan | 749.5483 | nan |
 
 
 
 
80
 
81
 
82
  ### Framework versions