aconeil commited on
Commit
533d62a
·
verified ·
1 Parent(s): 1972145

End of training

Browse files
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Wer
25
  type: wer
26
- value: 0.7700348432055749
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +33,9 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the audiofolder dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 2.2629
37
- - Wer: 0.7700
38
- - Cer: 0.3244
39
 
40
  ## Model description
41
 
@@ -70,22 +70,22 @@ The following hyperparameters were used during training:
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
72
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
73
- | 5.732 | 6.25 | 100 | 3.3371 | 1.0 | 1.0 |
74
- | 3.0052 | 12.5 | 200 | 2.8812 | 1.0 | 1.0 |
75
- | 2.6434 | 18.75 | 300 | 2.3653 | 1.0 | 0.8850 |
76
- | 0.8393 | 25.0 | 400 | 1.5602 | 0.7770 | 0.3488 |
77
- | 0.2892 | 31.25 | 500 | 1.6106 | 0.7770 | 0.3298 |
78
- | 0.1167 | 37.5 | 600 | 1.7649 | 0.7909 | 0.3267 |
79
- | 0.0595 | 43.75 | 700 | 1.8324 | 0.7666 | 0.3138 |
80
- | 0.0337 | 50.0 | 800 | 2.0307 | 0.7875 | 0.3351 |
81
- | 0.0222 | 56.25 | 900 | 2.0604 | 0.7840 | 0.3305 |
82
- | 0.015 | 62.5 | 1000 | 2.1389 | 0.7735 | 0.3313 |
83
- | 0.0127 | 68.75 | 1100 | 2.1756 | 0.7700 | 0.3260 |
84
- | 0.0109 | 75.0 | 1200 | 2.2084 | 0.7805 | 0.3283 |
85
- | 0.0097 | 81.25 | 1300 | 2.2374 | 0.7805 | 0.3267 |
86
- | 0.0088 | 87.5 | 1400 | 2.2508 | 0.7700 | 0.3252 |
87
- | 0.008 | 93.75 | 1500 | 2.2586 | 0.7735 | 0.3252 |
88
- | 0.0077 | 100.0 | 1600 | 2.2629 | 0.7700 | 0.3244 |
89
 
90
 
91
  ### Framework versions
 
23
  metrics:
24
  - name: Wer
25
  type: wer
26
+ value: 0.9372822299651568
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the audiofolder dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 1.4927
37
+ - Wer: 0.9373
38
+ - Cer: 0.4631
39
 
40
  ## Model description
41
 
 
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
72
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
73
+ | 11.1283 | 6.25 | 100 | 7.6957 | 1.0 | 1.0 |
74
+ | 3.4765 | 12.5 | 200 | 3.0361 | 1.0 | 1.0 |
75
+ | 3.0411 | 18.75 | 300 | 2.9111 | 1.0 | 1.0 |
76
+ | 2.9832 | 25.0 | 400 | 2.8719 | 1.0 | 1.0 |
77
+ | 2.9412 | 31.25 | 500 | 2.8650 | 1.0 | 1.0 |
78
+ | 2.9002 | 37.5 | 600 | 2.8412 | 1.0 | 1.0 |
79
+ | 2.9023 | 43.75 | 700 | 2.8232 | 1.0 | 1.0 |
80
+ | 2.7997 | 50.0 | 800 | 2.6466 | 1.0 | 0.9985 |
81
+ | 2.7052 | 56.25 | 900 | 2.4730 | 1.0 | 0.9863 |
82
+ | 2.5173 | 62.5 | 1000 | 2.2351 | 1.0 | 0.9337 |
83
+ | 2.3026 | 68.75 | 1100 | 1.9446 | 0.9721 | 0.7403 |
84
+ | 2.1178 | 75.0 | 1200 | 1.7418 | 0.9756 | 0.5903 |
85
+ | 1.9672 | 81.25 | 1300 | 1.5979 | 0.9477 | 0.5217 |
86
+ | 1.891 | 87.5 | 1400 | 1.5311 | 0.9443 | 0.4958 |
87
+ | 1.827 | 93.75 | 1500 | 1.4928 | 0.9443 | 0.4714 |
88
+ | 1.8131 | 100.0 | 1600 | 1.4927 | 0.9373 | 0.4631 |
89
 
90
 
91
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e1f6bea52c3ff45ea92e54f87946b1d69cfb4b9ab58707ecb8de8bc2d359c1c
3
  size 1261938680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db7e8b18907118cf217d65b8959e963232e9503dbc4701470c587f7cbc9ab121
3
  size 1261938680
runs/Nov21_15-28-53_x1001c1s7b0n1/events.out.tfevents.1763756943.x1001c1s7b0n1.480367.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5ba354e8d5dcdfd75933f5923208f83a6c2f5f126a50e61ec5b8f65645ae719
3
- size 16098
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa9fe6b196f2d3ab7507f482cdf2d6f11347aa7852cfc64785071e9d571066c
3
+ size 19600