St4n commited on
Commit
2fdcfb4
1 Parent(s): 95f7dd7

End of training

Browse files
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.98989898989899
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 2.5154
36
- - Wer: 0.9899
37
 
38
  ## Model description
39
 
@@ -61,16 +61,22 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
- - num_epochs: 100
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Wer |
70
- |:-------------:|:-----:|:----:|:---------------:|:------:|
71
- | 4.3029 | 30.77 | 200 | 3.5530 | 1.0 |
72
- | 3.3121 | 61.54 | 400 | 3.0604 | 1.0 |
73
- | 2.7461 | 92.31 | 600 | 2.5154 | 0.9899 |
 
 
 
 
 
 
74
 
75
 
76
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.15007215007215008
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.3282
36
+ - Wer: 0.1501
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
+ - num_epochs: 300
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
70
+ |:-------------:|:------:|:----:|:---------------:|:------:|
71
+ | 2.3444 | 30.77 | 200 | 2.1940 | 0.9841 |
72
+ | 1.972 | 61.54 | 400 | 1.4582 | 0.8167 |
73
+ | 1.3875 | 92.31 | 600 | 0.8476 | 0.5902 |
74
+ | 0.9092 | 123.08 | 800 | 0.5445 | 0.3636 |
75
+ | 0.6382 | 153.85 | 1000 | 0.4129 | 0.2641 |
76
+ | 0.5789 | 184.62 | 1200 | 0.3497 | 0.1876 |
77
+ | 0.4632 | 215.38 | 1400 | 0.3478 | 0.1616 |
78
+ | 0.4474 | 246.15 | 1600 | 0.3394 | 0.1486 |
79
+ | 0.429 | 276.92 | 1800 | 0.3282 | 0.1501 |
80
 
81
 
82
  ### Framework versions
runs/Mar31_08-54-59_ae4be65433ef/events.out.tfevents.1711875323.ae4be65433ef.291.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a7bd036373f61e69487c267db8bda631323dfb6ae72e55c26cbbe043b901136
3
- size 10829
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a76192d7ee93c6811d0c4443c2ea4c23e5fec521a65e7b3403c9d405f40ae9
3
+ size 11183