Wiam commited on
Commit
329c523
1 Parent(s): e400a6a

End of training

Browse files
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: jonatasgrosman/wav2vec2-large-xlsr-53-english
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - audiofolder
9
+ metrics:
10
+ - accuracy
11
+ - f1
12
+ - precision
13
+ - recall
14
+ model-index:
15
+ - name: wav2vec2-large-xlsr-53-english-finetuned-babycry-v3
16
+ results:
17
+ - task:
18
+ name: Audio Classification
19
+ type: audio-classification
20
+ dataset:
21
+ name: audiofolder
22
+ type: audiofolder
23
+ config: default
24
+ split: train
25
+ args: default
26
+ metrics:
27
+ - name: Accuracy
28
+ type: accuracy
29
+ value:
30
+ accuracy: 0.8152173913043478
31
+ - name: F1
32
+ type: f1
33
+ value: 0.7322311897943244
34
+ - name: Precision
35
+ type: precision
36
+ value: 0.6645793950850661
37
+ - name: Recall
38
+ type: recall
39
+ value: 0.8152173913043478
40
+ ---
41
+
42
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
43
+ should probably proofread and complete it, then remove this comment. -->
44
+
45
+ # wav2vec2-large-xlsr-53-english-finetuned-babycry-v3
46
+
47
+ This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-english](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english) on the audiofolder dataset.
48
+ It achieves the following results on the evaluation set:
49
+ - Loss: 0.7337
50
+ - Accuracy: {'accuracy': 0.8152173913043478}
51
+ - F1: 0.7322
52
+ - Precision: 0.6646
53
+ - Recall: 0.8152
54
+
55
+ ## Model description
56
+
57
+ More information needed
58
+
59
+ ## Intended uses & limitations
60
+
61
+ More information needed
62
+
63
+ ## Training and evaluation data
64
+
65
+ More information needed
66
+
67
+ ## Training procedure
68
+
69
+ ### Training hyperparameters
70
+
71
+ The following hyperparameters were used during training:
72
+ - learning_rate: 0.001
73
+ - train_batch_size: 4
74
+ - eval_batch_size: 8
75
+ - seed: 42
76
+ - gradient_accumulation_steps: 2
77
+ - total_train_batch_size: 8
78
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
79
+ - lr_scheduler_type: linear
80
+ - lr_scheduler_warmup_ratio: 0.1
81
+ - num_epochs: 5
82
+
83
+ ### Training results
84
+
85
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
86
+ |:-------------:|:------:|:----:|:---------------:|:--------------------------------:|:------:|:---------:|:------:|
87
+ | 0.949 | 0.5435 | 25 | 0.7351 | {'accuracy': 0.8152173913043478} | 0.7322 | 0.6646 | 0.8152 |
88
+ | 0.7488 | 1.0870 | 50 | 0.7795 | {'accuracy': 0.8152173913043478} | 0.7322 | 0.6646 | 0.8152 |
89
+ | 0.6911 | 1.6304 | 75 | 0.7066 | {'accuracy': 0.8152173913043478} | 0.7322 | 0.6646 | 0.8152 |
90
+ | 0.8113 | 2.1739 | 100 | 0.8012 | {'accuracy': 0.8152173913043478} | 0.7322 | 0.6646 | 0.8152 |
91
+ | 0.634 | 2.7174 | 125 | 0.7801 | {'accuracy': 0.8152173913043478} | 0.7322 | 0.6646 | 0.8152 |
92
+ | 0.6503 | 3.2609 | 150 | 0.7712 | {'accuracy': 0.8152173913043478} | 0.7322 | 0.6646 | 0.8152 |
93
+ | 0.7523 | 3.8043 | 175 | 0.7078 | {'accuracy': 0.8152173913043478} | 0.7322 | 0.6646 | 0.8152 |
94
+ | 0.5493 | 4.3478 | 200 | 0.7484 | {'accuracy': 0.8152173913043478} | 0.7322 | 0.6646 | 0.8152 |
95
+ | 0.7253 | 4.8913 | 225 | 0.7341 | {'accuracy': 0.8152173913043478} | 0.7322 | 0.6646 | 0.8152 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.44.2
101
+ - Pytorch 2.4.1+cu121
102
+ - Datasets 3.0.1
103
+ - Tokenizers 0.19.1
runs/Oct01_15-49-58_c9432f693ceb/events.out.tfevents.1727798329.c9432f693ceb.266.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:298248a7fbaec0672ffecbe27d5814119b1adadbabae523a2ce46fbdebb560fd
3
+ size 508