indrajitharidas commited on
Commit
6ff8afe
1 Parent(s): 81822ec

Model save

Browse files
README.md CHANGED
@@ -19,19 +19,19 @@ model-index:
19
  dataset:
20
  name: audiofolder
21
  type: audiofolder
22
- config: default
23
- split: train
24
- args: default
25
  metrics:
26
  - name: F1
27
  type: f1
28
- value: 0.5864661654135338
29
  - name: Precision
30
  type: precision
31
- value: 0.42391304347826086
32
  - name: Recall
33
  type: recall
34
- value: 0.9512195121951219
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,10 +41,10 @@ should probably proofread and complete it, then remove this comment. -->
41
 
42
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
43
  It achieves the following results on the evaluation set:
44
- - Loss: 0.9514
45
- - F1: 0.5865
46
- - Precision: 0.4239
47
- - Recall: 0.9512
48
 
49
  ## Model description
50
 
@@ -76,14 +76,18 @@ The following hyperparameters were used during training:
76
 
77
  ### Training results
78
 
79
- | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall |
80
- |:-------------:|:------:|:----:|:---------------:|:------:|:---------:|:------:|
81
- | No log | 0.5714 | 1 | 1.0873 | 0.0 | 0.0 | 0.0 |
82
- | No log | 1.7143 | 3 | 1.0299 | 0.1111 | 0.2308 | 0.0732 |
83
- | No log | 2.8571 | 5 | 0.9925 | 0.3736 | 0.34 | 0.4146 |
84
- | No log | 4.0 | 7 | 0.9678 | 0.5397 | 0.4 | 0.8293 |
85
- | No log | 4.5714 | 8 | 0.9594 | 0.5538 | 0.4045 | 0.8780 |
86
- | 1.006 | 5.7143 | 10 | 0.9514 | 0.5865 | 0.4239 | 0.9512 |
 
 
 
 
87
 
88
 
89
  ### Framework versions
 
19
  dataset:
20
  name: audiofolder
21
  type: audiofolder
22
+ config: initial_audio
23
+ split: test
24
+ args: initial_audio
25
  metrics:
26
  - name: F1
27
  type: f1
28
+ value: 0.4
29
  - name: Precision
30
  type: precision
31
+ value: 0.6923076923076923
32
  - name: Recall
33
  type: recall
34
+ value: 0.28125
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
41
 
42
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
43
  It achieves the following results on the evaluation set:
44
+ - Loss: 0.8348
45
+ - F1: 0.4
46
+ - Precision: 0.6923
47
+ - Recall: 0.2812
48
 
49
  ## Model description
50
 
 
76
 
77
  ### Training results
78
 
79
+ | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall |
80
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|
81
+ | No log | 1.0 | 2 | 1.0602 | 0.6667 | 0.5 | 1.0 |
82
+ | No log | 2.0 | 4 | 1.0043 | 0.6667 | 0.5 | 1.0 |
83
+ | No log | 3.0 | 6 | 0.9622 | 0.625 | 0.5208 | 0.7812 |
84
+ | No log | 4.0 | 8 | 0.9279 | 0.5902 | 0.6207 | 0.5625 |
85
+ | 1.0103 | 5.0 | 10 | 0.9005 | 0.5098 | 0.6842 | 0.4062 |
86
+ | 1.0103 | 6.0 | 12 | 0.8782 | 0.4286 | 0.9 | 0.2812 |
87
+ | 1.0103 | 7.0 | 14 | 0.8611 | 0.4651 | 0.9091 | 0.3125 |
88
+ | 1.0103 | 8.0 | 16 | 0.8478 | 0.3810 | 0.8 | 0.25 |
89
+ | 1.0103 | 9.0 | 18 | 0.8385 | 0.4 | 0.6923 | 0.2812 |
90
+ | 0.8578 | 10.0 | 20 | 0.8348 | 0.4 | 0.6923 | 0.2812 |
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:507cd15f5b691716363b4ef99cf391905e079e64f9dc4c960ff78d0f9ebb474a
3
  size 378303396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a1ab075d82d875ddd3ccd7e8b395678917925797600a91854741d64faab28bf
3
  size 378303396
runs/Sep23_14-43-19_Indrajits-MBP/events.out.tfevents.1727127802.Indrajits-MBP.67108.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74343bad06bab291cc35e4af4cb5cb742cc31326e5d2376a7f9b6e8e1f987ef4
3
- size 10912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd76947e18acdbdcf99a65890e8e703312f21b4eaa9e6a5ba54e4c1b44ba6341
3
+ size 11672