Commit
•
ff89ceb
1
Parent(s):
1458579
juniorjukeko/audio-class-minds14
Browse files- README.md +17 -12
- pytorch_model.bin +1 -1
README.md
CHANGED
@@ -8,7 +8,7 @@ datasets:
|
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
model-index:
|
11 |
-
- name:
|
12 |
results:
|
13 |
- task:
|
14 |
name: Audio Classification
|
@@ -22,18 +22,18 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
should probably proofread and complete it, then remove this comment. -->
|
30 |
|
31 |
-
#
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 2.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -52,29 +52,34 @@ More information needed
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
-
- learning_rate:
|
56 |
- train_batch_size: 32
|
57 |
- eval_batch_size: 32
|
58 |
-
- seed:
|
59 |
- gradient_accumulation_steps: 4
|
60 |
- total_train_batch_size: 128
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_ratio: 0.1
|
64 |
-
- num_epochs:
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
-
| No log | 0.8 | 3 | 2.
|
71 |
-
| No log | 1.87 | 7 | 2.
|
72 |
-
|
|
|
|
|
|
|
|
|
|
|
|
73 |
|
74 |
|
75 |
### Framework versions
|
76 |
|
77 |
-
- Transformers 4.33.
|
78 |
- Pytorch 2.0.1+cu118
|
79 |
- Datasets 2.14.5
|
80 |
- Tokenizers 0.13.3
|
|
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
model-index:
|
11 |
+
- name: audio-class-minds14
|
12 |
results:
|
13 |
- task:
|
14 |
name: Audio Classification
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.061946902654867256
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
should probably proofread and complete it, then remove this comment. -->
|
30 |
|
31 |
+
# audio-class-minds14
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 2.6413
|
36 |
+
- Accuracy: 0.0619
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-05
|
56 |
- train_batch_size: 32
|
57 |
- eval_batch_size: 32
|
58 |
+
- seed: 143
|
59 |
- gradient_accumulation_steps: 4
|
60 |
- total_train_batch_size: 128
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_ratio: 0.1
|
64 |
+
- num_epochs: 10
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| No log | 0.8 | 3 | 2.6388 | 0.0531 |
|
71 |
+
| No log | 1.87 | 7 | 2.6363 | 0.0442 |
|
72 |
+
| 2.6298 | 2.93 | 11 | 2.6413 | 0.0619 |
|
73 |
+
| 2.6298 | 4.0 | 15 | 2.6417 | 0.0531 |
|
74 |
+
| 2.6298 | 4.8 | 18 | 2.6425 | 0.0354 |
|
75 |
+
| 2.6296 | 5.87 | 22 | 2.6412 | 0.0354 |
|
76 |
+
| 2.6296 | 6.93 | 26 | 2.6427 | 0.0531 |
|
77 |
+
| 2.6175 | 8.0 | 30 | 2.6425 | 0.0442 |
|
78 |
|
79 |
|
80 |
### Framework versions
|
81 |
|
82 |
+
- Transformers 4.33.2
|
83 |
- Pytorch 2.0.1+cu118
|
84 |
- Datasets 2.14.5
|
85 |
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 378362729
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ba6a8565275ff84ed2dded28159811b23c9e03598db0ade1330303f1510f511
|
3 |
size 378362729
|