Hugging Face's logo

jacobgill37
/
rio-model

Audio Classification
Transformers
ONNX
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Model card Files
xet
 Community
1
jacobgill37 commited on
Commit
4bbb9e0
·
verified ·
1 Parent(s): 56fb6e4

Model save

Browse files
Files changed (4) hide show
  1. README.md +12 -12
  2. config.json +8 -9
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.0215
22
- - Accuracy: 1.0
23
 
24
  ## Model description
25
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 0.4285 | 1.0 | 28 | 0.3599 | 0.84 |
55
- | 0.2423 | 2.0 | 56 | 0.1057 | 0.96 |
56
- | 0.0558 | 3.0 | 84 | 0.1450 | 0.96 |
57
- | 0.0007 | 4.0 | 112 | 0.2225 | 0.88 |
58
- | 0.0002 | 5.0 | 140 | 0.0106 | 1.0 |
59
- | 0.0002 | 6.0 | 168 | 0.0942 | 0.96 |
60
- | 0.0001 | 7.0 | 196 | 0.0302 | 1.0 |
61
- | 0.0 | 8.0 | 224 | 0.0212 | 1.0 |
62
- | 0.0 | 9.0 | 252 | 0.0214 | 1.0 |
63
- | 0.0001 | 10.0 | 280 | 0.0215 | 1.0 |
64
 
65
 
66
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1567
22
+ - Accuracy: 0.96
23
 
24
  ## Model description
25
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 0.597 | 1.0 | 28 | 0.1618 | 0.92 |
55
+ | 0.1129 | 2.0 | 56 | 0.7487 | 0.8 |
56
+ | 0.0545 | 3.0 | 84 | 0.0181 | 1.0 |
57
+ | 0.001 | 4.0 | 112 | 0.7661 | 0.84 |
58
+ | 0.0003 | 5.0 | 140 | 0.1578 | 0.96 |
59
+ | 0.0001 | 6.0 | 168 | 0.1282 | 0.96 |
60
+ | 0.0001 | 7.0 | 196 | 0.1429 | 0.96 |
61
+ | 0.0 | 8.0 | 224 | 0.1519 | 0.96 |
62
+ | 0.0 | 9.0 | 252 | 0.1562 | 0.96 |
63
+ | 0.0 | 10.0 | 280 | 0.1567 | 0.96 |
64
 
65
 
66
  ### Framework versions
config.json CHANGED
@@ -1,6 +1,4 @@
1
  {
2
- "_attn_implementation_autoset": true,
3
- "_name_or_path": "../models/test-model-for-rio",
4
  "architectures": [
5
  "ASTForAudioClassification"
6
  ],
@@ -10,16 +8,16 @@
10
  "hidden_dropout_prob": 0.0,
11
  "hidden_size": 768,
12
  "id2label": {
13
- "0": "LABEL_0",
14
- "1": "LABEL_1",
15
- "2": "LABEL_2"
16
  },
17
  "initializer_range": 0.02,
18
  "intermediate_size": 3072,
19
  "label2id": {
20
- "LABEL_0": 0,
21
- "LABEL_1": 1,
22
- "LABEL_2": 2
23
  },
24
  "layer_norm_eps": 1e-12,
25
  "max_length": 1024,
@@ -31,5 +29,6 @@
31
  "problem_type": "single_label_classification",
32
  "qkv_bias": true,
33
  "time_stride": 10,
34
- "transformers_version": "4.46.0"
 
35
  }
 
1
  {
 
 
2
  "architectures": [
3
  "ASTForAudioClassification"
4
  ],
 
8
  "hidden_dropout_prob": 0.0,
9
  "hidden_size": 768,
10
  "id2label": {
11
+ "0": "advert",
12
+ "1": "music",
13
+ "2": "presenter"
14
  },
15
  "initializer_range": 0.02,
16
  "intermediate_size": 3072,
17
  "label2id": {
18
+ "advert": 0,
19
+ "music": 1,
20
+ "presenter": 2
21
  },
22
  "layer_norm_eps": 1e-12,
23
  "max_length": 1024,
 
29
  "problem_type": "single_label_classification",
30
  "qkv_bias": true,
31
  "time_stride": 10,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.51.3"
34
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed926a438610464d7ae766ce52ef7a2d99b44b82de29c80f35e75c35d9d30c13
3
  size 344793116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4420e1d32c74b5087d194f214168b23ad8046aa5917e8a478670ec6b15a06b
3
  size 344793116
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9953610bdbe97bf8e297959234d0c269a47c826c5f349ecab3a0266c1680bea2
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b11da011d0f810d62ba23aefc27900ae699f7f2766dec9303769e11080ffd5c
3
  size 5304