Hugging Face's logo

Vladimirlv
/
ast-finetuned-audioset-10-10-0.4593-heart-sounds

Audio Classification
Transformers
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
Vladimirlv commited on
Commit
008f257
·
verified ·
1 Parent(s): bcda6b5

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. config.json +35 -35
  2. model.safetensors +1 -1
  3. preprocessor_config.json +13 -13
  4. training_args.bin +2 -2
config.json CHANGED
@@ -1,35 +1,35 @@
1
- {
2
- "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
3
- "architectures": [
4
- "ASTForAudioClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.0,
7
- "frequency_stride": 10,
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.0,
10
- "hidden_size": 768,
11
- "id2label": {
12
- "0": "artifact",
13
- "1": "healthy",
14
- "2": "unhealthy"
15
- },
16
- "initializer_range": 0.02,
17
- "intermediate_size": 3072,
18
- "label2id": {
19
- "artifact": 0,
20
- "healthy": 1,
21
- "unhealthy": 2
22
- },
23
- "layer_norm_eps": 1e-12,
24
- "max_length": 1024,
25
- "model_type": "audio-spectrogram-transformer",
26
- "num_attention_heads": 12,
27
- "num_hidden_layers": 12,
28
- "num_mel_bins": 128,
29
- "patch_size": 16,
30
- "problem_type": "single_label_classification",
31
- "qkv_bias": true,
32
- "time_stride": 10,
33
- "torch_dtype": "float32",
34
- "transformers_version": "4.48.1"
35
- }
 
1
+ {
2
+ "_name_or_path": "checkpoints/linear_probing_checkpoint",
3
+ "architectures": [
4
+ "ASTForAudioClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "frequency_stride": 10,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "artifact",
13
+ "1": "healthy",
14
+ "2": "unhealthy"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "artifact": 0,
20
+ "healthy": 1,
21
+ "unhealthy": 2
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_length": 1024,
25
+ "model_type": "audio-spectrogram-transformer",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "num_mel_bins": 128,
29
+ "patch_size": 16,
30
+ "problem_type": "single_label_classification",
31
+ "qkv_bias": true,
32
+ "time_stride": 10,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.49.0"
35
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6ce20c1e95671a0fd0b59cb5fae2d3188100cb9c81844b709c1af08c9bf4983
3
  size 344793116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02153153f94d0b5eea5f3519c010353b4896d47c4b38594e7f50e2f6b66d6d10
3
  size 344793116
preprocessor_config.json CHANGED
@@ -1,13 +1,13 @@
1
- {
2
- "do_normalize": true,
3
- "feature_extractor_type": "ASTFeatureExtractor",
4
- "feature_size": 1,
5
- "max_length": 1024,
6
- "mean": -4.2677393,
7
- "num_mel_bins": 128,
8
- "padding_side": "right",
9
- "padding_value": 0.0,
10
- "return_attention_mask": false,
11
- "sampling_rate": 16000,
12
- "std": 4.5689974
13
- }
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "ASTFeatureExtractor",
4
+ "feature_size": 1,
5
+ "max_length": 1024,
6
+ "mean": -4.2677393,
7
+ "num_mel_bins": 128,
8
+ "padding_side": "right",
9
+ "padding_value": 0.0,
10
+ "return_attention_mask": false,
11
+ "sampling_rate": 16000,
12
+ "std": 4.5689974
13
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38dc63d6665f6b64fe544f714a0a897f56332942a145d89f800d49a78cadff62
3
- size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc595f152f431a573a2f488fab4bada5a1dd86d3e6870deec97584209d041f04
3
+ size 5051