Hugging Face's logo

iisking
/
AST-vocal-disorder-classification

Audio Classification
Transformers
Safetensors
audio-spectrogram-transformer
Model card Files
xet
Community
iisking commited on
Commit
a33aa9c
·
verified ·
1 Parent(s): 9381fba

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-570/config.json +39 -0
  2. checkpoint-570/model.safetensors +3 -0
  3. checkpoint-570/optimizer.pt +3 -0
  4. checkpoint-570/preprocessor_config.json +13 -0
  5. checkpoint-570/rng_state.pth +3 -0
  6. checkpoint-570/scheduler.pt +3 -0
  7. checkpoint-570/trainer_state.json +0 -0
  8. checkpoint-570/training_args.bin +3 -0
  9. config.json +39 -0
  10. model.safetensors +3 -0
  11. preprocessor_config.json +13 -0
  12. training_args.bin +3 -0
checkpoint-570/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Paralysis",
13
+ "1": "Atrophy",
14
+ "2": "MTD",
15
+ "3": "Lesion",
16
+ "4": "Normal"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "Atrophy": 1,
22
+ "Lesion": 3,
23
+ "MTD": 2,
24
+ "Normal": 4,
25
+ "Paralysis": 0
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_length": 1024,
29
+ "model_type": "audio-spectrogram-transformer",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "num_mel_bins": 128,
33
+ "patch_size": 16,
34
+ "problem_type": "single_label_classification",
35
+ "qkv_bias": true,
36
+ "time_stride": 10,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.42.0.dev0"
39
+ }
checkpoint-570/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e61b8d6b3e663a7f92eb62c49eac48c956427083ce5615e630700ee6cd04a56
3
+ size 346409340
checkpoint-570/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12cf1b6afb1cc74208b89332355c63cb535b7e563ae67f8e3f9c7208af35fcf7
3
+ size 692930938
checkpoint-570/preprocessor_config.json ADDED
@@ -0,0 +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
+ }
checkpoint-570/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68c0a7bb5c807ad5bc1c4dff28401d8ba88a8d5d80ef889d2be2ca17beb56b13
3
+ size 14244
checkpoint-570/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30562c6e10eb0d3d3ac27a05ed711c3ac35e2dc0d5f70e5760b406056cff515b
3
+ size 1064
checkpoint-570/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-570/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dce76439f94b86a3c2df91fd09bd85d03bbf0a8d8f2fbe4414ce174b913170f
3
+ size 5112
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Paralysis",
13
+ "1": "Atrophy",
14
+ "2": "MTD",
15
+ "3": "Lesion",
16
+ "4": "Normal"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "Atrophy": 1,
22
+ "Lesion": 3,
23
+ "MTD": 2,
24
+ "Normal": 4,
25
+ "Paralysis": 0
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_length": 1024,
29
+ "model_type": "audio-spectrogram-transformer",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "num_mel_bins": 128,
33
+ "patch_size": 16,
34
+ "problem_type": "single_label_classification",
35
+ "qkv_bias": true,
36
+ "time_stride": 10,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.42.0.dev0"
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e61b8d6b3e663a7f92eb62c49eac48c956427083ce5615e630700ee6cd04a56
3
+ size 346409340
preprocessor_config.json ADDED
@@ -0,0 +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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dce76439f94b86a3c2df91fd09bd85d03bbf0a8d8f2fbe4414ce174b913170f
3
+ size 5112