Hugging Face's logo

wa976
/
ast_18-finetuned-ICBHI

Audio Classification
Transformers
PyTorch
TensorBoard
audio-spectrogram-transformer
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
wa976 commited on
Commit
bc8c0e3
•
1 Parent(s): 77b57d8

Training in progress, epoch 0

Browse files
Files changed (6) hide show
  1. config.json +6 -6
  2. pytorch_model.bin +2 -2
  3. runs/May19_13-37-19_1a5e2ea8ac5c/events.out.tfevents.1684503450.1a5e2ea8ac5c.6379.11 +2 -2
  4. runs/May19_14-01-42_1a5e2ea8ac5c/1684504920.184949/events.out.tfevents.1684504920.1a5e2ea8ac5c.175185.1 +3 -0
  5. runs/May19_14-01-42_1a5e2ea8ac5c/events.out.tfevents.1684504920.1a5e2ea8ac5c.175185.0 +3 -0
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "Ericwang/tiny-random-ast",
3
  "architectures": [
4
  "ASTForAudioClassification"
5
  ],
@@ -7,7 +7,7 @@
7
  "frequency_stride": 10,
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.0,
10
- "hidden_size": 32,
11
  "id2label": {
12
  "0": "both",
13
  "1": "crackles",
@@ -15,7 +15,7 @@
15
  "3": "weezels"
16
  },
17
  "initializer_range": 0.02,
18
- "intermediate_size": 37,
19
  "label2id": {
20
  "both": 0,
21
  "crackles": 1,
@@ -25,10 +25,10 @@
25
  "layer_norm_eps": 1e-12,
26
  "max_length": 1024,
27
  "model_type": "audio-spectrogram-transformer",
28
- "num_attention_heads": 4,
29
- "num_hidden_layers": 5,
30
  "num_mel_bins": 128,
31
- "patch_size": 1,
32
  "problem_type": "single_label_classification",
33
  "qkv_bias": true,
34
  "time_stride": 10,
 
1
  {
2
+ "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
3
  "architectures": [
4
  "ASTForAudioClassification"
5
  ],
 
7
  "frequency_stride": 10,
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
  "id2label": {
12
  "0": "both",
13
  "1": "crackles",
 
15
  "3": "weezels"
16
  },
17
  "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
  "label2id": {
20
  "both": 0,
21
  "crackles": 1,
 
25
  "layer_norm_eps": 1e-12,
26
  "max_length": 1024,
27
  "model_type": "audio-spectrogram-transformer",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
  "num_mel_bins": 128,
31
+ "patch_size": 16,
32
  "problem_type": "single_label_classification",
33
  "qkv_bias": true,
34
  "time_stride": 10,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3a22fa73a7cfd67a7728e23c43e46f8c1d5457bcdb23927da4672b4d5effa28
3
- size 341442
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d0f40ffd7040fe3c27932661e4bdb468a3940fe6510a2e4cdbd49ca23638ca7
3
+ size 344841593
runs/May19_13-37-19_1a5e2ea8ac5c/events.out.tfevents.1684503450.1a5e2ea8ac5c.6379.11 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94ca288af28efd66259d30c0a6442ce17793fee1d97210121dd6937c3a58b5e2
3
- size 13095
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f478153cae11229d1995cec02306fb38905e68dc8a32619bd61097bde607bf28
3
+ size 14665
runs/May19_14-01-42_1a5e2ea8ac5c/1684504920.184949/events.out.tfevents.1684504920.1a5e2ea8ac5c.175185.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a402fdcefdc2034ac51736aed6419c72c675e497ab0e5c0b7ad35a8cde900091
3
+ size 5932
runs/May19_14-01-42_1a5e2ea8ac5c/events.out.tfevents.1684504920.1a5e2ea8ac5c.175185.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda087efaefdde58ff77731570c9300303ad0899f0330e9c81c9e0e2c304ad72
3
+ size 5136
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90f686045332233df8baf0810e4d27975f9d5cfc0ecb31cf474ac144b974a107
3
  size 3899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e13127434174f46810089a0d3486ef951fdc608e9c56d049aab3c642b792746c
3
  size 3899