dhaselhan commited on
Commit
476f1b4
1 Parent(s): 9a1aa0f

Training in progress, epoch 0

Browse files
Files changed (4) hide show
  1. config.json +103 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +13 -0
  4. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MIT/ast-finetuned-speech-commands-v2",
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": "yes",
13
+ "1": "no",
14
+ "10": "zero",
15
+ "11": "one",
16
+ "12": "two",
17
+ "13": "three",
18
+ "14": "four",
19
+ "15": "five",
20
+ "16": "six",
21
+ "17": "seven",
22
+ "18": "eight",
23
+ "19": "nine",
24
+ "2": "up",
25
+ "20": "bed",
26
+ "21": "bird",
27
+ "22": "cat",
28
+ "23": "dog",
29
+ "24": "happy",
30
+ "25": "house",
31
+ "26": "marvin",
32
+ "27": "sheila",
33
+ "28": "tree",
34
+ "29": "wow",
35
+ "3": "down",
36
+ "30": "backward",
37
+ "31": "forward",
38
+ "32": "follow",
39
+ "33": "learn",
40
+ "34": "visual",
41
+ "35": "_silence_",
42
+ "36": "player2",
43
+ "4": "left",
44
+ "5": "right",
45
+ "6": "on",
46
+ "7": "off",
47
+ "8": "stop",
48
+ "9": "go"
49
+ },
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 3072,
52
+ "label2id": {
53
+ "_silence_": "35",
54
+ "backward": "30",
55
+ "bed": "20",
56
+ "bird": "21",
57
+ "cat": "22",
58
+ "dog": "23",
59
+ "down": "3",
60
+ "eight": "18",
61
+ "five": "15",
62
+ "follow": "32",
63
+ "forward": "31",
64
+ "four": "14",
65
+ "go": "9",
66
+ "happy": "24",
67
+ "house": "25",
68
+ "learn": "33",
69
+ "left": "4",
70
+ "marvin": "26",
71
+ "nine": "19",
72
+ "no": "1",
73
+ "off": "7",
74
+ "on": "6",
75
+ "one": "11",
76
+ "player2": "36",
77
+ "right": "5",
78
+ "seven": "17",
79
+ "sheila": "27",
80
+ "six": "16",
81
+ "stop": "8",
82
+ "three": "13",
83
+ "tree": "28",
84
+ "two": "12",
85
+ "up": "2",
86
+ "visual": "34",
87
+ "wow": "29",
88
+ "yes": "0",
89
+ "zero": "10"
90
+ },
91
+ "layer_norm_eps": 1e-12,
92
+ "max_length": 128,
93
+ "model_type": "audio-spectrogram-transformer",
94
+ "num_attention_heads": 12,
95
+ "num_hidden_layers": 12,
96
+ "num_mel_bins": 128,
97
+ "patch_size": 16,
98
+ "problem_type": "single_label_classification",
99
+ "qkv_bias": true,
100
+ "time_stride": 10,
101
+ "torch_dtype": "float32",
102
+ "transformers_version": "4.38.2"
103
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5117a86708326f89f34f08e5370491b58c3900e141b152eab0ae8a9e331c6ba0
3
+ size 341616804
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": 128,
6
+ "mean": -6.845978,
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": 5.5654526
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:011ae1d0a3ae27b35335f6cf71ad9789305ef30414387a950614314144f80410
3
+ size 4856