Training in progress, epoch 1
Browse files
config.json
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "A",
|
13 |
+
"1": "B",
|
14 |
+
"10": "K",
|
15 |
+
"11": "L",
|
16 |
+
"12": "M",
|
17 |
+
"13": "N",
|
18 |
+
"14": "O",
|
19 |
+
"15": "P",
|
20 |
+
"16": "Q",
|
21 |
+
"17": "R",
|
22 |
+
"18": "S",
|
23 |
+
"19": "T",
|
24 |
+
"2": "C",
|
25 |
+
"20": "U",
|
26 |
+
"21": "V",
|
27 |
+
"22": "W",
|
28 |
+
"23": "X",
|
29 |
+
"24": "Y",
|
30 |
+
"25": "Z",
|
31 |
+
"26": "_silence_",
|
32 |
+
"27": "_unknown_",
|
33 |
+
"3": "D",
|
34 |
+
"4": "E",
|
35 |
+
"5": "F",
|
36 |
+
"6": "G",
|
37 |
+
"7": "H",
|
38 |
+
"8": "I",
|
39 |
+
"9": "J"
|
40 |
+
},
|
41 |
+
"initializer_range": 0.02,
|
42 |
+
"intermediate_size": 3072,
|
43 |
+
"label2id": {
|
44 |
+
"A": "0",
|
45 |
+
"B": "1",
|
46 |
+
"C": "2",
|
47 |
+
"D": "3",
|
48 |
+
"E": "4",
|
49 |
+
"F": "5",
|
50 |
+
"G": "6",
|
51 |
+
"H": "7",
|
52 |
+
"I": "8",
|
53 |
+
"J": "9",
|
54 |
+
"K": "10",
|
55 |
+
"L": "11",
|
56 |
+
"M": "12",
|
57 |
+
"N": "13",
|
58 |
+
"O": "14",
|
59 |
+
"P": "15",
|
60 |
+
"Q": "16",
|
61 |
+
"R": "17",
|
62 |
+
"S": "18",
|
63 |
+
"T": "19",
|
64 |
+
"U": "20",
|
65 |
+
"V": "21",
|
66 |
+
"W": "22",
|
67 |
+
"X": "23",
|
68 |
+
"Y": "24",
|
69 |
+
"Z": "25",
|
70 |
+
"_silence_": "26",
|
71 |
+
"_unknown_": "27"
|
72 |
+
},
|
73 |
+
"layer_norm_eps": 1e-12,
|
74 |
+
"max_length": 128,
|
75 |
+
"model_type": "audio-spectrogram-transformer",
|
76 |
+
"num_attention_heads": 12,
|
77 |
+
"num_hidden_layers": 12,
|
78 |
+
"num_mel_bins": 128,
|
79 |
+
"patch_size": 16,
|
80 |
+
"problem_type": "single_label_classification",
|
81 |
+
"qkv_bias": true,
|
82 |
+
"time_stride": 10,
|
83 |
+
"torch_dtype": "float32",
|
84 |
+
"transformers_version": "4.47.1"
|
85 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e3a317f0c1044f9d52289655a40930d5d4811a8bdfb36d88b5e39cd13da8fe2
|
3 |
+
size 341589120
|
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 |
+
}
|
runs/May17_09-37-23_ip-10-192-12-85/events.out.tfevents.1747474656.ip-10-192-12-85.1892.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2df1f5c3e5312b9766eb1a096bb84e52eb1989a923c37afe5f78a1051387c399
|
3 |
+
size 10699
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:beff4cefbb74adb5bd8146b1454c537438c8ee83642e336c47ac63e1f95b6ea1
|
3 |
+
size 5368
|