Upload AudioSpectrogramTransformerForSequenceClassification
Browse files- config.json +97 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"AudioSpectrogramTransformerForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.0,
|
| 6 |
+
"frequency_dimension": 128,
|
| 7 |
+
"frequency_stride": 10,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "backward",
|
| 13 |
+
"1": "follow",
|
| 14 |
+
"2": "five",
|
| 15 |
+
"3": "bed",
|
| 16 |
+
"4": "zero",
|
| 17 |
+
"5": "on",
|
| 18 |
+
"6": "learn",
|
| 19 |
+
"7": "two",
|
| 20 |
+
"8": "house",
|
| 21 |
+
"9": "tree",
|
| 22 |
+
"10": "dog",
|
| 23 |
+
"11": "stop",
|
| 24 |
+
"12": "seven",
|
| 25 |
+
"13": "eight",
|
| 26 |
+
"14": "down",
|
| 27 |
+
"15": "six",
|
| 28 |
+
"16": "forward",
|
| 29 |
+
"17": "cat",
|
| 30 |
+
"18": "right",
|
| 31 |
+
"19": "visual",
|
| 32 |
+
"20": "four",
|
| 33 |
+
"21": "wow",
|
| 34 |
+
"22": "no",
|
| 35 |
+
"23": "nine",
|
| 36 |
+
"24": "off",
|
| 37 |
+
"25": "three",
|
| 38 |
+
"26": "left",
|
| 39 |
+
"27": "marvin",
|
| 40 |
+
"28": "yes",
|
| 41 |
+
"29": "up",
|
| 42 |
+
"30": "sheila",
|
| 43 |
+
"31": "happy",
|
| 44 |
+
"32": "bird",
|
| 45 |
+
"33": "go",
|
| 46 |
+
"34": "one"
|
| 47 |
+
},
|
| 48 |
+
"initializer_range": 0.02,
|
| 49 |
+
"intermediate_size": 3072,
|
| 50 |
+
"label2id": {
|
| 51 |
+
"backward": 0,
|
| 52 |
+
"bed": 3,
|
| 53 |
+
"bird": 32,
|
| 54 |
+
"cat": 17,
|
| 55 |
+
"dog": 10,
|
| 56 |
+
"down": 14,
|
| 57 |
+
"eight": 13,
|
| 58 |
+
"five": 2,
|
| 59 |
+
"follow": 1,
|
| 60 |
+
"forward": 16,
|
| 61 |
+
"four": 20,
|
| 62 |
+
"go": 33,
|
| 63 |
+
"happy": 31,
|
| 64 |
+
"house": 8,
|
| 65 |
+
"learn": 6,
|
| 66 |
+
"left": 26,
|
| 67 |
+
"marvin": 27,
|
| 68 |
+
"nine": 23,
|
| 69 |
+
"no": 22,
|
| 70 |
+
"off": 24,
|
| 71 |
+
"on": 5,
|
| 72 |
+
"one": 34,
|
| 73 |
+
"right": 18,
|
| 74 |
+
"seven": 12,
|
| 75 |
+
"sheila": 30,
|
| 76 |
+
"six": 15,
|
| 77 |
+
"stop": 11,
|
| 78 |
+
"three": 25,
|
| 79 |
+
"tree": 9,
|
| 80 |
+
"two": 7,
|
| 81 |
+
"up": 29,
|
| 82 |
+
"visual": 19,
|
| 83 |
+
"wow": 21,
|
| 84 |
+
"yes": 28,
|
| 85 |
+
"zero": 4
|
| 86 |
+
},
|
| 87 |
+
"layer_norm_eps": 1e-12,
|
| 88 |
+
"model_type": "audio-spectrogram-transformer",
|
| 89 |
+
"num_attention_heads": 12,
|
| 90 |
+
"num_hidden_layers": 12,
|
| 91 |
+
"patch_size": 16,
|
| 92 |
+
"qkv_bias": true,
|
| 93 |
+
"time_dimension": 128,
|
| 94 |
+
"time_stride": 10,
|
| 95 |
+
"torch_dtype": "float32",
|
| 96 |
+
"transformers_version": "4.25.0.dev0"
|
| 97 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c6afd3df64ec12837f06a3bfb3fcdcb3311d7de78d5a5e65ca03e035f616770
|
| 3 |
+
size 341651371
|