Upload folder using huggingface_hub
Browse files- ast-emotion.config +42 -0
- ast-emotion.feature +13 -0
- ast-emotion.onnx +3 -0
- ast-emotion.processor +13 -0
- ast-emotion.tokens +0 -0
- ast-emotion.yaml +15 -0
ast-emotion.config
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
ASTConfig {
|
| 2 |
+
"_name_or_path": "abletobetable/ast-emotion",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ASTForAudioClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"frequency_stride": 10,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "anger",
|
| 13 |
+
"1": "disgust",
|
| 14 |
+
"2": "enthusiasm",
|
| 15 |
+
"3": "fear",
|
| 16 |
+
"4": "happiness",
|
| 17 |
+
"5": "neutral",
|
| 18 |
+
"6": "sadness"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"anger": 0,
|
| 24 |
+
"disgust": 1,
|
| 25 |
+
"enthusiasm": 2,
|
| 26 |
+
"fear": 3,
|
| 27 |
+
"happiness": 4,
|
| 28 |
+
"neutral": 5,
|
| 29 |
+
"sadness": 6
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-12,
|
| 32 |
+
"max_length": 1024,
|
| 33 |
+
"model_type": "audio-spectrogram-transformer",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_hidden_layers": 12,
|
| 36 |
+
"num_mel_bins": 128,
|
| 37 |
+
"patch_size": 16,
|
| 38 |
+
"qkv_bias": true,
|
| 39 |
+
"time_stride": 10,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.40.2"
|
| 42 |
+
}
|
ast-emotion.feature
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
ASTFeatureExtractor {
|
| 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 |
+
}
|
ast-emotion.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51f402d0aab41348f864d10bd2ea420df39f81a5e3371d2c96f702a3569ef51e
|
| 3 |
+
size 345154748
|
ast-emotion.processor
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
ASTFeatureExtractor {
|
| 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 |
+
}
|
ast-emotion.tokens
ADDED
|
File without changes
|
ast-emotion.yaml
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
feature_extractor: ASTFeatureExtractor
|
| 2 |
+
labels:
|
| 3 |
+
0: anger
|
| 4 |
+
1: disgust
|
| 5 |
+
2: enthusiasm
|
| 6 |
+
3: fear
|
| 7 |
+
4: happiness
|
| 8 |
+
5: neutral
|
| 9 |
+
6: sadness
|
| 10 |
+
model: ASTForAudioClassification
|
| 11 |
+
sampling_rate: 16000
|
| 12 |
+
shape:
|
| 13 |
+
- 1
|
| 14 |
+
- 1024
|
| 15 |
+
- 128
|