Adding ONNX file of this model
#8
by
boridori
- opened
- onnx/config.json +138 -0
- onnx/model.onnx +3 -0
- onnx/preprocessor_config.json +9 -0
onnx/config.json
ADDED
|
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition",
|
| 3 |
+
"activation_dropout": 0.05,
|
| 4 |
+
"adapter_attn_dim": null,
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2ForSequenceClassification"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 256,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": true,
|
| 18 |
+
"conv_dim": [
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"conv_kernel": [
|
| 28 |
+
10,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
3,
|
| 33 |
+
2,
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"conv_stride": [
|
| 37 |
+
5,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
2
|
| 44 |
+
],
|
| 45 |
+
"ctc_loss_reduction": "mean",
|
| 46 |
+
"ctc_zero_infinity": true,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": true,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_dropout": 0.0,
|
| 52 |
+
"feat_extract_norm": "layer",
|
| 53 |
+
"feat_proj_dropout": 0.05,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.0,
|
| 56 |
+
"finetuning_task": "wav2vec2_clf",
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.05,
|
| 59 |
+
"hidden_size": 1024,
|
| 60 |
+
"id2label": {
|
| 61 |
+
"0": "angry",
|
| 62 |
+
"1": "calm",
|
| 63 |
+
"2": "disgust",
|
| 64 |
+
"3": "fearful",
|
| 65 |
+
"4": "happy",
|
| 66 |
+
"5": "neutral",
|
| 67 |
+
"6": "sad",
|
| 68 |
+
"7": "surprised"
|
| 69 |
+
},
|
| 70 |
+
"initializer_range": 0.02,
|
| 71 |
+
"intermediate_size": 4096,
|
| 72 |
+
"label2id": {
|
| 73 |
+
"angry": 0,
|
| 74 |
+
"calm": 1,
|
| 75 |
+
"disgust": 2,
|
| 76 |
+
"fearful": 3,
|
| 77 |
+
"happy": 4,
|
| 78 |
+
"neutral": 5,
|
| 79 |
+
"sad": 6,
|
| 80 |
+
"surprised": 7
|
| 81 |
+
},
|
| 82 |
+
"layer_norm_eps": 1e-05,
|
| 83 |
+
"layerdrop": 0.05,
|
| 84 |
+
"mask_channel_length": 10,
|
| 85 |
+
"mask_channel_min_space": 1,
|
| 86 |
+
"mask_channel_other": 0.0,
|
| 87 |
+
"mask_channel_prob": 0.0,
|
| 88 |
+
"mask_channel_selection": "static",
|
| 89 |
+
"mask_feature_length": 10,
|
| 90 |
+
"mask_feature_min_masks": 0,
|
| 91 |
+
"mask_feature_prob": 0.0,
|
| 92 |
+
"mask_time_length": 10,
|
| 93 |
+
"mask_time_min_masks": 2,
|
| 94 |
+
"mask_time_min_space": 1,
|
| 95 |
+
"mask_time_other": 0.0,
|
| 96 |
+
"mask_time_prob": 0.05,
|
| 97 |
+
"mask_time_selection": "static",
|
| 98 |
+
"model_type": "wav2vec2",
|
| 99 |
+
"num_adapter_layers": 3,
|
| 100 |
+
"num_attention_heads": 16,
|
| 101 |
+
"num_codevector_groups": 2,
|
| 102 |
+
"num_codevectors_per_group": 320,
|
| 103 |
+
"num_conv_pos_embedding_groups": 16,
|
| 104 |
+
"num_conv_pos_embeddings": 128,
|
| 105 |
+
"num_feat_extract_layers": 7,
|
| 106 |
+
"num_hidden_layers": 24,
|
| 107 |
+
"num_negatives": 100,
|
| 108 |
+
"output_hidden_size": 1024,
|
| 109 |
+
"pad_token_id": 0,
|
| 110 |
+
"pooling_mode": "mean",
|
| 111 |
+
"problem_type": "single_label_classification",
|
| 112 |
+
"proj_codevector_dim": 256,
|
| 113 |
+
"tdnn_dilation": [
|
| 114 |
+
1,
|
| 115 |
+
2,
|
| 116 |
+
3,
|
| 117 |
+
1,
|
| 118 |
+
1
|
| 119 |
+
],
|
| 120 |
+
"tdnn_dim": [
|
| 121 |
+
512,
|
| 122 |
+
512,
|
| 123 |
+
512,
|
| 124 |
+
512,
|
| 125 |
+
1500
|
| 126 |
+
],
|
| 127 |
+
"tdnn_kernel": [
|
| 128 |
+
5,
|
| 129 |
+
3,
|
| 130 |
+
3,
|
| 131 |
+
1,
|
| 132 |
+
1
|
| 133 |
+
],
|
| 134 |
+
"transformers_version": "4.37.2",
|
| 135 |
+
"use_weighted_layer_sum": false,
|
| 136 |
+
"vocab_size": 33,
|
| 137 |
+
"xvector_output_dim": 512
|
| 138 |
+
}
|
onnx/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e6c875f2bb1fe16d29005d6f57dda37e64e27401724353ff0d0c6b1f22d0a23
|
| 3 |
+
size 1263409099
|
onnx/preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"return_attention_mask": true,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|