Training in progress, epoch 1
Browse files- config.json +142 -0
- model.safetensors +3 -0
- preprocessor_config.json +10 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru",
|
3 |
+
"activation_dropout": 0.0,
|
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 |
+
"auto_map": {
|
14 |
+
"AutoModelForAudioClassification": "KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru--emotion_model.Wav2Vec2ForSpeechClassification"
|
15 |
+
},
|
16 |
+
"bos_token_id": 1,
|
17 |
+
"classifier_proj_size": 256,
|
18 |
+
"codevector_dim": 256,
|
19 |
+
"contrastive_logits_temperature": 0.1,
|
20 |
+
"conv_bias": true,
|
21 |
+
"conv_dim": [
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512,
|
25 |
+
512,
|
26 |
+
512,
|
27 |
+
512,
|
28 |
+
512
|
29 |
+
],
|
30 |
+
"conv_kernel": [
|
31 |
+
10,
|
32 |
+
3,
|
33 |
+
3,
|
34 |
+
3,
|
35 |
+
3,
|
36 |
+
2,
|
37 |
+
2
|
38 |
+
],
|
39 |
+
"conv_stride": [
|
40 |
+
5,
|
41 |
+
2,
|
42 |
+
2,
|
43 |
+
2,
|
44 |
+
2,
|
45 |
+
2,
|
46 |
+
2
|
47 |
+
],
|
48 |
+
"ctc_loss_reduction": "mean",
|
49 |
+
"ctc_zero_infinity": true,
|
50 |
+
"custom_pipelines": {
|
51 |
+
"audio-classification": {
|
52 |
+
"impl": "emotion_recognition_pipeline.SpeechEmotionRecognitionPipeline",
|
53 |
+
"pt": [
|
54 |
+
"AutoModelForAudioClassification"
|
55 |
+
],
|
56 |
+
"tf": []
|
57 |
+
}
|
58 |
+
},
|
59 |
+
"diversity_loss_weight": 0.1,
|
60 |
+
"do_stable_layer_norm": true,
|
61 |
+
"eos_token_id": 2,
|
62 |
+
"feat_extract_activation": "gelu",
|
63 |
+
"feat_extract_dropout": 0.0,
|
64 |
+
"feat_extract_norm": "layer",
|
65 |
+
"feat_proj_dropout": 0.0,
|
66 |
+
"feat_quantizer_dropout": 0.0,
|
67 |
+
"final_dropout": 0.0,
|
68 |
+
"finetuning_task": "wav2vec2_emotion_ru",
|
69 |
+
"hidden_act": "gelu",
|
70 |
+
"hidden_dropout": 0.1,
|
71 |
+
"hidden_size": 1024,
|
72 |
+
"id2label": {
|
73 |
+
"0": "pingpong",
|
74 |
+
"1": "caughing",
|
75 |
+
"2": "clapping",
|
76 |
+
"3": "silence"
|
77 |
+
},
|
78 |
+
"initializer_range": 0.02,
|
79 |
+
"intermediate_size": 4096,
|
80 |
+
"label2id": {
|
81 |
+
"caughing": "1",
|
82 |
+
"clapping": "2",
|
83 |
+
"pingpong": "0",
|
84 |
+
"silence": "3"
|
85 |
+
},
|
86 |
+
"layer_norm_eps": 1e-05,
|
87 |
+
"layerdrop": 0.1,
|
88 |
+
"mask_channel_length": 10,
|
89 |
+
"mask_channel_min_space": 1,
|
90 |
+
"mask_channel_other": 0.0,
|
91 |
+
"mask_channel_prob": 0.0,
|
92 |
+
"mask_channel_selection": "static",
|
93 |
+
"mask_feature_length": 10,
|
94 |
+
"mask_feature_min_masks": 0,
|
95 |
+
"mask_feature_prob": 0.0,
|
96 |
+
"mask_time_length": 10,
|
97 |
+
"mask_time_min_masks": 2,
|
98 |
+
"mask_time_min_space": 1,
|
99 |
+
"mask_time_other": 0.0,
|
100 |
+
"mask_time_prob": 0.05,
|
101 |
+
"mask_time_selection": "static",
|
102 |
+
"model_type": "wav2vec2",
|
103 |
+
"num_adapter_layers": 3,
|
104 |
+
"num_attention_heads": 16,
|
105 |
+
"num_codevector_groups": 2,
|
106 |
+
"num_codevectors_per_group": 320,
|
107 |
+
"num_conv_pos_embedding_groups": 16,
|
108 |
+
"num_conv_pos_embeddings": 128,
|
109 |
+
"num_feat_extract_layers": 7,
|
110 |
+
"num_hidden_layers": 24,
|
111 |
+
"num_negatives": 100,
|
112 |
+
"output_hidden_size": 1024,
|
113 |
+
"pad_token_id": 54,
|
114 |
+
"problem_type": "single_label_classification",
|
115 |
+
"proj_codevector_dim": 256,
|
116 |
+
"tdnn_dilation": [
|
117 |
+
1,
|
118 |
+
2,
|
119 |
+
3,
|
120 |
+
1,
|
121 |
+
1
|
122 |
+
],
|
123 |
+
"tdnn_dim": [
|
124 |
+
512,
|
125 |
+
512,
|
126 |
+
512,
|
127 |
+
512,
|
128 |
+
1500
|
129 |
+
],
|
130 |
+
"tdnn_kernel": [
|
131 |
+
5,
|
132 |
+
3,
|
133 |
+
3,
|
134 |
+
1,
|
135 |
+
1
|
136 |
+
],
|
137 |
+
"torch_dtype": "float32",
|
138 |
+
"transformers_version": "4.37.0.dev0",
|
139 |
+
"use_weighted_layer_sum": false,
|
140 |
+
"vocab_size": 55,
|
141 |
+
"xvector_output_dim": 512
|
142 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:738b4589f95e3c919a7f25550c06cc38fa66d29fe57ffb8e4e85d382b3bf2d2c
|
3 |
+
size 1262861360
|
preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0,
|
7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44eb768b40a3cfa5eb66e81bebf60014a2080e61cb362723c45dabb6fda930e0
|
3 |
+
size 4792
|