End of training
Browse files- README.md +85 -0
- config.json +150 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- minds14
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: results
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Audio Classification
|
15 |
+
type: audio-classification
|
16 |
+
dataset:
|
17 |
+
name: minds14
|
18 |
+
type: minds14
|
19 |
+
config: en-US
|
20 |
+
split: train
|
21 |
+
args: en-US
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.09734513274336283
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# results
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 2.6487
|
36 |
+
- Accuracy: 0.0973
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 3e-05
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 32
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 128
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
64 |
+
- num_epochs: 10
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
70 |
+
| No log | 0.8 | 3 | 2.6385 | 0.0619 |
|
71 |
+
| No log | 1.8667 | 7 | 2.6417 | 0.1062 |
|
72 |
+
| No log | 2.9333 | 11 | 2.6460 | 0.0708 |
|
73 |
+
| No log | 4.0 | 15 | 2.6476 | 0.0796 |
|
74 |
+
| No log | 4.8 | 18 | 2.6480 | 0.0796 |
|
75 |
+
| No log | 5.8667 | 22 | 2.6484 | 0.0885 |
|
76 |
+
| No log | 6.9333 | 26 | 2.6488 | 0.0885 |
|
77 |
+
| No log | 8.0 | 30 | 2.6487 | 0.0973 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.41.2
|
83 |
+
- Pytorch 2.2.2
|
84 |
+
- Datasets 2.19.1
|
85 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
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 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 256,
|
15 |
+
"codevector_dim": 256,
|
16 |
+
"contrastive_logits_temperature": 0.1,
|
17 |
+
"conv_bias": false,
|
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": "sum",
|
46 |
+
"ctc_zero_infinity": false,
|
47 |
+
"diversity_loss_weight": 0.1,
|
48 |
+
"do_stable_layer_norm": false,
|
49 |
+
"eos_token_id": 2,
|
50 |
+
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"freeze_feat_extract_train": true,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_size": 768,
|
59 |
+
"id2label": {
|
60 |
+
"0": "abroad",
|
61 |
+
"1": "address",
|
62 |
+
"10": "high_value_payment",
|
63 |
+
"11": "joint_account",
|
64 |
+
"12": "latest_transactions",
|
65 |
+
"13": "pay_bill",
|
66 |
+
"2": "app_error",
|
67 |
+
"3": "atm_limit",
|
68 |
+
"4": "balance",
|
69 |
+
"5": "business_loan",
|
70 |
+
"6": "card_issues",
|
71 |
+
"7": "cash_deposit",
|
72 |
+
"8": "direct_debit",
|
73 |
+
"9": "freeze"
|
74 |
+
},
|
75 |
+
"initializer_range": 0.02,
|
76 |
+
"intermediate_size": 3072,
|
77 |
+
"label2id": {
|
78 |
+
"abroad": "0",
|
79 |
+
"address": "1",
|
80 |
+
"app_error": "2",
|
81 |
+
"atm_limit": "3",
|
82 |
+
"balance": "4",
|
83 |
+
"business_loan": "5",
|
84 |
+
"card_issues": "6",
|
85 |
+
"cash_deposit": "7",
|
86 |
+
"direct_debit": "8",
|
87 |
+
"freeze": "9",
|
88 |
+
"high_value_payment": "10",
|
89 |
+
"joint_account": "11",
|
90 |
+
"latest_transactions": "12",
|
91 |
+
"pay_bill": "13"
|
92 |
+
},
|
93 |
+
"layer_norm_eps": 1e-05,
|
94 |
+
"layerdrop": 0.0,
|
95 |
+
"mask_channel_length": 10,
|
96 |
+
"mask_channel_min_space": 1,
|
97 |
+
"mask_channel_other": 0.0,
|
98 |
+
"mask_channel_prob": 0.0,
|
99 |
+
"mask_channel_selection": "static",
|
100 |
+
"mask_feature_length": 10,
|
101 |
+
"mask_feature_min_masks": 0,
|
102 |
+
"mask_feature_prob": 0.0,
|
103 |
+
"mask_time_length": 10,
|
104 |
+
"mask_time_min_masks": 2,
|
105 |
+
"mask_time_min_space": 1,
|
106 |
+
"mask_time_other": 0.0,
|
107 |
+
"mask_time_prob": 0.05,
|
108 |
+
"mask_time_selection": "static",
|
109 |
+
"model_type": "wav2vec2",
|
110 |
+
"no_mask_channel_overlap": false,
|
111 |
+
"no_mask_time_overlap": false,
|
112 |
+
"num_adapter_layers": 3,
|
113 |
+
"num_attention_heads": 12,
|
114 |
+
"num_codevector_groups": 2,
|
115 |
+
"num_codevectors_per_group": 320,
|
116 |
+
"num_conv_pos_embedding_groups": 16,
|
117 |
+
"num_conv_pos_embeddings": 128,
|
118 |
+
"num_feat_extract_layers": 7,
|
119 |
+
"num_hidden_layers": 12,
|
120 |
+
"num_negatives": 100,
|
121 |
+
"output_hidden_size": 768,
|
122 |
+
"pad_token_id": 0,
|
123 |
+
"proj_codevector_dim": 256,
|
124 |
+
"tdnn_dilation": [
|
125 |
+
1,
|
126 |
+
2,
|
127 |
+
3,
|
128 |
+
1,
|
129 |
+
1
|
130 |
+
],
|
131 |
+
"tdnn_dim": [
|
132 |
+
512,
|
133 |
+
512,
|
134 |
+
512,
|
135 |
+
512,
|
136 |
+
1500
|
137 |
+
],
|
138 |
+
"tdnn_kernel": [
|
139 |
+
5,
|
140 |
+
3,
|
141 |
+
3,
|
142 |
+
1,
|
143 |
+
1
|
144 |
+
],
|
145 |
+
"torch_dtype": "float32",
|
146 |
+
"transformers_version": "4.41.2",
|
147 |
+
"use_weighted_layer_sum": false,
|
148 |
+
"vocab_size": 32,
|
149 |
+
"xvector_output_dim": 512
|
150 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39ddbbbdff834b24b4d0ea09b256e8ccd6d97a5c0341dab256ad0066e1ca222f
|
3 |
+
size 378314704
|
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": false,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36ac8f753957da0cc4cd93e833b9668a77c2d46f7c92edb3ab3bcf7af912d3d6
|
3 |
+
size 5048
|