heado commited on
Commit
17c5cc3
·
verified ·
1 Parent(s): 3dcf571

heado/audio

Browse files
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: facebook/wav2vec2-xls-r-300m
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: my_model
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # my_model
18
+
19
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.6403
22
+ - Accuracy: 0.0672
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0001
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 16
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 10
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
57
+ | 2.6453 | 1.0 | 30 | 2.6434 | 0.0336 |
58
+ | 2.6503 | 2.0 | 60 | 2.6434 | 0.0840 |
59
+ | 2.649 | 3.0 | 90 | 2.6506 | 0.0588 |
60
+ | 2.6433 | 4.0 | 120 | 2.6488 | 0.0924 |
61
+ | 2.6252 | 5.0 | 150 | 2.6514 | 0.1008 |
62
+ | 2.6123 | 6.0 | 180 | 2.6542 | 0.0840 |
63
+ | 2.6167 | 7.0 | 210 | 2.6520 | 0.0840 |
64
+ | 2.6051 | 8.0 | 240 | 2.6461 | 0.0588 |
65
+ | 2.5975 | 9.0 | 270 | 2.6402 | 0.1345 |
66
+ | 2.5809 | 10.0 | 300 | 2.6403 | 0.0672 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.56.1
72
+ - Pytorch 2.8.0+cu126
73
+ - Datasets 4.0.0
74
+ - Tokenizers 0.22.0
config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "adapter_attn_dim": null,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "dtype": "float32",
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": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "id2label": {
61
+ "0": "abroad",
62
+ "1": "address",
63
+ "10": "high_value_payment",
64
+ "11": "joint_account",
65
+ "12": "latest_transactions",
66
+ "13": "pay_bill",
67
+ "2": "app_error",
68
+ "3": "atm_limit",
69
+ "4": "balance",
70
+ "5": "business_loan",
71
+ "6": "card_issues",
72
+ "7": "cash_deposit",
73
+ "8": "direct_debit",
74
+ "9": "freeze"
75
+ },
76
+ "initializer_range": 0.02,
77
+ "intermediate_size": 4096,
78
+ "label2id": {
79
+ "abroad": "0",
80
+ "address": "1",
81
+ "app_error": "2",
82
+ "atm_limit": "3",
83
+ "balance": "4",
84
+ "business_loan": "5",
85
+ "card_issues": "6",
86
+ "cash_deposit": "7",
87
+ "direct_debit": "8",
88
+ "freeze": "9",
89
+ "high_value_payment": "10",
90
+ "joint_account": "11",
91
+ "latest_transactions": "12",
92
+ "pay_bill": "13"
93
+ },
94
+ "layer_norm_eps": 1e-05,
95
+ "layerdrop": 0.1,
96
+ "mask_feature_length": 10,
97
+ "mask_feature_min_masks": 0,
98
+ "mask_feature_prob": 0.0,
99
+ "mask_time_length": 10,
100
+ "mask_time_min_masks": 2,
101
+ "mask_time_prob": 0.075,
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": 0,
114
+ "proj_codevector_dim": 768,
115
+ "tdnn_dilation": [
116
+ 1,
117
+ 2,
118
+ 3,
119
+ 1,
120
+ 1
121
+ ],
122
+ "tdnn_dim": [
123
+ 512,
124
+ 512,
125
+ 512,
126
+ 512,
127
+ 1500
128
+ ],
129
+ "tdnn_kernel": [
130
+ 5,
131
+ 3,
132
+ 3,
133
+ 1,
134
+ 1
135
+ ],
136
+ "transformers_version": "4.56.1",
137
+ "use_weighted_layer_sum": false,
138
+ "vocab_size": 32,
139
+ "xvector_output_dim": 512
140
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212d07978168a0f426223d415210db9ae6f34713fa113f5d5bb3a24dc391e008
3
+ size 1262871640
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,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
runs/Sep18_21-00-11_56be5970f861/events.out.tfevents.1758229217.56be5970f861.9317.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:734951e421f22f75e6201a0f6c8d82324f2719d2e450293636dd7ad7a68bc0d2
3
+ size 88
runs/Sep18_21-06-29_4ed70b94172d/events.out.tfevents.1758229594.4ed70b94172d.1153.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aa82bfc02a829793a768b7b82dbeb2816b192340738c1e6c0cac3716b63a13c
3
+ size 7111
runs/Sep18_21-07-16_4ed70b94172d/events.out.tfevents.1758229637.4ed70b94172d.1153.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c16c779e8fe394bb3bb6093982525fda7163cf6e69222e574d1bff3c1a8729
3
+ size 7109
runs/Sep18_21-07-47_4ed70b94172d/events.out.tfevents.1758229668.4ed70b94172d.1153.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d728e5baa8948da15b96c908f681a35577bb675366e533af54fdc8d41f471df
3
+ size 88
runs/Sep18_21-10-44_577eea9f1c0c/events.out.tfevents.1758229846.577eea9f1c0c.6632.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41db0373459b8e7d60e323c16bc3717adb2fa83fc9311b9aa65412d3ab958a9
3
+ size 7316
runs/Sep18_21-11-22_577eea9f1c0c/events.out.tfevents.1758229883.577eea9f1c0c.6632.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f61a244854d9a3f8929bfe1f70faf16a973f7af1329952180634c650f7ac41c7
3
+ size 88
runs/Sep18_21-11-49_577eea9f1c0c/events.out.tfevents.1758229909.577eea9f1c0c.6632.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb55ab93918ec79e5323161a65ba789eeaccfa98e7007e5f212a591e509935f
3
+ size 88
runs/Sep18_21-12-59_577eea9f1c0c/events.out.tfevents.1758229980.577eea9f1c0c.7887.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ba4a0af8716f43faa9f98f402704fd765b232b051956aa4f3a519ecb5981b1
3
+ size 88
runs/Sep18_21-14-06_577eea9f1c0c/events.out.tfevents.1758230047.577eea9f1c0c.7887.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b52d025995833e6212978914e27917ffb9f4e64b0415d3efb7997b6ec06a5868
3
+ size 88
runs/Sep18_21-15-09_577eea9f1c0c/events.out.tfevents.1758230110.577eea9f1c0c.8575.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9f0853cae3313d6f883d46b644b69f6b4e440f1a4066de7e6504d8ad6ddfb55
3
+ size 88
runs/Sep18_21-17-46_577eea9f1c0c/events.out.tfevents.1758230267.577eea9f1c0c.9322.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d7ee9f4a89c9907c1452f597314da8dfb1360fcd0db5c72f8c7db15f4e99fbb
3
+ size 16951
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7168530a7c0a7f869fc6d929f49e9489370fc2f9dfec5b6f48f994d28de6de1c
3
+ size 5777