Hugging Face's logo

hamza666
/
Lesson1results

TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files Metrics Community
hamza666 commited on
Commit
d26ac45
•
1 Parent(s): 1e6075b

Model save

Browse files
Files changed (11) hide show
  1. README.md +70 -0
  2. best/config.json +178 -0
  3. best/label2id.pkl +3 -0
  4. best/model.safetensors +3 -0
  5. best/preprocessor_config.json +9 -0
  6. best/training_args.bin +3 -0
  7. config.json +178 -0
  8. model.safetensors +3 -0
  9. preprocessor_config.json +9 -0
  10. runs/Aug07_12-32-02_DESKTOP-SIV78OS/events.out.tfevents.1723015924.DESKTOP-SIV78OS +3 -0
  11. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: facebook/wav2vec2-base
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: Lesson1results
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # Lesson1results
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0935
20
+ - Accuracy: 0.9734
21
+ - F1-score: 0.9731
22
+ - Recall-score: 0.9734
23
+ - Precision-score: 0.9746
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 32
44
+ - eval_batch_size: 64
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 20
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Recall-score | Precision-score |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:------------:|:---------------:|
55
+ | 0.7793 | 1.0 | 556 | 0.7195 | 0.7981 | 0.7642 | 0.7981 | 0.7911 |
56
+ | 1.0073 | 2.0 | 1112 | 0.3774 | 0.9000 | 0.8979 | 0.9000 | 0.9064 |
57
+ | 0.8493 | 3.0 | 1668 | 0.1909 | 0.9456 | 0.9451 | 0.9456 | 0.9512 |
58
+ | 0.353 | 4.0 | 2224 | 0.1337 | 0.9668 | 0.9668 | 0.9668 | 0.9679 |
59
+ | 0.3413 | 5.0 | 2780 | 0.0794 | 0.9819 | 0.9819 | 0.9819 | 0.9823 |
60
+ | 0.0197 | 6.0 | 3336 | 0.0969 | 0.9756 | 0.9757 | 0.9756 | 0.9763 |
61
+ | 0.1234 | 7.0 | 3892 | 0.0873 | 0.9781 | 0.9782 | 0.9781 | 0.9793 |
62
+ | 0.0222 | 8.0 | 4448 | 0.0935 | 0.9734 | 0.9731 | 0.9734 | 0.9746 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - Transformers 4.42.3
68
+ - Pytorch 2.3.1+cu121
69
+ - Datasets 2.20.0
70
+ - Tokenizers 0.19.1
best/config.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "\u0636",
61
+ "1": "\u062d",
62
+ "10": "\u062e",
63
+ "11": "\u064a",
64
+ "12": "\u0641",
65
+ "13": "\u0643",
66
+ "14": "\u062f",
67
+ "15": "\u0644",
68
+ "16": "\u0648",
69
+ "17": "\u0635",
70
+ "18": "\u0633",
71
+ "19": "\u0638",
72
+ "2": "\u0647",
73
+ "20": "\u062a",
74
+ "21": "\u0642",
75
+ "22": "\u0628",
76
+ "23": "\u062c",
77
+ "24": "\u0630",
78
+ "25": "\u0627",
79
+ "26": "\u063a",
80
+ "27": "\u0645",
81
+ "3": "\u062b",
82
+ "4": "\u0637",
83
+ "5": "\u0639",
84
+ "6": "\u0634",
85
+ "7": "\u0632",
86
+ "8": "\u0646",
87
+ "9": "\u0631"
88
+ },
89
+ "initializer_range": 0.02,
90
+ "intermediate_size": 3072,
91
+ "label2id": {
92
+ "\u0627": "25",
93
+ "\u0628": "22",
94
+ "\u062a": "20",
95
+ "\u062b": "3",
96
+ "\u062c": "23",
97
+ "\u062d": "1",
98
+ "\u062e": "10",
99
+ "\u062f": "14",
100
+ "\u0630": "24",
101
+ "\u0631": "9",
102
+ "\u0632": "7",
103
+ "\u0633": "18",
104
+ "\u0634": "6",
105
+ "\u0635": "17",
106
+ "\u0636": "0",
107
+ "\u0637": "4",
108
+ "\u0638": "19",
109
+ "\u0639": "5",
110
+ "\u063a": "26",
111
+ "\u0641": "12",
112
+ "\u0642": "21",
113
+ "\u0643": "13",
114
+ "\u0644": "15",
115
+ "\u0645": "27",
116
+ "\u0646": "8",
117
+ "\u0647": "2",
118
+ "\u0648": "16",
119
+ "\u064a": "11"
120
+ },
121
+ "layer_norm_eps": 1e-05,
122
+ "layerdrop": 0.0,
123
+ "mask_channel_length": 10,
124
+ "mask_channel_min_space": 1,
125
+ "mask_channel_other": 0.0,
126
+ "mask_channel_prob": 0.0,
127
+ "mask_channel_selection": "static",
128
+ "mask_feature_length": 10,
129
+ "mask_feature_min_masks": 0,
130
+ "mask_feature_prob": 0.0,
131
+ "mask_time_length": 10,
132
+ "mask_time_min_masks": 2,
133
+ "mask_time_min_space": 1,
134
+ "mask_time_other": 0.0,
135
+ "mask_time_prob": 0.05,
136
+ "mask_time_selection": "static",
137
+ "model_type": "wav2vec2",
138
+ "no_mask_channel_overlap": false,
139
+ "no_mask_time_overlap": false,
140
+ "num_adapter_layers": 3,
141
+ "num_attention_heads": 12,
142
+ "num_codevector_groups": 2,
143
+ "num_codevectors_per_group": 320,
144
+ "num_conv_pos_embedding_groups": 16,
145
+ "num_conv_pos_embeddings": 128,
146
+ "num_feat_extract_layers": 7,
147
+ "num_hidden_layers": 12,
148
+ "num_negatives": 100,
149
+ "output_hidden_size": 768,
150
+ "pad_token_id": 0,
151
+ "proj_codevector_dim": 256,
152
+ "tdnn_dilation": [
153
+ 1,
154
+ 2,
155
+ 3,
156
+ 1,
157
+ 1
158
+ ],
159
+ "tdnn_dim": [
160
+ 512,
161
+ 512,
162
+ 512,
163
+ 512,
164
+ 1500
165
+ ],
166
+ "tdnn_kernel": [
167
+ 5,
168
+ 3,
169
+ 3,
170
+ 1,
171
+ 1
172
+ ],
173
+ "torch_dtype": "float32",
174
+ "transformers_version": "4.42.3",
175
+ "use_weighted_layer_sum": false,
176
+ "vocab_size": 32,
177
+ "xvector_output_dim": 512
178
+ }
best/label2id.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af9e94b3cee92aa07f976dc1be324ce458672aa4e72ff285b83b12b1a5d14168
3
+ size 286
best/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:653c0c059d4318ec6558e6f65a04363ccd84ddc86a85df6f732d2817102f5648
3
+ size 378329104
best/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
+ }
best/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49aa8221768899ea715efcaa47f92af85392e92dd98669211f6a7f5858b1a661
3
+ size 5112
config.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "\u0636",
61
+ "1": "\u062d",
62
+ "10": "\u062e",
63
+ "11": "\u064a",
64
+ "12": "\u0641",
65
+ "13": "\u0643",
66
+ "14": "\u062f",
67
+ "15": "\u0644",
68
+ "16": "\u0648",
69
+ "17": "\u0635",
70
+ "18": "\u0633",
71
+ "19": "\u0638",
72
+ "2": "\u0647",
73
+ "20": "\u062a",
74
+ "21": "\u0642",
75
+ "22": "\u0628",
76
+ "23": "\u062c",
77
+ "24": "\u0630",
78
+ "25": "\u0627",
79
+ "26": "\u063a",
80
+ "27": "\u0645",
81
+ "3": "\u062b",
82
+ "4": "\u0637",
83
+ "5": "\u0639",
84
+ "6": "\u0634",
85
+ "7": "\u0632",
86
+ "8": "\u0646",
87
+ "9": "\u0631"
88
+ },
89
+ "initializer_range": 0.02,
90
+ "intermediate_size": 3072,
91
+ "label2id": {
92
+ "\u0627": "25",
93
+ "\u0628": "22",
94
+ "\u062a": "20",
95
+ "\u062b": "3",
96
+ "\u062c": "23",
97
+ "\u062d": "1",
98
+ "\u062e": "10",
99
+ "\u062f": "14",
100
+ "\u0630": "24",
101
+ "\u0631": "9",
102
+ "\u0632": "7",
103
+ "\u0633": "18",
104
+ "\u0634": "6",
105
+ "\u0635": "17",
106
+ "\u0636": "0",
107
+ "\u0637": "4",
108
+ "\u0638": "19",
109
+ "\u0639": "5",
110
+ "\u063a": "26",
111
+ "\u0641": "12",
112
+ "\u0642": "21",
113
+ "\u0643": "13",
114
+ "\u0644": "15",
115
+ "\u0645": "27",
116
+ "\u0646": "8",
117
+ "\u0647": "2",
118
+ "\u0648": "16",
119
+ "\u064a": "11"
120
+ },
121
+ "layer_norm_eps": 1e-05,
122
+ "layerdrop": 0.0,
123
+ "mask_channel_length": 10,
124
+ "mask_channel_min_space": 1,
125
+ "mask_channel_other": 0.0,
126
+ "mask_channel_prob": 0.0,
127
+ "mask_channel_selection": "static",
128
+ "mask_feature_length": 10,
129
+ "mask_feature_min_masks": 0,
130
+ "mask_feature_prob": 0.0,
131
+ "mask_time_length": 10,
132
+ "mask_time_min_masks": 2,
133
+ "mask_time_min_space": 1,
134
+ "mask_time_other": 0.0,
135
+ "mask_time_prob": 0.05,
136
+ "mask_time_selection": "static",
137
+ "model_type": "wav2vec2",
138
+ "no_mask_channel_overlap": false,
139
+ "no_mask_time_overlap": false,
140
+ "num_adapter_layers": 3,
141
+ "num_attention_heads": 12,
142
+ "num_codevector_groups": 2,
143
+ "num_codevectors_per_group": 320,
144
+ "num_conv_pos_embedding_groups": 16,
145
+ "num_conv_pos_embeddings": 128,
146
+ "num_feat_extract_layers": 7,
147
+ "num_hidden_layers": 12,
148
+ "num_negatives": 100,
149
+ "output_hidden_size": 768,
150
+ "pad_token_id": 0,
151
+ "proj_codevector_dim": 256,
152
+ "tdnn_dilation": [
153
+ 1,
154
+ 2,
155
+ 3,
156
+ 1,
157
+ 1
158
+ ],
159
+ "tdnn_dim": [
160
+ 512,
161
+ 512,
162
+ 512,
163
+ 512,
164
+ 1500
165
+ ],
166
+ "tdnn_kernel": [
167
+ 5,
168
+ 3,
169
+ 3,
170
+ 1,
171
+ 1
172
+ ],
173
+ "torch_dtype": "float32",
174
+ "transformers_version": "4.42.3",
175
+ "use_weighted_layer_sum": false,
176
+ "vocab_size": 32,
177
+ "xvector_output_dim": 512
178
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:653c0c059d4318ec6558e6f65a04363ccd84ddc86a85df6f732d2817102f5648
3
+ size 378329104
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
+ }
runs/Aug07_12-32-02_DESKTOP-SIV78OS/events.out.tfevents.1723015924.DESKTOP-SIV78OS ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5badfba9759db21bfaf1579045fe3454d4806b1191a1d3244c056c651b6e7eb
3
+ size 949923
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49aa8221768899ea715efcaa47f92af85392e92dd98669211f6a7f5858b1a661
3
+ size 5112