Hugging Face's logo

mageec
/
wav2vec2-attempt2

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mageec commited on
Commit
1695ab4
·
verified ·
1 Parent(s): fc53afe

wav2vec2-attempt2

Browse files
Files changed (20) hide show
  1. README.md +70 -0
  2. config.json +168 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. runs/Apr30_02-41-40_ip-10-0-2-211/events.out.tfevents.1714444902.ip-10-0-2-211.4674.0 +3 -0
  6. runs/Apr30_02-41-40_ip-10-0-2-211/events.out.tfevents.1714444973.ip-10-0-2-211.4674.1 +3 -0
  7. runs/Apr30_02-45-32_ip-10-0-2-211/events.out.tfevents.1714445133.ip-10-0-2-211.4978.0 +3 -0
  8. runs/Apr30_02-45-32_ip-10-0-2-211/events.out.tfevents.1714445261.ip-10-0-2-211.4978.1 +3 -0
  9. runs/Apr30_02-48-56_ip-10-0-2-211/events.out.tfevents.1714445337.ip-10-0-2-211.5396.0 +3 -0
  10. runs/Apr30_02-48-56_ip-10-0-2-211/events.out.tfevents.1714445463.ip-10-0-2-211.5396.1 +3 -0
  11. runs/Apr30_02-57-55_ip-10-0-2-211/events.out.tfevents.1714445875.ip-10-0-2-211.5783.0 +3 -0
  12. runs/Apr30_02-57-55_ip-10-0-2-211/events.out.tfevents.1714446005.ip-10-0-2-211.5783.1 +3 -0
  13. runs/Apr30_03-01-39_ip-10-0-2-211/events.out.tfevents.1714446100.ip-10-0-2-211.6210.0 +3 -0
  14. runs/Apr30_03-01-39_ip-10-0-2-211/events.out.tfevents.1714446216.ip-10-0-2-211.6210.1 +3 -0
  15. runs/Apr30_03-05-25_ip-10-0-2-211/events.out.tfevents.1714446325.ip-10-0-2-211.6875.0 +3 -0
  16. runs/Apr30_03-05-25_ip-10-0-2-211/events.out.tfevents.1714446443.ip-10-0-2-211.6875.1 +3 -0
  17. runs/Apr30_03-09-22_ip-10-0-2-211/events.out.tfevents.1714446563.ip-10-0-2-211.7327.0 +3 -0
  18. runs/Apr30_03-09-22_ip-10-0-2-211/events.out.tfevents.1714446678.ip-10-0-2-211.7327.1 +3 -0
  19. runs/Apr30_03-12-49_ip-10-0-2-211/events.out.tfevents.1714446770.ip-10-0-2-211.7795.0 +3 -0
  20. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ model-index:
10
+ - name: wav2vec2-attempt2
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
+ # wav2vec2-attempt2
18
+
19
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 3.1347
22
+ - Accuracy: 0.0952
23
+ - F1: 0.0491
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: 3e-06
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 5
47
+ - total_train_batch_size: 40
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 8
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
58
+ | No log | 0.56 | 1 | 3.1350 | 0.0952 | 0.0625 |
59
+ | No log | 1.67 | 3 | 3.1350 | 0.0952 | 0.0625 |
60
+ | No log | 2.78 | 5 | 3.1350 | 0.0952 | 0.0625 |
61
+ | No log | 3.89 | 7 | 3.1347 | 0.0952 | 0.0491 |
62
+ | No log | 4.44 | 8 | 3.1347 | 0.0952 | 0.0491 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - Transformers 4.36.2
68
+ - Pytorch 2.1.2+cu121
69
+ - Datasets 2.16.0
70
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "en",
61
+ "1": "ca",
62
+ "10": "sw",
63
+ "11": "fa",
64
+ "12": "it",
65
+ "13": "mhr",
66
+ "14": "zh-CN",
67
+ "15": "ba",
68
+ "16": "ta",
69
+ "17": "ru",
70
+ "18": "eu",
71
+ "19": "th",
72
+ "2": "rw",
73
+ "20": "pt",
74
+ "21": "pl",
75
+ "22": "ja",
76
+ "3": "be",
77
+ "4": "eo",
78
+ "5": "de",
79
+ "6": "fr",
80
+ "7": "kab",
81
+ "8": "es",
82
+ "9": "lg"
83
+ },
84
+ "initializer_range": 0.02,
85
+ "intermediate_size": 3072,
86
+ "label2id": {
87
+ "ba": "15",
88
+ "be": "3",
89
+ "ca": "1",
90
+ "de": "5",
91
+ "en": "0",
92
+ "eo": "4",
93
+ "es": "8",
94
+ "eu": "18",
95
+ "fa": "11",
96
+ "fr": "6",
97
+ "it": "12",
98
+ "ja": "22",
99
+ "kab": "7",
100
+ "lg": "9",
101
+ "mhr": "13",
102
+ "pl": "21",
103
+ "pt": "20",
104
+ "ru": "17",
105
+ "rw": "2",
106
+ "sw": "10",
107
+ "ta": "16",
108
+ "th": "19",
109
+ "zh-CN": "14"
110
+ },
111
+ "layer_norm_eps": 1e-05,
112
+ "layerdrop": 0.0,
113
+ "mask_channel_length": 10,
114
+ "mask_channel_min_space": 1,
115
+ "mask_channel_other": 0.0,
116
+ "mask_channel_prob": 0.0,
117
+ "mask_channel_selection": "static",
118
+ "mask_feature_length": 10,
119
+ "mask_feature_min_masks": 0,
120
+ "mask_feature_prob": 0.0,
121
+ "mask_time_length": 10,
122
+ "mask_time_min_masks": 2,
123
+ "mask_time_min_space": 1,
124
+ "mask_time_other": 0.0,
125
+ "mask_time_prob": 0.05,
126
+ "mask_time_selection": "static",
127
+ "model_type": "wav2vec2",
128
+ "no_mask_channel_overlap": false,
129
+ "no_mask_time_overlap": false,
130
+ "num_adapter_layers": 3,
131
+ "num_attention_heads": 12,
132
+ "num_codevector_groups": 2,
133
+ "num_codevectors_per_group": 320,
134
+ "num_conv_pos_embedding_groups": 16,
135
+ "num_conv_pos_embeddings": 128,
136
+ "num_feat_extract_layers": 7,
137
+ "num_hidden_layers": 12,
138
+ "num_negatives": 100,
139
+ "output_hidden_size": 768,
140
+ "pad_token_id": 0,
141
+ "proj_codevector_dim": 256,
142
+ "tdnn_dilation": [
143
+ 1,
144
+ 2,
145
+ 3,
146
+ 1,
147
+ 1
148
+ ],
149
+ "tdnn_dim": [
150
+ 512,
151
+ 512,
152
+ 512,
153
+ 512,
154
+ 1500
155
+ ],
156
+ "tdnn_kernel": [
157
+ 5,
158
+ 3,
159
+ 3,
160
+ 1,
161
+ 1
162
+ ],
163
+ "torch_dtype": "float32",
164
+ "transformers_version": "4.36.2",
165
+ "use_weighted_layer_sum": false,
166
+ "vocab_size": 32,
167
+ "xvector_output_dim": 512
168
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acd37f145e243855d5fe64c822d25ceba50f298006746fe6aae143e5ed803b7b
3
+ size 378323956
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/Apr30_02-41-40_ip-10-0-2-211/events.out.tfevents.1714444902.ip-10-0-2-211.4674.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8edef38ead665d13d11eb4c505b417413d7325df72beacfa38f4d1e0c387b2f2
3
+ size 9712
runs/Apr30_02-41-40_ip-10-0-2-211/events.out.tfevents.1714444973.ip-10-0-2-211.4674.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1210efb1c0214dd6341e7c27b2606ff134bc958e32d58d56a7aef309037673ac
3
+ size 812
runs/Apr30_02-45-32_ip-10-0-2-211/events.out.tfevents.1714445133.ip-10-0-2-211.4978.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec5e3e6e2db9677e14639f5f244dc8fc5a4a37a0669df8ffffb1314416dc3c5
3
+ size 8988
runs/Apr30_02-45-32_ip-10-0-2-211/events.out.tfevents.1714445261.ip-10-0-2-211.4978.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95c2e48dde7489a868dfaef4961e0a681662818e5eaccd02f7b6cd5b26cc074
3
+ size 812
runs/Apr30_02-48-56_ip-10-0-2-211/events.out.tfevents.1714445337.ip-10-0-2-211.5396.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70fe816e2b2cb101fa970bdda58d6201f6ceaec1d1b7709bdfa6cf6c4d8f494
3
+ size 8988
runs/Apr30_02-48-56_ip-10-0-2-211/events.out.tfevents.1714445463.ip-10-0-2-211.5396.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec03d110fcb49fa85a56148a26ab6120341b0281fcba04776ba31b745500ed1c
3
+ size 812
runs/Apr30_02-57-55_ip-10-0-2-211/events.out.tfevents.1714445875.ip-10-0-2-211.5783.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da475679884e88bc54c75a17159262823f1847d885a9ea596792c8458e097f5d
3
+ size 8988
runs/Apr30_02-57-55_ip-10-0-2-211/events.out.tfevents.1714446005.ip-10-0-2-211.5783.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b127bd4fda3a8d615e312f6111fbd668a7d5bf71953ce442fe4c25a8fa2f5d3
3
+ size 812
runs/Apr30_03-01-39_ip-10-0-2-211/events.out.tfevents.1714446100.ip-10-0-2-211.6210.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0819e25c4c8579700a105636b4df205f6e539ba4a5a4780104be7325f40d12d7
3
+ size 8988
runs/Apr30_03-01-39_ip-10-0-2-211/events.out.tfevents.1714446216.ip-10-0-2-211.6210.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4be6a8df64a173ba017993da2e6c84f3a2e4445bdcacd26460e896635cedaecb
3
+ size 812
runs/Apr30_03-05-25_ip-10-0-2-211/events.out.tfevents.1714446325.ip-10-0-2-211.6875.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ee63d9532c300dd9735469f198f9f41087ff99973fbf5395067fa677e15c283
3
+ size 8988
runs/Apr30_03-05-25_ip-10-0-2-211/events.out.tfevents.1714446443.ip-10-0-2-211.6875.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0e22a09151d85ed40b018818b8da9987150063ea177357dc371bef1d1e4c46
3
+ size 812
runs/Apr30_03-09-22_ip-10-0-2-211/events.out.tfevents.1714446563.ip-10-0-2-211.7327.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87603026abdb27bffc73fd19d79b06b590bd774e16d3eebc7969b096c9b2eebf
3
+ size 8988
runs/Apr30_03-09-22_ip-10-0-2-211/events.out.tfevents.1714446678.ip-10-0-2-211.7327.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5a0519f573f69ab8a45dc6da8e95428d259effd4dc94c4baff59ce5b65e8401
3
+ size 812
runs/Apr30_03-12-49_ip-10-0-2-211/events.out.tfevents.1714446770.ip-10-0-2-211.7795.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23047432c19aa89bba2837263c6725e725074fa2e3a4a9a8d30d4e4cdae24548
3
+ size 8982
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16444dce6d5743ae08c7cb8941733afed2f37ca9f395bf6faadf95b7e0fc3d52
3
+ size 4728