Hugging Face's logo

jadasdn
/
wav2vec2-1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
jadasdn commited on
Commit
ba70849
•
1 Parent(s): bb71487

End of training

Browse files
Files changed (6) hide show
  1. README.md +121 -0
  2. config.json +118 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. runs/Nov27_09-31-34_7fadf3e13014/events.out.tfevents.1701077777.7fadf3e13014.1082.0 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: wav2vec2-1
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # wav2vec2-1
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.8870
21
+ - Wer: 0.3805
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0001
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 1000
47
+ - num_epochs: 30
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
54
+ | 4.6457 | 0.5 | 500 | 2.8866 | 0.9999 |
55
+ | 2.863 | 1.0 | 1000 | 2.8676 | 1.0 |
56
+ | 1.8085 | 1.5 | 1500 | 0.9396 | 0.6602 |
57
+ | 0.8828 | 2.0 | 2000 | 0.7278 | 0.5699 |
58
+ | 0.6659 | 2.5 | 2500 | 0.7000 | 0.5401 |
59
+ | 0.6085 | 3.0 | 3000 | 0.7143 | 0.4939 |
60
+ | 0.4878 | 3.5 | 3500 | 0.5845 | 0.4717 |
61
+ | 0.4888 | 4.0 | 4000 | 0.6201 | 0.4677 |
62
+ | 0.4022 | 4.5 | 4500 | 0.5984 | 0.4532 |
63
+ | 0.3947 | 5.0 | 5000 | 0.5874 | 0.4378 |
64
+ | 0.3415 | 5.5 | 5500 | 0.6486 | 0.4405 |
65
+ | 0.3413 | 6.0 | 6000 | 0.5988 | 0.4355 |
66
+ | 0.2903 | 6.5 | 6500 | 0.6584 | 0.4304 |
67
+ | 0.3046 | 7.0 | 7000 | 0.6602 | 0.4189 |
68
+ | 0.2625 | 7.5 | 7500 | 0.5924 | 0.4235 |
69
+ | 0.2625 | 8.0 | 8000 | 0.6541 | 0.4212 |
70
+ | 0.2341 | 8.5 | 8500 | 0.6365 | 0.4171 |
71
+ | 0.2384 | 9.0 | 9000 | 0.6095 | 0.4182 |
72
+ | 0.2052 | 9.5 | 9500 | 0.6675 | 0.4091 |
73
+ | 0.2124 | 10.0 | 10000 | 0.6524 | 0.4110 |
74
+ | 0.1915 | 10.5 | 10500 | 0.6877 | 0.4122 |
75
+ | 0.1922 | 11.0 | 11000 | 0.6857 | 0.4122 |
76
+ | 0.1719 | 11.5 | 11500 | 0.6881 | 0.4056 |
77
+ | 0.1811 | 12.0 | 12000 | 0.6832 | 0.4083 |
78
+ | 0.1554 | 12.5 | 12500 | 0.7378 | 0.4103 |
79
+ | 0.163 | 13.0 | 13000 | 0.6940 | 0.4019 |
80
+ | 0.1452 | 13.5 | 13500 | 0.6811 | 0.3993 |
81
+ | 0.1457 | 14.0 | 14000 | 0.7216 | 0.4007 |
82
+ | 0.1319 | 14.5 | 14500 | 0.7243 | 0.3996 |
83
+ | 0.1367 | 15.0 | 15000 | 0.7332 | 0.4006 |
84
+ | 0.118 | 15.5 | 15500 | 0.7609 | 0.4050 |
85
+ | 0.121 | 16.0 | 16000 | 0.7585 | 0.4021 |
86
+ | 0.1096 | 16.5 | 16500 | 0.7583 | 0.4003 |
87
+ | 0.112 | 17.0 | 17000 | 0.7928 | 0.4011 |
88
+ | 0.1063 | 17.5 | 17500 | 0.7794 | 0.4038 |
89
+ | 0.1009 | 18.0 | 18000 | 0.7474 | 0.3982 |
90
+ | 0.0931 | 18.5 | 18500 | 0.8143 | 0.3980 |
91
+ | 0.0943 | 19.0 | 19000 | 0.7873 | 0.4000 |
92
+ | 0.0847 | 19.5 | 19500 | 0.8064 | 0.3991 |
93
+ | 0.0831 | 20.0 | 20000 | 0.8564 | 0.3967 |
94
+ | 0.0821 | 20.5 | 20500 | 0.8632 | 0.3956 |
95
+ | 0.0807 | 21.0 | 21000 | 0.8250 | 0.3928 |
96
+ | 0.0748 | 21.5 | 21500 | 0.8389 | 0.3949 |
97
+ | 0.0751 | 22.0 | 22000 | 0.8355 | 0.3943 |
98
+ | 0.072 | 22.5 | 22500 | 0.8568 | 0.3930 |
99
+ | 0.0696 | 23.0 | 23000 | 0.8396 | 0.3912 |
100
+ | 0.0678 | 23.5 | 23500 | 0.8634 | 0.3901 |
101
+ | 0.0671 | 24.0 | 24000 | 0.8576 | 0.3880 |
102
+ | 0.063 | 24.5 | 24500 | 0.8303 | 0.3876 |
103
+ | 0.0575 | 25.0 | 25000 | 0.9125 | 0.3847 |
104
+ | 0.0572 | 25.5 | 25500 | 0.8745 | 0.3839 |
105
+ | 0.0572 | 26.0 | 26000 | 0.8714 | 0.3844 |
106
+ | 0.0533 | 26.5 | 26500 | 0.8824 | 0.3840 |
107
+ | 0.0496 | 27.0 | 27000 | 0.8993 | 0.3830 |
108
+ | 0.0525 | 27.5 | 27500 | 0.8818 | 0.3830 |
109
+ | 0.0514 | 28.0 | 28000 | 0.8874 | 0.3819 |
110
+ | 0.0464 | 28.5 | 28500 | 0.8947 | 0.3802 |
111
+ | 0.0473 | 29.0 | 29000 | 0.9028 | 0.3805 |
112
+ | 0.048 | 29.5 | 29500 | 0.8899 | 0.3801 |
113
+ | 0.0458 | 30.0 | 30000 | 0.8870 | 0.3805 |
114
+
115
+
116
+ ### Framework versions
117
+
118
+ - Transformers 4.35.2
119
+ - Pytorch 2.1.0+cu118
120
+ - Datasets 2.15.0
121
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "Wav2Vec2ForCTC"
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": "mean",
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
+ "initializer_range": 0.02,
60
+ "intermediate_size": 3072,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.0,
63
+ "mask_channel_length": 10,
64
+ "mask_channel_min_space": 1,
65
+ "mask_channel_other": 0.0,
66
+ "mask_channel_prob": 0.0,
67
+ "mask_channel_selection": "static",
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_min_space": 1,
74
+ "mask_time_other": 0.0,
75
+ "mask_time_prob": 0.05,
76
+ "mask_time_selection": "static",
77
+ "model_type": "wav2vec2",
78
+ "no_mask_channel_overlap": false,
79
+ "no_mask_time_overlap": false,
80
+ "num_adapter_layers": 3,
81
+ "num_attention_heads": 12,
82
+ "num_codevector_groups": 2,
83
+ "num_codevectors_per_group": 320,
84
+ "num_conv_pos_embedding_groups": 16,
85
+ "num_conv_pos_embeddings": 128,
86
+ "num_feat_extract_layers": 7,
87
+ "num_hidden_layers": 12,
88
+ "num_negatives": 100,
89
+ "output_hidden_size": 768,
90
+ "pad_token_id": 29,
91
+ "proj_codevector_dim": 256,
92
+ "tdnn_dilation": [
93
+ 1,
94
+ 2,
95
+ 3,
96
+ 1,
97
+ 1
98
+ ],
99
+ "tdnn_dim": [
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 512,
104
+ 1500
105
+ ],
106
+ "tdnn_kernel": [
107
+ 5,
108
+ 3,
109
+ 3,
110
+ 1,
111
+ 1
112
+ ],
113
+ "torch_dtype": "float32",
114
+ "transformers_version": "4.35.2",
115
+ "use_weighted_layer_sum": false,
116
+ "vocab_size": 32,
117
+ "xvector_output_dim": 512
118
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ea676405fbab0744e6781a2dc920360b45152d8b72e34a2ca98f289fdf72a9
3
+ size 377611120
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/Nov27_09-31-34_7fadf3e13014/events.out.tfevents.1701077777.7fadf3e13014.1082.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e7b93ba16dee0c02809bbe41d3c22d64323ed5c7ee910bd0e3ce251b25aa4b
3
+ size 35007
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c64a5c46c2063c6551945a069e05211bd2e8c26f274dbb6dbe94fd26051650a2
3
+ size 4536