Hugging Face's logo

Samuael
/
wav2vec2-phenome-based-alffaamharic

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
1
Samuael commited on
Commit
fb8fd09
·
1 Parent(s): dde5203

End of training

Browse files
Files changed (5) hide show
  1. README.md +91 -0
  2. config.json +118 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-phenome-based-alffaamharic
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-phenome-based-alffaamharic
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: 0.4640
21
+ - Wer: 0.4119
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: 0.0005
41
+ - train_batch_size: 32
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
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 3.1855 | 0.97 | 200 | 3.1227 | 1.0 |
54
+ | 1.1453 | 1.93 | 400 | 0.9709 | 0.8614 |
55
+ | 0.6918 | 2.9 | 600 | 0.5763 | 0.7047 |
56
+ | 0.5615 | 3.86 | 800 | 0.5264 | 0.6577 |
57
+ | 0.4151 | 4.83 | 1000 | 0.4902 | 0.6307 |
58
+ | 0.4082 | 5.8 | 1200 | 0.4867 | 0.6159 |
59
+ | 0.4249 | 6.76 | 1400 | 0.4387 | 0.6066 |
60
+ | 0.4422 | 7.73 | 1600 | 0.4713 | 0.5876 |
61
+ | 0.3768 | 8.7 | 1800 | 0.4875 | 0.5715 |
62
+ | 0.3404 | 9.66 | 2000 | 0.4730 | 0.5408 |
63
+ | 0.2373 | 10.63 | 2200 | 0.4249 | 0.5167 |
64
+ | 0.2167 | 11.59 | 2400 | 0.4051 | 0.5012 |
65
+ | 0.2074 | 12.56 | 2600 | 0.4385 | 0.4923 |
66
+ | 0.2195 | 13.53 | 2800 | 0.3927 | 0.4919 |
67
+ | 0.2079 | 14.49 | 3000 | 0.4488 | 0.5117 |
68
+ | 0.2268 | 15.46 | 3200 | 0.4579 | 0.4859 |
69
+ | 0.1587 | 16.43 | 3400 | 0.4496 | 0.4764 |
70
+ | 0.1395 | 17.39 | 3600 | 0.4429 | 0.4710 |
71
+ | 0.1078 | 18.36 | 3800 | 0.4502 | 0.4591 |
72
+ | 0.124 | 19.32 | 4000 | 0.4060 | 0.4490 |
73
+ | 0.1339 | 20.29 | 4200 | 0.4466 | 0.4658 |
74
+ | 0.1235 | 21.26 | 4400 | 0.4355 | 0.4617 |
75
+ | 0.1304 | 22.22 | 4600 | 0.4817 | 0.4566 |
76
+ | 0.1026 | 23.19 | 4800 | 0.4608 | 0.4413 |
77
+ | 0.064 | 24.15 | 5000 | 0.4689 | 0.4363 |
78
+ | 0.0813 | 25.12 | 5200 | 0.4616 | 0.4275 |
79
+ | 0.0782 | 26.09 | 5400 | 0.4574 | 0.4277 |
80
+ | 0.0529 | 27.05 | 5600 | 0.4445 | 0.4171 |
81
+ | 0.0616 | 28.02 | 5800 | 0.4674 | 0.4214 |
82
+ | 0.0639 | 28.99 | 6000 | 0.4568 | 0.4113 |
83
+ | 0.0923 | 29.95 | 6200 | 0.4640 | 0.4119 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.34.0
89
+ - Pytorch 2.0.1+cu118
90
+ - Datasets 2.14.5
91
+ - Tokenizers 0.14.1
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": 0,
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": "4.34.0",
115
+ "use_weighted_layer_sum": false,
116
+ "vocab_size": 41,
117
+ "xvector_output_dim": 512
118
+ }
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92100230f32aa7825e40ae7220ff20083f99467361d3bfe095e79214024701d8
3
+ size 377686433
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ada5775188786952493afe8d74d5d83e0e826e8db9720b9ff78db8e5da60b11e
3
+ size 4155