Hugging Face's logo

Siyong
/
MC_RN_LM

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
1
Siyong commited on
Commit
d679eb5
·
1 Parent(s): 7867de3

Upload noLM model

Browse files
Files changed (8) hide show
  1. README.md +104 -0
  2. config.json +117 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +1 -0
  6. tokenizer_config.json +1 -0
  7. training_args.bin +3 -0
  8. vocab.json +1 -0
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: Millad_Customer_RN
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # Millad_Customer_RN
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 4.5635
18
+ - Wer: 0.8113
19
+ - Cer: 0.4817
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 4000
45
+ - num_epochs: 600
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
51
+ |:-------------:|:------:|:-----:|:---------------:|:------:|:------:|
52
+ | 1.9257 | 13.33 | 2000 | 2.0606 | 0.9767 | 0.5500 |
53
+ | 1.4828 | 26.67 | 4000 | 2.1161 | 0.9019 | 0.4932 |
54
+ | 1.2582 | 40.0 | 6000 | 2.0589 | 0.8504 | 0.4942 |
55
+ | 0.9804 | 53.33 | 8000 | 2.4633 | 0.8745 | 0.4763 |
56
+ | 0.7862 | 66.67 | 10000 | 2.4794 | 0.8861 | 0.4944 |
57
+ | 0.6492 | 80.0 | 12000 | 2.8693 | 0.8554 | 0.4928 |
58
+ | 0.5375 | 93.33 | 14000 | 2.6125 | 0.8296 | 0.4802 |
59
+ | 0.4462 | 106.67 | 16000 | 2.7591 | 0.8770 | 0.4974 |
60
+ | 0.3873 | 120.0 | 18000 | 3.0325 | 0.8379 | 0.4800 |
61
+ | 0.3445 | 133.33 | 20000 | 2.9965 | 0.8761 | 0.4986 |
62
+ | 0.3087 | 146.67 | 22000 | 3.3437 | 0.8221 | 0.4923 |
63
+ | 0.2755 | 160.0 | 24000 | 3.3022 | 0.8803 | 0.5211 |
64
+ | 0.2467 | 173.33 | 26000 | 3.2348 | 0.8479 | 0.4933 |
65
+ | 0.2281 | 186.67 | 28000 | 3.8010 | 0.8695 | 0.5081 |
66
+ | 0.2119 | 200.0 | 30000 | 3.0446 | 0.8545 | 0.4902 |
67
+ | 0.194 | 213.33 | 32000 | 3.0873 | 0.8454 | 0.4840 |
68
+ | 0.1677 | 226.67 | 34000 | 3.6184 | 0.8645 | 0.5019 |
69
+ | 0.1642 | 240.0 | 36000 | 3.2480 | 0.8412 | 0.4903 |
70
+ | 0.1656 | 253.33 | 38000 | 3.4379 | 0.8362 | 0.4816 |
71
+ | 0.1371 | 266.67 | 40000 | 3.5117 | 0.8479 | 0.5040 |
72
+ | 0.1301 | 280.0 | 42000 | 3.4360 | 0.8404 | 0.4870 |
73
+ | 0.128 | 293.33 | 44000 | 3.6589 | 0.8537 | 0.4977 |
74
+ | 0.1152 | 306.67 | 46000 | 4.2359 | 0.8545 | 0.5051 |
75
+ | 0.1119 | 320.0 | 48000 | 3.5818 | 0.7980 | 0.4882 |
76
+ | 0.1026 | 333.33 | 50000 | 3.7618 | 0.8013 | 0.4865 |
77
+ | 0.0945 | 346.67 | 52000 | 4.2197 | 0.8404 | 0.5028 |
78
+ | 0.0962 | 360.0 | 54000 | 3.9231 | 0.8653 | 0.5030 |
79
+ | 0.088 | 373.33 | 56000 | 3.8400 | 0.8354 | 0.4914 |
80
+ | 0.0743 | 386.67 | 58000 | 3.4924 | 0.8088 | 0.4824 |
81
+ | 0.0811 | 400.0 | 60000 | 3.8370 | 0.8396 | 0.4861 |
82
+ | 0.0696 | 413.33 | 62000 | 4.2808 | 0.8412 | 0.5065 |
83
+ | 0.0692 | 426.67 | 64000 | 4.0161 | 0.8088 | 0.4744 |
84
+ | 0.0622 | 440.0 | 66000 | 3.9080 | 0.8163 | 0.4910 |
85
+ | 0.0591 | 453.33 | 68000 | 3.9838 | 0.8113 | 0.4823 |
86
+ | 0.0527 | 466.67 | 70000 | 3.8067 | 0.8329 | 0.4914 |
87
+ | 0.056 | 480.0 | 72000 | 4.1415 | 0.8096 | 0.4782 |
88
+ | 0.0535 | 493.33 | 74000 | 4.3350 | 0.8229 | 0.4828 |
89
+ | 0.0531 | 506.67 | 76000 | 3.9808 | 0.8071 | 0.4807 |
90
+ | 0.0451 | 520.0 | 78000 | 4.0301 | 0.7988 | 0.4816 |
91
+ | 0.044 | 533.33 | 80000 | 4.4680 | 0.8371 | 0.4921 |
92
+ | 0.0389 | 546.67 | 82000 | 4.1380 | 0.8121 | 0.4819 |
93
+ | 0.0392 | 560.0 | 84000 | 4.3910 | 0.7930 | 0.4763 |
94
+ | 0.0389 | 573.33 | 86000 | 4.5086 | 0.8055 | 0.4802 |
95
+ | 0.0355 | 586.67 | 88000 | 4.6259 | 0.8113 | 0.4821 |
96
+ | 0.0307 | 600.0 | 90000 | 4.5635 | 0.8113 | 0.4817 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - Transformers 4.17.0
102
+ - Pytorch 1.12.0+cu113
103
+ - Datasets 1.18.3
104
+ - Tokenizers 0.12.1
config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
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": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.0,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.1,
62
+ "mask_channel_length": 10,
63
+ "mask_channel_min_space": 1,
64
+ "mask_channel_other": 0.0,
65
+ "mask_channel_prob": 0.0,
66
+ "mask_channel_selection": "static",
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_min_space": 1,
73
+ "mask_time_other": 0.0,
74
+ "mask_time_prob": 0.05,
75
+ "mask_time_selection": "static",
76
+ "model_type": "wav2vec2",
77
+ "no_mask_channel_overlap": false,
78
+ "no_mask_time_overlap": false,
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 12,
81
+ "num_codevector_groups": 2,
82
+ "num_codevectors_per_group": 320,
83
+ "num_conv_pos_embedding_groups": 16,
84
+ "num_conv_pos_embeddings": 128,
85
+ "num_feat_extract_layers": 7,
86
+ "num_hidden_layers": 12,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 768,
89
+ "pad_token_id": 31,
90
+ "proj_codevector_dim": 256,
91
+ "tdnn_dilation": [
92
+ 1,
93
+ 2,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tdnn_dim": [
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 1500
104
+ ],
105
+ "tdnn_kernel": [
106
+ 5,
107
+ 3,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.17.0",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 34,
116
+ "xvector_output_dim": 512
117
+ }
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 sha256:599bf9199ae24b5e36bbfc209bf9977dd0b6a60c874f21cb9fe123812c12e43e
3
+ size 377677719
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69ae2283efd341bd1c2b37a21247cc836fcb7734baf822b2ea47c3de0fb095f8
3
+ size 3055
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"j": 0, "l": 1, "e": 2, "n": 3, "t": 4, "g": 5, "i": 6, "r": 7, "a": 8, "u": 9, "'": 10, "k": 11, "q": 12, "s": 13, "c": 14, "1": 15, "h": 16, "v": 17, "p": 18, "f": 19, "m": 20, "z": 21, "x": 22, "o": 23, "w": 25, "b": 26, "2": 27, "d": 28, "y": 29, "[UNK]": 30, "[PAD]": 31, "|": 24}