datdo commited on
Commit
3303ced
·
verified ·
0 Parent(s):

Duplicate from datdo/wav2vec2-base-timit-demo-google-colab

Browse files
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ base_model: facebook/wav2vec2-base
6
+ datasets:
7
+ - timit_asr
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: wav2vec2-base-timit-demo-google-colab
12
+ results:
13
+ - task:
14
+ type: automatic-speech-recognition
15
+ name: Automatic Speech Recognition
16
+ dataset:
17
+ name: timit_asr
18
+ type: timit_asr
19
+ config: clean
20
+ split: None
21
+ args: clean
22
+ metrics:
23
+ - type: wer
24
+ value: 0.33795052029494865
25
+ name: Wer
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # wav2vec2-base-timit-demo-google-colab
32
+
33
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the timit_asr dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.5720
36
+ - Wer: 0.3380
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 0.0001
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 1000
62
+ - num_epochs: 30
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|
69
+ | 3.466 | 1.0040 | 500 | 1.4947 | 0.9858 |
70
+ | 0.8266 | 2.0080 | 1000 | 0.5298 | 0.5179 |
71
+ | 0.438 | 3.0120 | 1500 | 0.4565 | 0.4564 |
72
+ | 0.2918 | 4.0161 | 2000 | 0.4528 | 0.4382 |
73
+ | 0.2282 | 5.0201 | 2500 | 0.4541 | 0.4095 |
74
+ | 0.184 | 6.0241 | 3000 | 0.5109 | 0.4053 |
75
+ | 0.1513 | 7.0281 | 3500 | 0.5116 | 0.3923 |
76
+ | 0.1378 | 8.0321 | 4000 | 0.5137 | 0.3876 |
77
+ | 0.1194 | 9.0361 | 4500 | 0.5208 | 0.3961 |
78
+ | 0.1072 | 10.0402 | 5000 | 0.5417 | 0.3845 |
79
+ | 0.0982 | 11.0442 | 5500 | 0.5653 | 0.3847 |
80
+ | 0.0868 | 12.0482 | 6000 | 0.4593 | 0.3722 |
81
+ | 0.0774 | 13.0522 | 6500 | 0.4822 | 0.3723 |
82
+ | 0.0723 | 14.0562 | 7000 | 0.5303 | 0.3702 |
83
+ | 0.0635 | 15.0602 | 7500 | 0.4888 | 0.3742 |
84
+ | 0.0597 | 16.0643 | 8000 | 0.5254 | 0.3638 |
85
+ | 0.0571 | 17.0683 | 8500 | 0.5107 | 0.3632 |
86
+ | 0.0491 | 18.0723 | 9000 | 0.5649 | 0.3575 |
87
+ | 0.0511 | 19.0763 | 9500 | 0.5430 | 0.3627 |
88
+ | 0.0425 | 20.0803 | 10000 | 0.5726 | 0.3633 |
89
+ | 0.0386 | 21.0843 | 10500 | 0.5977 | 0.3657 |
90
+ | 0.0388 | 22.0884 | 11000 | 0.5430 | 0.3570 |
91
+ | 0.0338 | 23.0924 | 11500 | 0.5612 | 0.3535 |
92
+ | 0.0301 | 24.0964 | 12000 | 0.5841 | 0.3514 |
93
+ | 0.0272 | 25.1004 | 12500 | 0.5682 | 0.3457 |
94
+ | 0.0255 | 26.1044 | 13000 | 0.5657 | 0.3494 |
95
+ | 0.0234 | 27.1084 | 13500 | 0.5611 | 0.3450 |
96
+ | 0.0248 | 28.1124 | 14000 | 0.5721 | 0.3399 |
97
+ | 0.0203 | 29.1165 | 14500 | 0.5720 | 0.3380 |
98
+
99
+
100
+ ### Framework versions
101
+
102
+ - Transformers 4.41.2
103
+ - Pytorch 2.1.2
104
+ - Datasets 2.19.2
105
+ - Tokenizers 0.19.1
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 31,
3
+ "<s>": 30
4
+ }
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": "4.41.2",
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 sha256:86dbd57b8272959740e71aa4a64dea80555a2a87f6ab12ffbe9f82f410418221
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/Jul09_10-51-18_84a1efd54bd7/events.out.tfevents.1720522396.84a1efd54bd7.24.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647d7be9db402f679c2b7995399b82d46ff59e28ac6c3e83c567bae6e5c3cbc1
3
+ size 22282
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "28": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "29": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "30": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "31": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": null,
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c7271d28a65abca684acc259053dad5a258bc817f9f87fbf61116fe057fa374
3
+ size 5112
vocab.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 9,
3
+ "[PAD]": 29,
4
+ "[UNK]": 28,
5
+ "a": 5,
6
+ "b": 14,
7
+ "c": 2,
8
+ "d": 26,
9
+ "e": 4,
10
+ "f": 25,
11
+ "g": 8,
12
+ "h": 15,
13
+ "i": 10,
14
+ "j": 23,
15
+ "k": 7,
16
+ "l": 11,
17
+ "m": 19,
18
+ "n": 24,
19
+ "o": 18,
20
+ "p": 6,
21
+ "q": 3,
22
+ "r": 1,
23
+ "s": 13,
24
+ "t": 21,
25
+ "u": 17,
26
+ "v": 0,
27
+ "w": 16,
28
+ "x": 12,
29
+ "y": 22,
30
+ "z": 20,
31
+ "|": 27
32
+ }