Hugging Face's logo

bobboyms
/
wav2vec2-xls-r-300m-en-phoneme-ctc-60h-balanced

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
bobboyms commited on
Commit
75b51b3
·
verified ·
1 Parent(s): dadb1c3

End of training (fixed pipeline)

Browse files
Files changed (9) hide show
  1. README.md +99 -0
  2. added_tokens.json +4 -0
  3. config.json +108 -0
  4. model.safetensors +3 -0
  5. preprocessor_config.json +10 -0
  6. special_tokens_map.json +4 -0
  7. tokenizer_config.json +50 -0
  8. training_args.bin +3 -0
  9. vocab.json +88 -0
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: facebook/wav2vec2-xls-r-300m
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: wav2vec2-xls-r-300m-en-phoneme-ctc-60h-balanced
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # wav2vec2-xls-r-300m-en-phoneme-ctc-60h-balanced
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.1532
20
+ - Per: 0.0378
21
+ - Phoneme Accuracy: 0.9622
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: 5e-05
41
+ - train_batch_size: 24
42
+ - eval_batch_size: 24
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_ratio: 0.05
47
+ - num_epochs: 20
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Per | Phoneme Accuracy |
53
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|:----------------:|
54
+ | 4.9502 | 0.3185 | 500 | 4.3875 | 1.0 | 0.0 |
55
+ | 3.6506 | 0.6369 | 1000 | 3.5930 | 1.0 | 0.0 |
56
+ | 3.6533 | 0.9554 | 1500 | 3.5748 | 1.0 | 0.0 |
57
+ | 3.6035 | 1.2739 | 2000 | 3.5249 | 1.0 | 0.0 |
58
+ | 1.4335 | 1.5924 | 2500 | 0.7984 | 0.1635 | 0.8365 |
59
+ | 0.6011 | 1.9108 | 3000 | 0.3071 | 0.0706 | 0.9294 |
60
+ | 0.4718 | 2.2293 | 3500 | 0.2315 | 0.0576 | 0.9424 |
61
+ | 0.4498 | 2.5478 | 4000 | 0.2091 | 0.0528 | 0.9472 |
62
+ | 0.3683 | 2.8662 | 4500 | 0.1897 | 0.0504 | 0.9496 |
63
+ | 0.331 | 3.1847 | 5000 | 0.1810 | 0.0472 | 0.9528 |
64
+ | 0.3256 | 3.5032 | 5500 | 0.1725 | 0.0458 | 0.9542 |
65
+ | 0.2949 | 3.8217 | 6000 | 0.1643 | 0.0441 | 0.9559 |
66
+ | 0.2894 | 4.1401 | 6500 | 0.1662 | 0.0436 | 0.9564 |
67
+ | 0.2542 | 4.4586 | 7000 | 0.1592 | 0.0430 | 0.9570 |
68
+ | 0.2422 | 4.7771 | 7500 | 0.1563 | 0.0433 | 0.9567 |
69
+ | 0.2485 | 5.0955 | 8000 | 0.1577 | 0.0417 | 0.9583 |
70
+ | 0.2592 | 5.4140 | 8500 | 0.1538 | 0.0427 | 0.9573 |
71
+ | 0.2295 | 5.7325 | 9000 | 0.1520 | 0.0412 | 0.9588 |
72
+ | 0.215 | 6.0510 | 9500 | 0.1493 | 0.0402 | 0.9598 |
73
+ | 0.2304 | 6.3694 | 10000 | 0.1508 | 0.0410 | 0.9590 |
74
+ | 0.2111 | 6.6879 | 10500 | 0.1475 | 0.0397 | 0.9603 |
75
+ | 0.2007 | 7.0064 | 11000 | 0.1477 | 0.0393 | 0.9607 |
76
+ | 0.1947 | 7.3248 | 11500 | 0.1529 | 0.0390 | 0.9610 |
77
+ | 0.1895 | 7.6433 | 12000 | 0.1512 | 0.0390 | 0.9610 |
78
+ | 0.2178 | 7.9618 | 12500 | 0.1443 | 0.0396 | 0.9604 |
79
+ | 0.2088 | 8.2803 | 13000 | 0.1467 | 0.0393 | 0.9607 |
80
+ | 0.1813 | 8.5987 | 13500 | 0.1488 | 0.0383 | 0.9617 |
81
+ | 0.1796 | 8.9172 | 14000 | 0.1450 | 0.0384 | 0.9616 |
82
+ | 0.1657 | 9.2357 | 14500 | 0.1474 | 0.0382 | 0.9618 |
83
+ | 0.1687 | 9.5541 | 15000 | 0.1478 | 0.0384 | 0.9616 |
84
+ | 0.1759 | 9.8726 | 15500 | 0.1452 | 0.0379 | 0.9621 |
85
+ | 0.1699 | 10.1911 | 16000 | 0.1495 | 0.0376 | 0.9624 |
86
+ | 0.1737 | 10.5096 | 16500 | 0.1492 | 0.0374 | 0.9626 |
87
+ | 0.1784 | 10.8280 | 17000 | 0.1465 | 0.0385 | 0.9615 |
88
+ | 0.1697 | 11.1465 | 17500 | 0.1480 | 0.0385 | 0.9615 |
89
+ | 0.1618 | 11.4650 | 18000 | 0.1477 | 0.0375 | 0.9625 |
90
+ | 0.1499 | 11.7834 | 18500 | 0.1474 | 0.0398 | 0.9602 |
91
+ | 0.1363 | 12.1019 | 19000 | 0.1532 | 0.0378 | 0.9622 |
92
+
93
+
94
+ ### Framework versions
95
+
96
+ - Transformers 4.57.6
97
+ - Pytorch 2.11.0+cu130
98
+ - Datasets 5.0.0
99
+ - Tokenizers 0.22.2
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 87,
3
+ "<s>": 86
4
+ }
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "adapter_attn_dim": null,
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": null,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
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": true,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "dtype": "float32",
49
+ "eos_token_id": null,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.1,
64
+ "mask_feature_length": 10,
65
+ "mask_feature_min_masks": 0,
66
+ "mask_feature_prob": 0.03,
67
+ "mask_time_length": 10,
68
+ "mask_time_min_masks": 2,
69
+ "mask_time_prob": 0.05,
70
+ "model_type": "wav2vec2",
71
+ "num_adapter_layers": 3,
72
+ "num_attention_heads": 16,
73
+ "num_codevector_groups": 2,
74
+ "num_codevectors_per_group": 320,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 24,
79
+ "num_negatives": 100,
80
+ "output_hidden_size": 1024,
81
+ "pad_token_id": 0,
82
+ "proj_codevector_dim": 768,
83
+ "tdnn_dilation": [
84
+ 1,
85
+ 2,
86
+ 3,
87
+ 1,
88
+ 1
89
+ ],
90
+ "tdnn_dim": [
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 1500
96
+ ],
97
+ "tdnn_kernel": [
98
+ 5,
99
+ 3,
100
+ 3,
101
+ 1,
102
+ 1
103
+ ],
104
+ "transformers_version": "4.57.6",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 88,
107
+ "xvector_output_dim": 512
108
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ff6a57cf7cc33672bb159ce8f6d6a80660575b97d18f42ae7a786de99724726
3
+ size 1262168280
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "<pad>",
3
+ "unk_token": "<unk>"
4
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "86": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "87": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": null,
37
+ "clean_up_tokenization_spaces": false,
38
+ "do_phonemize": false,
39
+ "eos_token": null,
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<pad>",
43
+ "phone_delimiter_token": " ",
44
+ "phonemizer_backend": "espeak",
45
+ "phonemizer_lang": "en-us",
46
+ "processor_class": "Wav2Vec2Processor",
47
+ "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer",
48
+ "unk_token": "<unk>",
49
+ "word_delimiter_token": "|"
50
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd76c3dcd540178bd92ee037389a2fece31afa2691ffda94830514f975de9204
3
+ size 5905
vocab.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<pad>": 0,
3
+ "<unk>": 1,
4
+ "aɪ": 2,
5
+ "aɪə": 3,
6
+ "aɪɚ": 4,
7
+ "aʊ": 5,
8
+ "b": 6,
9
+ "d": 7,
10
+ "dʒ": 8,
11
+ "eɪ": 9,
12
+ "f": 10,
13
+ "h": 11,
14
+ "i": 12,
15
+ "iə": 13,
16
+ "iː": 14,
17
+ "j": 15,
18
+ "k": 16,
19
+ "l": 17,
20
+ "m": 18,
21
+ "n": 19,
22
+ "n̩": 20,
23
+ "oʊ": 21,
24
+ "p": 22,
25
+ "s": 23,
26
+ "t": 24,
27
+ "tʃ": 25,
28
+ "uː": 26,
29
+ "v": 27,
30
+ "w": 28,
31
+ "z": 29,
32
+ "|": 30,
33
+ "æ": 31,
34
+ "ð": 32,
35
+ "ŋ": 33,
36
+ "ɐ": 34,
37
+ "ɑː": 35,
38
+ "ɑːɹ": 36,
39
+ "ɔ": 37,
40
+ "ɔɪ": 38,
41
+ "ɔː": 39,
42
+ "ɔːɹ": 40,
43
+ "ə": 41,
44
+ "əl": 42,
45
+ "ɚ": 43,
46
+ "ɛ": 44,
47
+ "ɛɹ": 45,
48
+ "ɜː": 46,
49
+ "ɡ": 47,
50
+ "ɪ": 48,
51
+ "ɪɹ": 49,
52
+ "ɹ": 50,
53
+ "ɾ": 51,
54
+ "ʃ": 52,
55
+ "ʊ": 53,
56
+ "ʊɹ": 54,
57
+ "ʌ": 55,
58
+ "ʒ": 56,
59
+ "ʔ": 57,
60
+ "ˈaɪ": 58,
61
+ "ˈaɪə": 59,
62
+ "ˈaɪɚ": 60,
63
+ "ˈaʊ": 61,
64
+ "ˈeɪ": 62,
65
+ "ˈiə": 63,
66
+ "ˈiː": 64,
67
+ "ˈn̩": 65,
68
+ "ˈoʊ": 66,
69
+ "ˈuː": 67,
70
+ "ˈæ": 68,
71
+ "ˈɑː": 69,
72
+ "ˈɑːɹ": 70,
73
+ "ˈɔ": 71,
74
+ "ˈɔɪ": 72,
75
+ "ˈɔː": 73,
76
+ "ˈɔːɹ": 74,
77
+ "ˈə": 75,
78
+ "ˈɛ": 76,
79
+ "ˈɛɹ": 77,
80
+ "ˈɜː": 78,
81
+ "ˈɪ": 79,
82
+ "ˈɪɹ": 80,
83
+ "ˈʊ": 81,
84
+ "ˈʊɹ": 82,
85
+ "ˈʌ": 83,
86
+ "θ": 84,
87
+ "ᵻ": 85
88
+ }