Hugging Face's logo

sil-ai
/
w2v2-kaqchikel

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Kaqchikel
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
DCNemesis commited on
Commit
58cabbc
·
1 Parent(s): 8daa679

moving files to repo

Browse files
Files changed (27) hide show
  1. README.md +89 -0
  2. added_tokens.json +1 -0
  3. config.json +79 -0
  4. preprocessor_config.json +9 -0
  5. pytorch_model.bin +3 -0
  6. runs/Apr14_17-13-58_ea396a5a3c34/1649956485.637141/events.out.tfevents.1649956485.ea396a5a3c34.86.1 +3 -0
  7. runs/Apr14_17-13-58_ea396a5a3c34/events.out.tfevents.1649956485.ea396a5a3c34.86.0 +3 -0
  8. runs/Apr21_12-07-05_67ae26b0b998/1650542905.282875/events.out.tfevents.1650542905.67ae26b0b998.80.1 +3 -0
  9. runs/Apr21_12-07-05_67ae26b0b998/events.out.tfevents.1650542905.67ae26b0b998.80.0 +3 -0
  10. runs/Apr21_12-37-00_67ae26b0b998/1650544811.2666936/events.out.tfevents.1650544811.67ae26b0b998.80.3 +3 -0
  11. runs/Apr21_12-37-00_67ae26b0b998/events.out.tfevents.1650544811.67ae26b0b998.80.2 +3 -0
  12. runs/Apr21_12-45-40_67ae26b0b998/1650545219.9652703/events.out.tfevents.1650545219.67ae26b0b998.80.5 +3 -0
  13. runs/Apr21_12-45-40_67ae26b0b998/1650545281.8778462/events.out.tfevents.1650545281.67ae26b0b998.80.7 +3 -0
  14. runs/Apr21_12-45-40_67ae26b0b998/events.out.tfevents.1650545219.67ae26b0b998.80.4 +3 -0
  15. runs/Apr21_12-45-40_67ae26b0b998/events.out.tfevents.1650545281.67ae26b0b998.80.6 +3 -0
  16. runs/Apr21_12-51-48_67ae26b0b998/1650545551.2196941/events.out.tfevents.1650545551.67ae26b0b998.4446.1 +3 -0
  17. runs/Apr21_12-51-48_67ae26b0b998/events.out.tfevents.1650545551.67ae26b0b998.4446.0 +3 -0
  18. runs/Apr21_15-55-28_67ae26b0b998/1650556558.152829/events.out.tfevents.1650556558.67ae26b0b998.4947.1 +3 -0
  19. runs/Apr21_15-55-28_67ae26b0b998/events.out.tfevents.1650556558.67ae26b0b998.4947.0 +3 -0
  20. runs/Apr21_16-05-04_67ae26b0b998/1650557137.9502409/events.out.tfevents.1650557137.67ae26b0b998.4947.3 +3 -0
  21. runs/Apr21_16-05-04_67ae26b0b998/events.out.tfevents.1650557137.67ae26b0b998.4947.2 +3 -0
  22. runs/Apr21_17-50-57_67ae26b0b998/1650563493.796129/events.out.tfevents.1650563493.67ae26b0b998.4947.5 +3 -0
  23. runs/Apr21_17-50-57_67ae26b0b998/events.out.tfevents.1650563493.67ae26b0b998.4947.4 +3 -0
  24. special_tokens_map.json +1 -0
  25. tokenizer_config.json +1 -0
  26. training_args.bin +3 -0
  27. vocab.json +1 -0
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec2-large-xls-r-300m-kaqchikel
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
+ # wav2vec2-large-xls-r-300m-kaqchikel
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 2.7944
18
+ - Cer: 0.3042
19
+ - Wer: 0.6409
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: 0.0003
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 32
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 200
47
+ - num_epochs: 100
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
54
+ | 8.2725 | 3.56 | 100 | 3.2834 | 1.0 | 1.0 |
55
+ | 3.3088 | 7.14 | 200 | 3.0773 | 1.0 | 1.0 |
56
+ | 3.1588 | 10.7 | 300 | 3.1077 | 1.0 | 1.0 |
57
+ | 3.0761 | 14.28 | 400 | 2.8695 | 0.9655 | 1.0 |
58
+ | 2.1863 | 17.84 | 500 | 1.7030 | 0.4362 | 0.9421 |
59
+ | 1.2297 | 21.42 | 600 | 1.7189 | 0.3418 | 0.7567 |
60
+ | 0.8466 | 24.98 | 700 | 2.0529 | 0.3435 | 0.7656 |
61
+ | 0.5978 | 28.56 | 800 | 1.9337 | 0.3343 | 0.7226 |
62
+ | 0.4197 | 32.14 | 900 | 2.0655 | 0.3228 | 0.7018 |
63
+ | 0.3161 | 35.7 | 1000 | 2.1808 | 0.3265 | 0.7033 |
64
+ | 0.2511 | 39.28 | 1100 | 2.2830 | 0.3284 | 0.6973 |
65
+ | 0.199 | 42.84 | 1200 | 2.3076 | 0.3181 | 0.6810 |
66
+ | 0.1828 | 46.42 | 1300 | 2.5238 | 0.3123 | 0.6409 |
67
+ | 0.1536 | 49.98 | 1400 | 2.3768 | 0.3123 | 0.6736 |
68
+ | 0.1305 | 53.56 | 1500 | 2.4302 | 0.3139 | 0.6617 |
69
+ | 0.1221 | 57.14 | 1600 | 2.4143 | 0.3134 | 0.6588 |
70
+ | 0.1077 | 60.7 | 1700 | 2.5522 | 0.3095 | 0.6513 |
71
+ | 0.0942 | 64.28 | 1800 | 2.5287 | 0.3053 | 0.6528 |
72
+ | 0.0809 | 67.84 | 1900 | 2.6239 | 0.3075 | 0.6350 |
73
+ | 0.0735 | 71.42 | 2000 | 2.6427 | 0.3036 | 0.6261 |
74
+ | 0.0696 | 74.98 | 2100 | 2.7212 | 0.3145 | 0.6484 |
75
+ | 0.0606 | 78.56 | 2200 | 2.6362 | 0.3178 | 0.6543 |
76
+ | 0.0545 | 82.14 | 2300 | 2.6754 | 0.3084 | 0.6365 |
77
+ | 0.0505 | 85.7 | 2400 | 2.7123 | 0.3111 | 0.6380 |
78
+ | 0.0465 | 89.28 | 2500 | 2.7157 | 0.3125 | 0.6291 |
79
+ | 0.0427 | 92.84 | 2600 | 2.8010 | 0.3078 | 0.6320 |
80
+ | 0.0429 | 96.42 | 2700 | 2.7976 | 0.3067 | 0.6395 |
81
+ | 0.0384 | 99.98 | 2800 | 2.7944 | 0.3042 | 0.6409 |
82
+
83
+
84
+ ### Framework versions
85
+
86
+ - Transformers 4.11.3
87
+ - Pytorch 1.10.0+cu111
88
+ - Datasets 2.1.0
89
+ - Tokenizers 0.10.3
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 41, "</s>": 42}
config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForCTC"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "codevector_dim": 768,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": true,
14
+ "conv_dim": [
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "conv_kernel": [
24
+ 10,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 3,
29
+ 2,
30
+ 2
31
+ ],
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "ctc_loss_reduction": "mean",
42
+ "ctc_zero_infinity": true,
43
+ "diversity_loss_weight": 0.1,
44
+ "do_stable_layer_norm": true,
45
+ "eos_token_id": 2,
46
+ "feat_extract_activation": "gelu",
47
+ "feat_extract_dropout": 0.0,
48
+ "feat_extract_norm": "layer",
49
+ "feat_proj_dropout": 0.0,
50
+ "feat_quantizer_dropout": 0.0,
51
+ "final_dropout": 0.0,
52
+ "gradient_checkpointing": false,
53
+ "hidden_act": "gelu",
54
+ "hidden_dropout": 0.0,
55
+ "hidden_size": 1024,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 4096,
58
+ "layer_norm_eps": 1e-05,
59
+ "layerdrop": 0.0,
60
+ "mask_feature_length": 10,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_prob": 0.05,
64
+ "model_type": "wav2vec2",
65
+ "num_attention_heads": 16,
66
+ "num_codevector_groups": 2,
67
+ "num_codevectors_per_group": 320,
68
+ "num_conv_pos_embedding_groups": 16,
69
+ "num_conv_pos_embeddings": 128,
70
+ "num_feat_extract_layers": 7,
71
+ "num_hidden_layers": 24,
72
+ "num_negatives": 100,
73
+ "pad_token_id": 40,
74
+ "proj_codevector_dim": 768,
75
+ "torch_dtype": "float32",
76
+ "transformers_version": "4.11.3",
77
+ "use_weighted_layer_sum": false,
78
+ "vocab_size": 43
79
+ }
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": true,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3214e3a78df562de8e26f41e1614f2f0a0276682720647dbb9f7557bd72ee39c
3
+ size 1262099953
runs/Apr14_17-13-58_ea396a5a3c34/1649956485.637141/events.out.tfevents.1649956485.ea396a5a3c34.86.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b9b76170df495d5a7693b29b7defcbbce8510e59f10bb7b3c3d4a24d05cc54
3
+ size 4570
runs/Apr14_17-13-58_ea396a5a3c34/events.out.tfevents.1649956485.ea396a5a3c34.86.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd3f85331b98f8f2a16be59983479d138618b7087e7e7aa2c78ccb41261b2d6
3
+ size 5528
runs/Apr21_12-07-05_67ae26b0b998/1650542905.282875/events.out.tfevents.1650542905.67ae26b0b998.80.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9083de2af7dc0d017d04246baa079e2ff43e5630e2a25e433d629d1628ac801
3
+ size 4570
runs/Apr21_12-07-05_67ae26b0b998/events.out.tfevents.1650542905.67ae26b0b998.80.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caadb38ebd00e19c709a9b11507fcd20fedfb21a9c6a7a80d49edfbdceb02510
3
+ size 5154
runs/Apr21_12-37-00_67ae26b0b998/1650544811.2666936/events.out.tfevents.1650544811.67ae26b0b998.80.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e05c5462bc94f0897bad13650cad59f31a0f82654e40f41025041134a89a8f7
3
+ size 4570
runs/Apr21_12-37-00_67ae26b0b998/events.out.tfevents.1650544811.67ae26b0b998.80.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c527bb3ac8e53af05c819057eecdd00eaf33972747d81f7128eb548eb1465df5
3
+ size 4688
runs/Apr21_12-45-40_67ae26b0b998/1650545219.9652703/events.out.tfevents.1650545219.67ae26b0b998.80.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8a98791443ad88ed35f10c1145de387a6a476b87b68a34f70b3b88a4077efb9
3
+ size 4570
runs/Apr21_12-45-40_67ae26b0b998/1650545281.8778462/events.out.tfevents.1650545281.67ae26b0b998.80.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c8e27e47e07e76dcdc0d73ee2590d21f948464ce58c9adf9b00bfd477130ed5
3
+ size 4570
runs/Apr21_12-45-40_67ae26b0b998/events.out.tfevents.1650545219.67ae26b0b998.80.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:840ab80e555bac53503f4aa1690e72e7ce5de4b978b898aebafd395c4786b9bb
3
+ size 4221
runs/Apr21_12-45-40_67ae26b0b998/events.out.tfevents.1650545281.67ae26b0b998.80.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d2b52000d061d88ea4881ec66532dc15c8f2c6e7ecd4cc3ea8980f0d4381d6
3
+ size 4221
runs/Apr21_12-51-48_67ae26b0b998/1650545551.2196941/events.out.tfevents.1650545551.67ae26b0b998.4446.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1ea9f503c1a446b65786e6a771cacd0c525901e70d2d92c26d070a80a474da2
3
+ size 4570
runs/Apr21_12-51-48_67ae26b0b998/events.out.tfevents.1650545551.67ae26b0b998.4446.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:358a01b8c145ae335c06c87123ce01dbc0d8d36dd5a966cdbe98c16044879a80
3
+ size 7528
runs/Apr21_15-55-28_67ae26b0b998/1650556558.152829/events.out.tfevents.1650556558.67ae26b0b998.4947.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a3a0118937a6695c7822259a46d4b4932446ee396c36d3213bc22f932dc7787
3
+ size 4570
runs/Apr21_15-55-28_67ae26b0b998/events.out.tfevents.1650556558.67ae26b0b998.4947.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67d38bca79eeefed1c31582515ec8999e8d8f6d5312aaf7a0b55bf175b1078da
3
+ size 5153
runs/Apr21_16-05-04_67ae26b0b998/1650557137.9502409/events.out.tfevents.1650557137.67ae26b0b998.4947.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7743d9a2dfc35840e66fa67b8c4aac9152732a0799eb4779395a16874b313e9e
3
+ size 4570
runs/Apr21_16-05-04_67ae26b0b998/events.out.tfevents.1650557137.67ae26b0b998.4947.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5f76aad23691264be9ac11400f980557b10988930ab78958beaf94228e101f
3
+ size 16039
runs/Apr21_17-50-57_67ae26b0b998/1650563493.796129/events.out.tfevents.1650563493.67ae26b0b998.4947.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c631b7d69142626fabb48efeb39aad2beb040ce17333e68e55280b3bcbca8b0
3
+ size 4570
runs/Apr21_17-50-57_67ae26b0b998/events.out.tfevents.1650563493.67ae26b0b998.4947.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d77bce2dcaeae2c0929102fdc56d362157d923921514c6df71c9ac54fd6b0937
3
+ size 19184
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b1f442364671a9d9696d575f2424d0ff8be67c429a0827edf24dcd8e523568
3
+ size 2863
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "á": 27, "ä": 28, "é": 29, "ë": 30, "í": 31, "ï": 32, "ñ": 33, "ó": 34, "ö": 35, "ú": 36, "ü": 37, "’": 38, "|": 0, "[UNK]": 39, "[PAD]": 40}