ayymen commited on
Commit
1fda542
·
verified ·
1 Parent(s): 2899e8c

Upload folder using huggingface_hub

Browse files
Files changed (44) hide show
  1. README.md +141 -0
  2. adapter.hau.safetensors +3 -0
  3. added_tokens.json +4 -0
  4. all_results.json +16 -0
  5. checkpoint-35500/added_tokens.json +4 -0
  6. checkpoint-35500/config.json +108 -0
  7. checkpoint-35500/model.safetensors +3 -0
  8. checkpoint-35500/optimizer.pt +3 -0
  9. checkpoint-35500/preprocessor_config.json +10 -0
  10. checkpoint-35500/rng_state_0.pth +3 -0
  11. checkpoint-35500/rng_state_1.pth +3 -0
  12. checkpoint-35500/scheduler.pt +3 -0
  13. checkpoint-35500/special_tokens_map.json +30 -0
  14. checkpoint-35500/tokenizer_config.json +49 -0
  15. checkpoint-35500/trainer_state.json +0 -0
  16. checkpoint-35500/training_args.bin +3 -0
  17. checkpoint-35500/vocab.json +103 -0
  18. checkpoint-35796/added_tokens.json +4 -0
  19. checkpoint-35796/config.json +108 -0
  20. checkpoint-35796/model.safetensors +3 -0
  21. checkpoint-35796/optimizer.pt +3 -0
  22. checkpoint-35796/preprocessor_config.json +10 -0
  23. checkpoint-35796/rng_state_0.pth +3 -0
  24. checkpoint-35796/rng_state_1.pth +3 -0
  25. checkpoint-35796/scheduler.pt +3 -0
  26. checkpoint-35796/special_tokens_map.json +30 -0
  27. checkpoint-35796/tokenizer_config.json +49 -0
  28. checkpoint-35796/trainer_state.json +0 -0
  29. checkpoint-35796/training_args.bin +3 -0
  30. checkpoint-35796/vocab.json +103 -0
  31. cmd.sh +27 -0
  32. config.json +108 -0
  33. eval_results.json +10 -0
  34. model.safetensors +3 -0
  35. preprocessor_config.json +10 -0
  36. runs/Mar13_14-46-02_gmy/events.out.tfevents.1741871146.gmy.21769.0 +3 -0
  37. runs/Mar13_20-53-06_gmy/events.out.tfevents.1741893192.gmy.53002.0 +3 -0
  38. runs/Mar13_20-53-06_gmy/events.out.tfevents.1741941775.gmy.53002.1 +3 -0
  39. special_tokens_map.json +30 -0
  40. tokenizer_config.json +49 -0
  41. train_results.json +9 -0
  42. trainer_state.json +0 -0
  43. training_args.bin +3 -0
  44. vocab.json +103 -0
README.md ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: facebook/mms-1b-all
4
+ tags:
5
+ - automatic-speech-recognition
6
+ - /mnt/md0/synvoices/data/naijavoices_500h
7
+ - mms
8
+ - generated_from_trainer
9
+ metrics:
10
+ - wer
11
+ model-index:
12
+ - name: mms-1b-naijavoices_500h-hau-ft
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # mms-1b-naijavoices_500h-hau-ft
20
+
21
+ This model is a fine-tuned version of [./training_runs/mms-1b-naijavoices_500h-hau-ft/checkpoint-5000](https://huggingface.co/./training_runs/mms-1b-naijavoices_500h-hau-ft/checkpoint-5000) on the /MNT/MD0/SYNVOICES/DATA/NAIJAVOICES_500H - NA dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.3121
24
+ - Wer: 0.3303
25
+ - Cer: 0.0830
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 0.001
45
+ - train_batch_size: 8
46
+ - eval_batch_size: 8
47
+ - seed: 42
48
+ - distributed_type: multi-GPU
49
+ - num_devices: 2
50
+ - gradient_accumulation_steps: 2
51
+ - total_train_batch_size: 32
52
+ - total_eval_batch_size: 16
53
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
54
+ - lr_scheduler_type: linear
55
+ - lr_scheduler_warmup_steps: 100
56
+ - num_epochs: 2.0
57
+ - mixed_precision_training: Native AMP
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
62
+ |:-------------:|:------:|:-----:|:------:|:---------------:|:------:|
63
+ | 0.5183 | 0.0279 | 500 | 0.1051 | 0.3932 | 0.4076 |
64
+ | 0.4379 | 0.0559 | 1000 | 0.1009 | 0.3776 | 0.3964 |
65
+ | 0.5709 | 0.0838 | 1500 | 0.1001 | 0.3829 | 0.3935 |
66
+ | 0.6257 | 0.1117 | 2000 | 0.0994 | 0.3710 | 0.3930 |
67
+ | 0.5065 | 0.1397 | 2500 | 0.1008 | 0.3796 | 0.3937 |
68
+ | 0.4613 | 0.1676 | 3000 | 0.0977 | 0.3637 | 0.3849 |
69
+ | 0.5305 | 0.1955 | 3500 | 0.0971 | 0.3674 | 0.3801 |
70
+ | 0.4303 | 0.2235 | 4000 | 0.0980 | 0.3663 | 0.3875 |
71
+ | 0.6497 | 0.2514 | 4500 | 0.0959 | 0.3617 | 0.3741 |
72
+ | 0.3887 | 0.2794 | 5000 | 0.0985 | 0.3620 | 0.3925 |
73
+ | 0.4604 | 0.3073 | 5500 | 0.3570 | 0.3727 | 0.0947 |
74
+ | 0.4349 | 0.3352 | 6000 | 0.3529 | 0.3686 | 0.0940 |
75
+ | 0.5403 | 0.3632 | 6500 | 0.3518 | 0.3722 | 0.0941 |
76
+ | 0.4455 | 0.3911 | 7000 | 0.3522 | 0.3695 | 0.0937 |
77
+ | 0.4454 | 0.4190 | 7500 | 0.3527 | 0.3722 | 0.0941 |
78
+ | 0.3582 | 0.4470 | 8000 | 0.3479 | 0.3696 | 0.0932 |
79
+ | 0.6661 | 0.4749 | 8500 | 0.3453 | 0.3597 | 0.0911 |
80
+ | 0.4702 | 0.5028 | 9000 | 0.3472 | 0.3672 | 0.0929 |
81
+ | 0.3877 | 0.5308 | 9500 | 0.3467 | 0.3772 | 0.0952 |
82
+ | 0.5848 | 0.5587 | 10000 | 0.3422 | 0.3652 | 0.0920 |
83
+ | 0.4943 | 0.5866 | 10500 | 0.3444 | 0.3701 | 0.0926 |
84
+ | 0.5451 | 0.6146 | 11000 | 0.3441 | 0.3583 | 0.0908 |
85
+ | 0.4033 | 0.6425 | 11500 | 0.3424 | 0.3572 | 0.0907 |
86
+ | 0.4437 | 0.6704 | 12000 | 0.3427 | 0.3576 | 0.0906 |
87
+ | 0.4541 | 0.6984 | 12500 | 0.3375 | 0.3574 | 0.0901 |
88
+ | 0.3769 | 0.7263 | 13000 | 0.3381 | 0.3605 | 0.0901 |
89
+ | 0.3915 | 0.7543 | 13500 | 0.3357 | 0.3538 | 0.0892 |
90
+ | 0.5068 | 0.7822 | 14000 | 0.3373 | 0.3518 | 0.0892 |
91
+ | 0.3922 | 0.8101 | 14500 | 0.3362 | 0.3556 | 0.0895 |
92
+ | 0.3928 | 0.8381 | 15000 | 0.3337 | 0.3489 | 0.0887 |
93
+ | 0.487 | 0.8660 | 15500 | 0.3350 | 0.3580 | 0.0897 |
94
+ | 0.3974 | 0.8939 | 16000 | 0.3330 | 0.3545 | 0.0892 |
95
+ | 0.3988 | 0.9219 | 16500 | 0.3339 | 0.3468 | 0.0880 |
96
+ | 0.5077 | 0.9498 | 17000 | 0.3322 | 0.3529 | 0.0884 |
97
+ | 0.4159 | 0.9777 | 17500 | 0.3320 | 0.3509 | 0.0885 |
98
+ | 0.46 | 1.0057 | 18000 | 0.3313 | 0.3469 | 0.0881 |
99
+ | 0.4727 | 1.0336 | 18500 | 0.3320 | 0.3588 | 0.0893 |
100
+ | 0.5366 | 1.0616 | 19000 | 0.3292 | 0.3519 | 0.0891 |
101
+ | 0.7299 | 1.0895 | 19500 | 0.3292 | 0.3518 | 0.0882 |
102
+ | 0.4359 | 1.1174 | 20000 | 0.3292 | 0.3470 | 0.0872 |
103
+ | 0.4212 | 1.1454 | 20500 | 0.3266 | 0.3449 | 0.0873 |
104
+ | 0.4532 | 1.1733 | 21000 | 0.3264 | 0.3443 | 0.0868 |
105
+ | 0.5725 | 1.2012 | 21500 | 0.3264 | 0.3393 | 0.0857 |
106
+ | 0.4016 | 1.2292 | 22000 | 0.3249 | 0.3398 | 0.0861 |
107
+ | 0.4479 | 1.2571 | 22500 | 0.3243 | 0.3519 | 0.0875 |
108
+ | 0.3502 | 1.2851 | 23000 | 0.3253 | 0.3463 | 0.0867 |
109
+ | 0.4566 | 1.3130 | 23500 | 0.3207 | 0.3387 | 0.0854 |
110
+ | 0.4414 | 1.3409 | 24000 | 0.3218 | 0.3431 | 0.0858 |
111
+ | 0.4479 | 1.3689 | 24500 | 0.3243 | 0.3445 | 0.0864 |
112
+ | 0.4601 | 1.3968 | 25000 | 0.3197 | 0.3405 | 0.0858 |
113
+ | 0.4091 | 1.4247 | 25500 | 0.3219 | 0.3371 | 0.0851 |
114
+ | 0.3548 | 1.4527 | 26000 | 0.3207 | 0.3417 | 0.0856 |
115
+ | 0.4587 | 1.4806 | 26500 | 0.3183 | 0.3360 | 0.0851 |
116
+ | 0.51 | 1.5085 | 27000 | 0.3196 | 0.3393 | 0.0853 |
117
+ | 0.4705 | 1.5365 | 27500 | 0.3187 | 0.3382 | 0.0853 |
118
+ | 0.5046 | 1.5644 | 28000 | 0.3194 | 0.3337 | 0.0843 |
119
+ | 0.4924 | 1.5923 | 28500 | 0.3149 | 0.3327 | 0.0840 |
120
+ | 0.3216 | 1.6203 | 29000 | 0.3173 | 0.3395 | 0.0850 |
121
+ | 0.4593 | 1.6482 | 29500 | 0.3156 | 0.3297 | 0.0833 |
122
+ | 0.3163 | 1.6761 | 30000 | 0.3141 | 0.3355 | 0.0843 |
123
+ | 0.3492 | 1.7041 | 30500 | 0.3147 | 0.3337 | 0.0840 |
124
+ | 0.4529 | 1.7320 | 31000 | 0.3150 | 0.3363 | 0.0843 |
125
+ | 0.2976 | 1.7600 | 31500 | 0.3149 | 0.3320 | 0.0838 |
126
+ | 0.3691 | 1.7879 | 32000 | 0.3141 | 0.3313 | 0.0836 |
127
+ | 0.3154 | 1.8158 | 32500 | 0.3128 | 0.3296 | 0.0831 |
128
+ | 0.429 | 1.8438 | 33000 | 0.3134 | 0.3346 | 0.0841 |
129
+ | 0.3474 | 1.8717 | 33500 | 0.3136 | 0.3311 | 0.0836 |
130
+ | 0.4074 | 1.8996 | 34000 | 0.3130 | 0.3318 | 0.0832 |
131
+ | 0.3559 | 1.9276 | 34500 | 0.3123 | 0.3334 | 0.0835 |
132
+ | 0.3606 | 1.9555 | 35000 | 0.3119 | 0.3318 | 0.0834 |
133
+ | 0.4125 | 1.9834 | 35500 | 0.3123 | 0.3301 | 0.0830 |
134
+
135
+
136
+ ### Framework versions
137
+
138
+ - Transformers 4.48.1
139
+ - Pytorch 2.5.1+cu121
140
+ - Datasets 3.2.0
141
+ - Tokenizers 0.21.0
adapter.hau.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f873b6a456a3041f425e4bd9eebb8c6dba6d3eea13dc4f728988ba665baf22aa
3
+ size 9157244
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 100,
3
+ "<s>": 99
4
+ }
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.999972064698159,
3
+ "eval_cer": 0.08301965020239381,
4
+ "eval_loss": 0.3121410012245178,
5
+ "eval_runtime": 55.4824,
6
+ "eval_samples": 4538,
7
+ "eval_samples_per_second": 81.792,
8
+ "eval_steps_per_second": 5.119,
9
+ "eval_wer": 0.3302701041870339,
10
+ "total_flos": 5.8041710762050716e+20,
11
+ "train_loss": 0.3785943881215057,
12
+ "train_runtime": 48523.5238,
13
+ "train_samples": 572742,
14
+ "train_samples_per_second": 23.607,
15
+ "train_steps_per_second": 0.738
16
+ }
checkpoint-35500/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 100,
3
+ "<s>": 99
4
+ }
checkpoint-35500/config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./training_runs/mms-1b-naijavoices_500h-hau-ft/checkpoint-5000",
3
+ "activation_dropout": 0.05,
4
+ "adapter_attn_dim": 16,
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": 0.05,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 1024,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
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": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.05,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.05,
58
+ "hidden_size": 1280,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 5120,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.0,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 48,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1280,
80
+ "pad_token_id": 98,
81
+ "proj_codevector_dim": 1024,
82
+ "tdnn_dilation": [
83
+ 1,
84
+ 2,
85
+ 3,
86
+ 1,
87
+ 1
88
+ ],
89
+ "tdnn_dim": [
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 1500
95
+ ],
96
+ "tdnn_kernel": [
97
+ 5,
98
+ 3,
99
+ 3,
100
+ 1,
101
+ 1
102
+ ],
103
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.48.1",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 101,
107
+ "xvector_output_dim": 512
108
+ }
checkpoint-35500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c40c05cbe67d8be8e6bf5d34235315504c3f43af1543f5e1d9d545c1d9335f1
3
+ size 3859249604
checkpoint-35500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a3ea2b0e62437b70de749071a4917ea7a955064e2a3e2c90790a2137569131
3
+ size 18489786
checkpoint-35500/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,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
checkpoint-35500/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61308a4e1f44d2dfd65d2a470ac42f4492cdc5d39fbeff96782a78ecdcf3173b
3
+ size 14512
checkpoint-35500/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af4e84bf1ab4f7c9ca3300d123be6f0d1a79d0ab71cf5fc9627bf859b60855b
3
+ size 14576
checkpoint-35500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a812b6694a9c1ed3776f81d6c14c6c060cbc4942eabe19623b81b2f94031d00e
3
+ size 1064
checkpoint-35500/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-35500/tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "97": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "98": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "99": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
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": false,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "[PAD]",
43
+ "processor_class": "Wav2Vec2Processor",
44
+ "replace_word_delimiter_char": " ",
45
+ "target_lang": "hau",
46
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
47
+ "unk_token": "[UNK]",
48
+ "word_delimiter_token": "|"
49
+ }
checkpoint-35500/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-35500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c651b72a39453bdafd381a6f2e7b5741e38afd8690278b50637e37501127794
3
+ size 5432
checkpoint-35500/vocab.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "hau": {
3
+ "$": 1,
4
+ "%": 2,
5
+ "&": 3,
6
+ "'": 4,
7
+ "*": 5,
8
+ "+": 6,
9
+ "-": 7,
10
+ "/": 8,
11
+ "0": 9,
12
+ "1": 10,
13
+ "2": 11,
14
+ "3": 12,
15
+ "4": 13,
16
+ "5": 14,
17
+ "6": 15,
18
+ "7": 16,
19
+ "8": 17,
20
+ "9": 18,
21
+ "=": 19,
22
+ ">": 20,
23
+ "@": 21,
24
+ "[PAD]": 98,
25
+ "[UNK]": 97,
26
+ "\\": 22,
27
+ "_": 23,
28
+ "`": 24,
29
+ "a": 25,
30
+ "b": 26,
31
+ "c": 27,
32
+ "d": 28,
33
+ "e": 29,
34
+ "f": 30,
35
+ "g": 31,
36
+ "h": 32,
37
+ "i": 33,
38
+ "j": 34,
39
+ "k": 35,
40
+ "l": 36,
41
+ "m": 37,
42
+ "n": 38,
43
+ "o": 39,
44
+ "p": 40,
45
+ "q": 41,
46
+ "r": 42,
47
+ "s": 43,
48
+ "t": 44,
49
+ "u": 45,
50
+ "v": 46,
51
+ "w": 47,
52
+ "x": 48,
53
+ "y": 49,
54
+ "z": 50,
55
+ "|": 0,
56
+ "à": 51,
57
+ "á": 52,
58
+ "â": 53,
59
+ "ã": 54,
60
+ "è": 55,
61
+ "é": 56,
62
+ "ì": 57,
63
+ "í": 58,
64
+ "ñ": 59,
65
+ "ò": 60,
66
+ "ó": 61,
67
+ "ô": 62,
68
+ "õ": 63,
69
+ "ù": 64,
70
+ "ú": 65,
71
+ "ü": 66,
72
+ "ý": 67,
73
+ "ā": 68,
74
+ "ď": 69,
75
+ "ē": 70,
76
+ "ğ": 71,
77
+ "ı": 72,
78
+ "ķ": 73,
79
+ "ń": 74,
80
+ "ō": 75,
81
+ "ş": 76,
82
+ "š": 77,
83
+ "ũ": 78,
84
+ "ū": 79,
85
+ "ŭ": 80,
86
+ "ž": 81,
87
+ "ƙ": 82,
88
+ "ƴ": 83,
89
+ "ǹ": 84,
90
+ "ɓ": 85,
91
+ "ɗ": 86,
92
+ "ʼ": 87,
93
+ "̀": 88,
94
+ "ṣ": 89,
95
+ "ẹ": 90,
96
+ "ọ": 91,
97
+ "—": 92,
98
+ "‘": 93,
99
+ "’": 94,
100
+ "…": 95,
101
+ "₦": 96
102
+ }
103
+ }
checkpoint-35796/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 100,
3
+ "<s>": 99
4
+ }
checkpoint-35796/config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./training_runs/mms-1b-naijavoices_500h-hau-ft/checkpoint-5000",
3
+ "activation_dropout": 0.05,
4
+ "adapter_attn_dim": 16,
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": 0.05,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 1024,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
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": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.05,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.05,
58
+ "hidden_size": 1280,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 5120,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.0,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 48,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1280,
80
+ "pad_token_id": 98,
81
+ "proj_codevector_dim": 1024,
82
+ "tdnn_dilation": [
83
+ 1,
84
+ 2,
85
+ 3,
86
+ 1,
87
+ 1
88
+ ],
89
+ "tdnn_dim": [
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 1500
95
+ ],
96
+ "tdnn_kernel": [
97
+ 5,
98
+ 3,
99
+ 3,
100
+ 1,
101
+ 1
102
+ ],
103
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.48.1",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 101,
107
+ "xvector_output_dim": 512
108
+ }
checkpoint-35796/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b762c4e1f2a680ac3d27b66063703a3b4b22717e9298c9f0cbb52a411a9f92
3
+ size 3859249604
checkpoint-35796/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db2b98cb3060f3520ff69b273e6dcd6897f95f2b7f2fd55cc2c4e7792d329b16
3
+ size 18489786
checkpoint-35796/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,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
checkpoint-35796/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf602b9e97a3af0f2ccb3ef4e577eaf113f499ff88a23fff00416e7e40293534
3
+ size 14512
checkpoint-35796/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79219cf9f7e7918222038207daa4441107166ba33f7f8b167aaeed38c7c74917
3
+ size 14512
checkpoint-35796/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c813c37ff4a83862abc6fc7426fbb2f1027db556b854d2356f023c0b0496b7
3
+ size 1064
checkpoint-35796/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-35796/tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "97": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "98": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "99": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
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": false,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "[PAD]",
43
+ "processor_class": "Wav2Vec2Processor",
44
+ "replace_word_delimiter_char": " ",
45
+ "target_lang": "hau",
46
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
47
+ "unk_token": "[UNK]",
48
+ "word_delimiter_token": "|"
49
+ }
checkpoint-35796/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-35796/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c651b72a39453bdafd381a6f2e7b5741e38afd8690278b50637e37501127794
3
+ size 5432
checkpoint-35796/vocab.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "hau": {
3
+ "$": 1,
4
+ "%": 2,
5
+ "&": 3,
6
+ "'": 4,
7
+ "*": 5,
8
+ "+": 6,
9
+ "-": 7,
10
+ "/": 8,
11
+ "0": 9,
12
+ "1": 10,
13
+ "2": 11,
14
+ "3": 12,
15
+ "4": 13,
16
+ "5": 14,
17
+ "6": 15,
18
+ "7": 16,
19
+ "8": 17,
20
+ "9": 18,
21
+ "=": 19,
22
+ ">": 20,
23
+ "@": 21,
24
+ "[PAD]": 98,
25
+ "[UNK]": 97,
26
+ "\\": 22,
27
+ "_": 23,
28
+ "`": 24,
29
+ "a": 25,
30
+ "b": 26,
31
+ "c": 27,
32
+ "d": 28,
33
+ "e": 29,
34
+ "f": 30,
35
+ "g": 31,
36
+ "h": 32,
37
+ "i": 33,
38
+ "j": 34,
39
+ "k": 35,
40
+ "l": 36,
41
+ "m": 37,
42
+ "n": 38,
43
+ "o": 39,
44
+ "p": 40,
45
+ "q": 41,
46
+ "r": 42,
47
+ "s": 43,
48
+ "t": 44,
49
+ "u": 45,
50
+ "v": 46,
51
+ "w": 47,
52
+ "x": 48,
53
+ "y": 49,
54
+ "z": 50,
55
+ "|": 0,
56
+ "à": 51,
57
+ "á": 52,
58
+ "â": 53,
59
+ "ã": 54,
60
+ "è": 55,
61
+ "é": 56,
62
+ "ì": 57,
63
+ "í": 58,
64
+ "ñ": 59,
65
+ "ò": 60,
66
+ "ó": 61,
67
+ "ô": 62,
68
+ "õ": 63,
69
+ "ù": 64,
70
+ "ú": 65,
71
+ "ü": 66,
72
+ "ý": 67,
73
+ "ā": 68,
74
+ "ď": 69,
75
+ "ē": 70,
76
+ "ğ": 71,
77
+ "ı": 72,
78
+ "ķ": 73,
79
+ "ń": 74,
80
+ "ō": 75,
81
+ "ş": 76,
82
+ "š": 77,
83
+ "ũ": 78,
84
+ "ū": 79,
85
+ "ŭ": 80,
86
+ "ž": 81,
87
+ "ƙ": 82,
88
+ "ƴ": 83,
89
+ "ǹ": 84,
90
+ "ɓ": 85,
91
+ "ɗ": 86,
92
+ "ʼ": 87,
93
+ "̀": 88,
94
+ "ṣ": 89,
95
+ "ẹ": 90,
96
+ "ọ": 91,
97
+ "—": 92,
98
+ "‘": 93,
99
+ "’": 94,
100
+ "…": 95,
101
+ "₦": 96
102
+ }
103
+ }
cmd.sh ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ torchrun \
2
+ --nproc_per_node 2 run_speech_recognition_ctc_adapter.py \
3
+ --model_name_or_path="facebook/mms-1b-all" \
4
+ --dataset_name="/mnt/md0/synvoices/data/naijavoices_500h" \
5
+ --train_split_name="train" \
6
+ --eval_split_name="validation" \
7
+ --output_dir="./training_runs/mms-1b-naijavoices_500h-hau-ft" \
8
+ --num_train_epochs="2" \
9
+ --per_device_train_batch_size="8" \
10
+ --per_device_eval_batch_size="8" \
11
+ --gradient_accumulation_steps="2" \
12
+ --learning_rate="1e-3" \
13
+ --warmup_steps="100" \
14
+ --eval_strategy="steps" \
15
+ --save_steps="500" \
16
+ --eval_steps="500" \
17
+ --logging_steps="1" \
18
+ --eval_metrics wer cer \
19
+ --save_total_limit="2" \
20
+ --max_duration_in_seconds="30" \
21
+ --target_language="hau" \
22
+ --overwrite_lang_vocab \
23
+ --gradient_checkpointing \
24
+ --fp16 \
25
+ --do_train --do_eval \
26
+ --preprocessing_num_workers="12" \
27
+ --dataloader_num_workers="12"
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mms-1b-all",
3
+ "activation_dropout": 0.05,
4
+ "adapter_attn_dim": 16,
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": 0.05,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 1024,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
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": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.05,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.05,
58
+ "hidden_size": 1280,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 5120,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.0,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 48,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1280,
80
+ "pad_token_id": 98,
81
+ "proj_codevector_dim": 1024,
82
+ "tdnn_dilation": [
83
+ 1,
84
+ 2,
85
+ 3,
86
+ 1,
87
+ 1
88
+ ],
89
+ "tdnn_dim": [
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 1500
95
+ ],
96
+ "tdnn_kernel": [
97
+ 5,
98
+ 3,
99
+ 3,
100
+ 1,
101
+ 1
102
+ ],
103
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.48.1",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 101,
107
+ "xvector_output_dim": 512
108
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.999972064698159,
3
+ "eval_cer": 0.08301965020239381,
4
+ "eval_loss": 0.3121410012245178,
5
+ "eval_runtime": 55.4824,
6
+ "eval_samples": 4538,
7
+ "eval_samples_per_second": 81.792,
8
+ "eval_steps_per_second": 5.119,
9
+ "eval_wer": 0.3302701041870339
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b762c4e1f2a680ac3d27b66063703a3b4b22717e9298c9f0cbb52a411a9f92
3
+ size 3859249604
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,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
runs/Mar13_14-46-02_gmy/events.out.tfevents.1741871146.gmy.21769.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25b41411f63c0f6201ec87617bb5bfea2d6c78b9138a68d90085529900daa76a
3
+ size 1154975
runs/Mar13_20-53-06_gmy/events.out.tfevents.1741893192.gmy.53002.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5fac722c3cef71df95ece3cd30cc87aa7993eceeee4cac6134eafb0a078f155
3
+ size 6605134
runs/Mar13_20-53-06_gmy/events.out.tfevents.1741941775.gmy.53002.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3cc91f27baa1956244c9a87e3c9a0fa8d53b958fe796e1fffaf47e7405fcbae
3
+ size 460
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "97": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "98": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "99": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
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": false,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "[PAD]",
43
+ "processor_class": "Wav2Vec2Processor",
44
+ "replace_word_delimiter_char": " ",
45
+ "target_lang": "hau",
46
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
47
+ "unk_token": "[UNK]",
48
+ "word_delimiter_token": "|"
49
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.999972064698159,
3
+ "total_flos": 5.8041710762050716e+20,
4
+ "train_loss": 0.3785943881215057,
5
+ "train_runtime": 48523.5238,
6
+ "train_samples": 572742,
7
+ "train_samples_per_second": 23.607,
8
+ "train_steps_per_second": 0.738
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c651b72a39453bdafd381a6f2e7b5741e38afd8690278b50637e37501127794
3
+ size 5432
vocab.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "hau": {
3
+ "$": 1,
4
+ "%": 2,
5
+ "&": 3,
6
+ "'": 4,
7
+ "*": 5,
8
+ "+": 6,
9
+ "-": 7,
10
+ "/": 8,
11
+ "0": 9,
12
+ "1": 10,
13
+ "2": 11,
14
+ "3": 12,
15
+ "4": 13,
16
+ "5": 14,
17
+ "6": 15,
18
+ "7": 16,
19
+ "8": 17,
20
+ "9": 18,
21
+ "=": 19,
22
+ ">": 20,
23
+ "@": 21,
24
+ "[PAD]": 98,
25
+ "[UNK]": 97,
26
+ "\\": 22,
27
+ "_": 23,
28
+ "`": 24,
29
+ "a": 25,
30
+ "b": 26,
31
+ "c": 27,
32
+ "d": 28,
33
+ "e": 29,
34
+ "f": 30,
35
+ "g": 31,
36
+ "h": 32,
37
+ "i": 33,
38
+ "j": 34,
39
+ "k": 35,
40
+ "l": 36,
41
+ "m": 37,
42
+ "n": 38,
43
+ "o": 39,
44
+ "p": 40,
45
+ "q": 41,
46
+ "r": 42,
47
+ "s": 43,
48
+ "t": 44,
49
+ "u": 45,
50
+ "v": 46,
51
+ "w": 47,
52
+ "x": 48,
53
+ "y": 49,
54
+ "z": 50,
55
+ "|": 0,
56
+ "à": 51,
57
+ "á": 52,
58
+ "â": 53,
59
+ "ã": 54,
60
+ "è": 55,
61
+ "é": 56,
62
+ "ì": 57,
63
+ "í": 58,
64
+ "ñ": 59,
65
+ "ò": 60,
66
+ "ó": 61,
67
+ "ô": 62,
68
+ "õ": 63,
69
+ "ù": 64,
70
+ "ú": 65,
71
+ "ü": 66,
72
+ "ý": 67,
73
+ "ā": 68,
74
+ "ď": 69,
75
+ "ē": 70,
76
+ "ğ": 71,
77
+ "ı": 72,
78
+ "ķ": 73,
79
+ "ń": 74,
80
+ "ō": 75,
81
+ "ş": 76,
82
+ "š": 77,
83
+ "ũ": 78,
84
+ "ū": 79,
85
+ "ŭ": 80,
86
+ "ž": 81,
87
+ "ƙ": 82,
88
+ "ƴ": 83,
89
+ "ǹ": 84,
90
+ "ɓ": 85,
91
+ "ɗ": 86,
92
+ "ʼ": 87,
93
+ "̀": 88,
94
+ "ṣ": 89,
95
+ "ẹ": 90,
96
+ "ọ": 91,
97
+ "—": 92,
98
+ "‘": 93,
99
+ "’": 94,
100
+ "…": 95,
101
+ "₦": 96
102
+ }
103
+ }