dmusingu/muk-luganda-digits-classification
Browse files- README.md +136 -0
- config.json +141 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/wav2vec2-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: muk-luganda-digits-classification
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# muk-luganda-digits-classification
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 5.1901
|
| 22 |
+
- Accuracy: 0.2414
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 3e-05
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 75
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 2.304 | 1.0 | 58 | 2.3169 | 0.1034 |
|
| 55 |
+
| 2.2989 | 2.0 | 116 | 2.3166 | 0.0690 |
|
| 56 |
+
| 2.2921 | 3.0 | 174 | 2.3167 | 0.1379 |
|
| 57 |
+
| 2.2843 | 4.0 | 232 | 2.3237 | 0.1034 |
|
| 58 |
+
| 2.2657 | 5.0 | 290 | 2.3195 | 0.0690 |
|
| 59 |
+
| 2.2519 | 6.0 | 348 | 2.2997 | 0.1034 |
|
| 60 |
+
| 2.2187 | 7.0 | 406 | 2.3050 | 0.1034 |
|
| 61 |
+
| 2.15 | 8.0 | 464 | 2.2577 | 0.1034 |
|
| 62 |
+
| 2.0555 | 9.0 | 522 | 2.2375 | 0.1379 |
|
| 63 |
+
| 1.9332 | 10.0 | 580 | 2.2008 | 0.2414 |
|
| 64 |
+
| 1.8073 | 11.0 | 638 | 2.1950 | 0.1724 |
|
| 65 |
+
| 1.6742 | 12.0 | 696 | 2.2654 | 0.1724 |
|
| 66 |
+
| 1.5511 | 13.0 | 754 | 2.1905 | 0.1724 |
|
| 67 |
+
| 1.4453 | 14.0 | 812 | 2.2018 | 0.2069 |
|
| 68 |
+
| 1.3227 | 15.0 | 870 | 2.1572 | 0.2759 |
|
| 69 |
+
| 1.2019 | 16.0 | 928 | 2.4037 | 0.2414 |
|
| 70 |
+
| 1.1151 | 17.0 | 986 | 2.4147 | 0.3103 |
|
| 71 |
+
| 0.9743 | 18.0 | 1044 | 2.3563 | 0.2759 |
|
| 72 |
+
| 0.9336 | 19.0 | 1102 | 2.2765 | 0.3103 |
|
| 73 |
+
| 0.852 | 20.0 | 1160 | 2.3266 | 0.3448 |
|
| 74 |
+
| 0.7096 | 21.0 | 1218 | 2.2129 | 0.4138 |
|
| 75 |
+
| 0.6183 | 22.0 | 1276 | 2.4103 | 0.3103 |
|
| 76 |
+
| 0.6018 | 23.0 | 1334 | 2.8189 | 0.2759 |
|
| 77 |
+
| 0.5155 | 24.0 | 1392 | 2.9791 | 0.2759 |
|
| 78 |
+
| 0.4233 | 25.0 | 1450 | 2.9289 | 0.3103 |
|
| 79 |
+
| 0.4213 | 26.0 | 1508 | 3.2987 | 0.2759 |
|
| 80 |
+
| 0.4613 | 27.0 | 1566 | 3.1643 | 0.3103 |
|
| 81 |
+
| 0.4414 | 28.0 | 1624 | 2.9910 | 0.3448 |
|
| 82 |
+
| 0.4033 | 29.0 | 1682 | 3.2960 | 0.3103 |
|
| 83 |
+
| 0.3761 | 30.0 | 1740 | 3.5232 | 0.2759 |
|
| 84 |
+
| 0.2886 | 31.0 | 1798 | 3.9775 | 0.2414 |
|
| 85 |
+
| 0.3646 | 32.0 | 1856 | 3.4826 | 0.3103 |
|
| 86 |
+
| 0.3371 | 33.0 | 1914 | 3.5032 | 0.3793 |
|
| 87 |
+
| 0.2169 | 34.0 | 1972 | 3.4125 | 0.3448 |
|
| 88 |
+
| 0.2906 | 35.0 | 2030 | 3.3535 | 0.3793 |
|
| 89 |
+
| 0.414 | 36.0 | 2088 | 3.7734 | 0.2069 |
|
| 90 |
+
| 0.2058 | 37.0 | 2146 | 3.7419 | 0.2759 |
|
| 91 |
+
| 0.188 | 38.0 | 2204 | 3.7832 | 0.3103 |
|
| 92 |
+
| 0.2209 | 39.0 | 2262 | 3.6297 | 0.2414 |
|
| 93 |
+
| 0.2403 | 40.0 | 2320 | 3.7870 | 0.3103 |
|
| 94 |
+
| 0.2483 | 41.0 | 2378 | 3.9331 | 0.3448 |
|
| 95 |
+
| 0.2409 | 42.0 | 2436 | 4.1382 | 0.3103 |
|
| 96 |
+
| 0.2415 | 43.0 | 2494 | 4.1796 | 0.2759 |
|
| 97 |
+
| 0.1496 | 44.0 | 2552 | 4.1671 | 0.3448 |
|
| 98 |
+
| 0.1874 | 45.0 | 2610 | 4.5372 | 0.2069 |
|
| 99 |
+
| 0.2092 | 46.0 | 2668 | 4.8994 | 0.2414 |
|
| 100 |
+
| 0.2016 | 47.0 | 2726 | 4.4871 | 0.2414 |
|
| 101 |
+
| 0.259 | 48.0 | 2784 | 4.1237 | 0.2759 |
|
| 102 |
+
| 0.2078 | 49.0 | 2842 | 4.9369 | 0.2414 |
|
| 103 |
+
| 0.1413 | 50.0 | 2900 | 4.9249 | 0.2414 |
|
| 104 |
+
| 0.1453 | 51.0 | 2958 | 5.1858 | 0.2414 |
|
| 105 |
+
| 0.1963 | 52.0 | 3016 | 3.9934 | 0.3103 |
|
| 106 |
+
| 0.2249 | 53.0 | 3074 | 4.2996 | 0.3103 |
|
| 107 |
+
| 0.2058 | 54.0 | 3132 | 3.7626 | 0.3448 |
|
| 108 |
+
| 0.2483 | 55.0 | 3190 | 4.6947 | 0.2759 |
|
| 109 |
+
| 0.209 | 56.0 | 3248 | 4.0701 | 0.3793 |
|
| 110 |
+
| 0.144 | 57.0 | 3306 | 4.5588 | 0.2414 |
|
| 111 |
+
| 0.2093 | 58.0 | 3364 | 4.9072 | 0.3103 |
|
| 112 |
+
| 0.143 | 59.0 | 3422 | 5.1035 | 0.2414 |
|
| 113 |
+
| 0.2102 | 60.0 | 3480 | 5.3840 | 0.2069 |
|
| 114 |
+
| 0.1507 | 61.0 | 3538 | 5.3511 | 0.2414 |
|
| 115 |
+
| 0.1826 | 62.0 | 3596 | 5.0179 | 0.2069 |
|
| 116 |
+
| 0.1407 | 63.0 | 3654 | 5.2103 | 0.1724 |
|
| 117 |
+
| 0.1395 | 64.0 | 3712 | 5.4675 | 0.2069 |
|
| 118 |
+
| 0.1683 | 65.0 | 3770 | 5.3124 | 0.2414 |
|
| 119 |
+
| 0.1761 | 66.0 | 3828 | 4.8748 | 0.2414 |
|
| 120 |
+
| 0.1868 | 67.0 | 3886 | 4.9547 | 0.2414 |
|
| 121 |
+
| 0.2524 | 68.0 | 3944 | 4.9069 | 0.2759 |
|
| 122 |
+
| 0.1367 | 69.0 | 4002 | 4.8562 | 0.2414 |
|
| 123 |
+
| 0.1368 | 70.0 | 4060 | 4.9808 | 0.2414 |
|
| 124 |
+
| 0.1841 | 71.0 | 4118 | 5.1471 | 0.2414 |
|
| 125 |
+
| 0.1658 | 72.0 | 4176 | 5.1741 | 0.2414 |
|
| 126 |
+
| 0.1553 | 73.0 | 4234 | 5.2040 | 0.2414 |
|
| 127 |
+
| 0.1625 | 74.0 | 4292 | 5.1895 | 0.2414 |
|
| 128 |
+
| 0.1823 | 75.0 | 4350 | 5.1901 | 0.2414 |
|
| 129 |
+
|
| 130 |
+
|
| 131 |
+
### Framework versions
|
| 132 |
+
|
| 133 |
+
- Transformers 4.56.2
|
| 134 |
+
- Pytorch 2.8.0+cu128
|
| 135 |
+
- Datasets 3.6.0
|
| 136 |
+
- Tokenizers 0.22.1
|
config.json
ADDED
|
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"Wav2Vec2ForSequenceClassification"
|
| 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": "sum",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": false,
|
| 48 |
+
"dtype": "float32",
|
| 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 |
+
"id2label": {
|
| 60 |
+
"0": "notti",
|
| 61 |
+
"1": "emu",
|
| 62 |
+
"2": "bbiri",
|
| 63 |
+
"3": "ssatu",
|
| 64 |
+
"4": "nnya",
|
| 65 |
+
"5": "ttaano",
|
| 66 |
+
"6": "mukaaga",
|
| 67 |
+
"7": "musanvu",
|
| 68 |
+
"8": "munaana",
|
| 69 |
+
"9": "mwenda"
|
| 70 |
+
},
|
| 71 |
+
"initializer_range": 0.02,
|
| 72 |
+
"intermediate_size": 3072,
|
| 73 |
+
"label2id": {
|
| 74 |
+
"bbiri": 2,
|
| 75 |
+
"emu": 1,
|
| 76 |
+
"mukaaga": 6,
|
| 77 |
+
"munaana": 8,
|
| 78 |
+
"musanvu": 7,
|
| 79 |
+
"mwenda": 9,
|
| 80 |
+
"nnya": 4,
|
| 81 |
+
"notti": 0,
|
| 82 |
+
"ssatu": 3,
|
| 83 |
+
"ttaano": 5
|
| 84 |
+
},
|
| 85 |
+
"layer_norm_eps": 1e-05,
|
| 86 |
+
"layerdrop": 0.0,
|
| 87 |
+
"mask_channel_length": 10,
|
| 88 |
+
"mask_channel_min_space": 1,
|
| 89 |
+
"mask_channel_other": 0.0,
|
| 90 |
+
"mask_channel_prob": 0.0,
|
| 91 |
+
"mask_channel_selection": "static",
|
| 92 |
+
"mask_feature_length": 10,
|
| 93 |
+
"mask_feature_min_masks": 0,
|
| 94 |
+
"mask_feature_prob": 0.0,
|
| 95 |
+
"mask_time_length": 10,
|
| 96 |
+
"mask_time_min_masks": 2,
|
| 97 |
+
"mask_time_min_space": 1,
|
| 98 |
+
"mask_time_other": 0.0,
|
| 99 |
+
"mask_time_prob": 0.05,
|
| 100 |
+
"mask_time_selection": "static",
|
| 101 |
+
"model_type": "wav2vec2",
|
| 102 |
+
"no_mask_channel_overlap": false,
|
| 103 |
+
"no_mask_time_overlap": false,
|
| 104 |
+
"num_adapter_layers": 3,
|
| 105 |
+
"num_attention_heads": 12,
|
| 106 |
+
"num_codevector_groups": 2,
|
| 107 |
+
"num_codevectors_per_group": 320,
|
| 108 |
+
"num_conv_pos_embedding_groups": 16,
|
| 109 |
+
"num_conv_pos_embeddings": 128,
|
| 110 |
+
"num_feat_extract_layers": 7,
|
| 111 |
+
"num_hidden_layers": 12,
|
| 112 |
+
"num_negatives": 100,
|
| 113 |
+
"output_hidden_size": 768,
|
| 114 |
+
"pad_token_id": 0,
|
| 115 |
+
"proj_codevector_dim": 256,
|
| 116 |
+
"tdnn_dilation": [
|
| 117 |
+
1,
|
| 118 |
+
2,
|
| 119 |
+
3,
|
| 120 |
+
1,
|
| 121 |
+
1
|
| 122 |
+
],
|
| 123 |
+
"tdnn_dim": [
|
| 124 |
+
512,
|
| 125 |
+
512,
|
| 126 |
+
512,
|
| 127 |
+
512,
|
| 128 |
+
1500
|
| 129 |
+
],
|
| 130 |
+
"tdnn_kernel": [
|
| 131 |
+
5,
|
| 132 |
+
3,
|
| 133 |
+
3,
|
| 134 |
+
1,
|
| 135 |
+
1
|
| 136 |
+
],
|
| 137 |
+
"transformers_version": "4.56.2",
|
| 138 |
+
"use_weighted_layer_sum": false,
|
| 139 |
+
"vocab_size": 32,
|
| 140 |
+
"xvector_output_dim": 512
|
| 141 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83a905e0c6ced500f849e1c7a90338b1f01dfed272580dd770af2850ca20de56
|
| 3 |
+
size 378310592
|
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 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eabad3d3e1d00694d28fdb452b4c4ad56eb8006527158f935c32dab90691986f
|
| 3 |
+
size 5841
|