Commit
•
7f96a35
1
Parent(s):
f6ba3cb
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
base_model: carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Icelandic-finetuned-data-augmentation_light
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# Icelandic-finetuned-data-augmentation_light
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h](https://huggingface.co/carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.2736
|
| 21 |
+
- Wer: 0.2338
|
| 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: 0.0003
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 16
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 500
|
| 49 |
+
- num_epochs: 10
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| No log | 0.2 | 10 | 0.4566 | 0.2819 |
|
| 56 |
+
| No log | 0.4 | 20 | 0.3958 | 0.2494 |
|
| 57 |
+
| No log | 0.6 | 30 | 0.3829 | 0.2237 |
|
| 58 |
+
| No log | 0.8 | 40 | 0.3622 | 0.2103 |
|
| 59 |
+
| 0.7129 | 1.0 | 50 | 0.3751 | 0.2025 |
|
| 60 |
+
| 0.7129 | 1.2 | 60 | 0.3737 | 0.2025 |
|
| 61 |
+
| 0.7129 | 1.4 | 70 | 0.3765 | 0.2025 |
|
| 62 |
+
| 0.7129 | 1.6 | 80 | 0.3589 | 0.2069 |
|
| 63 |
+
| 0.7129 | 1.8 | 90 | 0.3246 | 0.1902 |
|
| 64 |
+
| 0.3852 | 2.0 | 100 | 0.3146 | 0.1879 |
|
| 65 |
+
| 0.3852 | 2.2 | 110 | 0.3209 | 0.1790 |
|
| 66 |
+
| 0.3852 | 2.4 | 120 | 0.3129 | 0.1779 |
|
| 67 |
+
| 0.3852 | 2.6 | 130 | 0.3003 | 0.1790 |
|
| 68 |
+
| 0.3852 | 2.8 | 140 | 0.2998 | 0.1790 |
|
| 69 |
+
| 0.2803 | 3.0 | 150 | 0.2851 | 0.1868 |
|
| 70 |
+
| 0.2803 | 3.2 | 160 | 0.2753 | 0.1801 |
|
| 71 |
+
| 0.2803 | 3.4 | 170 | 0.2957 | 0.1834 |
|
| 72 |
+
| 0.2803 | 3.6 | 180 | 0.2869 | 0.1790 |
|
| 73 |
+
| 0.2803 | 3.8 | 190 | 0.2650 | 0.1823 |
|
| 74 |
+
| 0.2545 | 4.0 | 200 | 0.2577 | 0.1734 |
|
| 75 |
+
| 0.2545 | 4.2 | 210 | 0.2389 | 0.1779 |
|
| 76 |
+
| 0.2545 | 4.4 | 220 | 0.2330 | 0.1801 |
|
| 77 |
+
| 0.2545 | 4.6 | 230 | 0.2592 | 0.1745 |
|
| 78 |
+
| 0.2545 | 4.8 | 240 | 0.2631 | 0.1779 |
|
| 79 |
+
| 0.2273 | 5.0 | 250 | 0.2305 | 0.1801 |
|
| 80 |
+
| 0.2273 | 5.2 | 260 | 0.2009 | 0.1913 |
|
| 81 |
+
| 0.2273 | 5.4 | 270 | 0.1982 | 0.1946 |
|
| 82 |
+
| 0.2273 | 5.6 | 280 | 0.1849 | 0.2002 |
|
| 83 |
+
| 0.2273 | 5.8 | 290 | 0.2038 | 0.1879 |
|
| 84 |
+
| 0.2192 | 6.0 | 300 | 0.2504 | 0.1857 |
|
| 85 |
+
| 0.2192 | 6.2 | 310 | 0.2993 | 0.1790 |
|
| 86 |
+
| 0.2192 | 6.4 | 320 | 0.2544 | 0.1812 |
|
| 87 |
+
| 0.2192 | 6.6 | 330 | 0.2471 | 0.1969 |
|
| 88 |
+
| 0.2192 | 6.8 | 340 | 0.2688 | 0.1868 |
|
| 89 |
+
| 0.232 | 7.0 | 350 | 0.2264 | 0.2069 |
|
| 90 |
+
| 0.232 | 7.2 | 360 | 0.2695 | 0.1924 |
|
| 91 |
+
| 0.232 | 7.4 | 370 | 0.2728 | 0.1946 |
|
| 92 |
+
| 0.232 | 7.6 | 380 | 0.2508 | 0.1902 |
|
| 93 |
+
| 0.232 | 7.8 | 390 | 0.2499 | 0.1723 |
|
| 94 |
+
| 0.216 | 8.0 | 400 | 0.2035 | 0.1946 |
|
| 95 |
+
| 0.216 | 8.2 | 410 | 0.2620 | 0.1767 |
|
| 96 |
+
| 0.216 | 8.4 | 420 | 0.2655 | 0.1879 |
|
| 97 |
+
| 0.216 | 8.6 | 430 | 0.2773 | 0.2069 |
|
| 98 |
+
| 0.216 | 8.8 | 440 | 0.3075 | 0.2058 |
|
| 99 |
+
| 0.207 | 9.0 | 450 | 0.2791 | 0.1980 |
|
| 100 |
+
| 0.207 | 9.2 | 460 | 0.2045 | 0.1924 |
|
| 101 |
+
| 0.207 | 9.4 | 470 | 0.2329 | 0.2036 |
|
| 102 |
+
| 0.207 | 9.6 | 480 | 0.2200 | 0.2114 |
|
| 103 |
+
| 0.207 | 9.8 | 490 | 0.2864 | 0.2237 |
|
| 104 |
+
| 0.2199 | 10.0 | 500 | 0.2736 | 0.2338 |
|
| 105 |
+
|
| 106 |
+
|
| 107 |
+
### Framework versions
|
| 108 |
+
|
| 109 |
+
- Transformers 4.35.2
|
| 110 |
+
- Pytorch 2.1.0+cu121
|
| 111 |
+
- Datasets 2.15.0
|
| 112 |
+
- Tokenizers 0.15.0
|