Commit
•
b1e477f
1
Parent(s):
06caed4
End of training
Browse files- README.md +109 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
base_model: nguyenvulebinh/wav2vec2-base-vi
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: wav2vec2-base-vietnamese-clean-dataset-20-epochs
|
| 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 |
+
# wav2vec2-base-vietnamese-clean-dataset-20-epochs
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vi](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vi) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5701
|
| 21 |
+
- Wer: 0.2489
|
| 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: 1e-05
|
| 41 |
+
- train_batch_size: 32
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 1000
|
| 47 |
+
- num_epochs: 20
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 53 |
+
| 15.8906 | 0.41 | 500 | 22.2498 | 1.0 |
|
| 54 |
+
| 10.675 | 0.81 | 1000 | 16.8372 | 1.0 |
|
| 55 |
+
| 7.7286 | 1.22 | 1500 | 10.6552 | 1.0 |
|
| 56 |
+
| 5.3176 | 1.63 | 2000 | 6.4350 | 1.0 |
|
| 57 |
+
| 4.004 | 2.04 | 2500 | 4.2915 | 1.0 |
|
| 58 |
+
| 3.5239 | 2.44 | 3000 | 3.8151 | 1.0 |
|
| 59 |
+
| 3.4366 | 2.85 | 3500 | 3.5758 | 1.0 |
|
| 60 |
+
| 3.3874 | 3.26 | 4000 | 3.4953 | 1.0 |
|
| 61 |
+
| 3.3758 | 3.66 | 4500 | 3.4716 | 1.0 |
|
| 62 |
+
| 3.3647 | 4.07 | 5000 | 3.6072 | 1.0 |
|
| 63 |
+
| 3.3574 | 4.48 | 5500 | 3.5273 | 1.0 |
|
| 64 |
+
| 3.303 | 4.89 | 6000 | 3.4187 | 1.0000 |
|
| 65 |
+
| 3.0766 | 5.29 | 6500 | 2.9887 | 0.9993 |
|
| 66 |
+
| 2.7324 | 5.7 | 7000 | 2.5486 | 1.0010 |
|
| 67 |
+
| 2.3984 | 6.11 | 7500 | 2.2322 | 0.9850 |
|
| 68 |
+
| 2.1125 | 6.51 | 8000 | 1.9550 | 0.8958 |
|
| 69 |
+
| 1.8964 | 6.92 | 8500 | 1.7719 | 0.8172 |
|
| 70 |
+
| 1.7212 | 7.33 | 9000 | 1.5676 | 0.7549 |
|
| 71 |
+
| 1.5851 | 7.74 | 9500 | 1.4595 | 0.7091 |
|
| 72 |
+
| 1.49 | 8.14 | 10000 | 1.2293 | 0.6449 |
|
| 73 |
+
| 1.3883 | 8.55 | 10500 | 1.1185 | 0.6026 |
|
| 74 |
+
| 1.2862 | 8.96 | 11000 | 1.0546 | 0.5747 |
|
| 75 |
+
| 1.2146 | 9.36 | 11500 | 0.9808 | 0.5227 |
|
| 76 |
+
| 1.153 | 9.77 | 12000 | 0.9699 | 0.4917 |
|
| 77 |
+
| 1.0782 | 10.18 | 12500 | 0.9498 | 0.4544 |
|
| 78 |
+
| 1.0517 | 10.59 | 13000 | 0.9242 | 0.4206 |
|
| 79 |
+
| 1.0001 | 10.99 | 13500 | 0.8411 | 0.3910 |
|
| 80 |
+
| 0.9578 | 11.4 | 14000 | 0.8315 | 0.3708 |
|
| 81 |
+
| 0.9302 | 11.81 | 14500 | 0.8107 | 0.3521 |
|
| 82 |
+
| 0.8978 | 12.21 | 15000 | 0.7713 | 0.3351 |
|
| 83 |
+
| 0.8738 | 12.62 | 15500 | 0.7798 | 0.3253 |
|
| 84 |
+
| 0.8932 | 13.03 | 16000 | 0.7182 | 0.3117 |
|
| 85 |
+
| 0.8267 | 13.44 | 16500 | 0.7165 | 0.3054 |
|
| 86 |
+
| 0.8007 | 13.84 | 17000 | 0.6838 | 0.2973 |
|
| 87 |
+
| 0.7854 | 14.25 | 17500 | 0.6783 | 0.2913 |
|
| 88 |
+
| 0.7878 | 14.66 | 18000 | 0.6394 | 0.2851 |
|
| 89 |
+
| 0.7738 | 15.07 | 18500 | 0.5956 | 0.2771 |
|
| 90 |
+
| 0.7626 | 15.47 | 19000 | 0.6121 | 0.2708 |
|
| 91 |
+
| 0.7342 | 15.88 | 19500 | 0.5865 | 0.2661 |
|
| 92 |
+
| 0.7297 | 16.29 | 20000 | 0.5963 | 0.2646 |
|
| 93 |
+
| 0.7113 | 16.69 | 20500 | 0.5828 | 0.2601 |
|
| 94 |
+
| 0.7302 | 17.1 | 21000 | 0.5981 | 0.2601 |
|
| 95 |
+
| 0.721 | 17.51 | 21500 | 0.5881 | 0.2555 |
|
| 96 |
+
| 0.7089 | 17.92 | 22000 | 0.5841 | 0.2545 |
|
| 97 |
+
| 0.7059 | 18.32 | 22500 | 0.5794 | 0.2525 |
|
| 98 |
+
| 0.6969 | 18.73 | 23000 | 0.5910 | 0.2507 |
|
| 99 |
+
| 0.7065 | 19.14 | 23500 | 0.5707 | 0.2498 |
|
| 100 |
+
| 0.6869 | 19.54 | 24000 | 0.5736 | 0.2496 |
|
| 101 |
+
| 0.7308 | 19.95 | 24500 | 0.5701 | 0.2489 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- Transformers 4.32.1
|
| 107 |
+
- Pytorch 2.0.1+cu117
|
| 108 |
+
- Datasets 2.14.4
|
| 109 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377855649
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01d1604cc37b0f99dbd00a446b01946d1240503908bbaee648d59aa4b60e498c
|
| 3 |
size 377855649
|