End of training
Browse files- README.md +79 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_control_dataset_100_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_control_dataset_100_epochs
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vi](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vi) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0584
|
| 21 |
+
- Wer: 0.1728
|
| 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: 3e-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: 75
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 16.8485 | 3.85 | 500 | 15.0708 | 1.0 |
|
| 54 |
+
| 7.7941 | 7.69 | 1000 | 5.1283 | 1.0 |
|
| 55 |
+
| 3.4391 | 11.54 | 1500 | 3.2167 | 1.0 |
|
| 56 |
+
| 3.116 | 15.38 | 2000 | 3.1172 | 1.0 |
|
| 57 |
+
| 3.0946 | 19.23 | 2500 | 3.1165 | 1.0 |
|
| 58 |
+
| 3.0478 | 23.08 | 3000 | 2.9426 | 1.0 |
|
| 59 |
+
| 2.4567 | 26.92 | 3500 | 1.6121 | 0.9993 |
|
| 60 |
+
| 1.2305 | 30.77 | 4000 | 0.5487 | 0.3630 |
|
| 61 |
+
| 0.5512 | 34.62 | 4500 | 0.2505 | 0.2364 |
|
| 62 |
+
| 0.3234 | 38.46 | 5000 | 0.1572 | 0.1869 |
|
| 63 |
+
| 0.2232 | 42.31 | 5500 | 0.1170 | 0.1782 |
|
| 64 |
+
| 0.1779 | 46.15 | 6000 | 0.0939 | 0.1772 |
|
| 65 |
+
| 0.145 | 50.0 | 6500 | 0.0830 | 0.1763 |
|
| 66 |
+
| 0.1383 | 53.85 | 7000 | 0.0739 | 0.1756 |
|
| 67 |
+
| 0.1161 | 57.69 | 7500 | 0.0681 | 0.1736 |
|
| 68 |
+
| 0.1054 | 61.54 | 8000 | 0.0630 | 0.1729 |
|
| 69 |
+
| 0.0958 | 65.38 | 8500 | 0.0620 | 0.1729 |
|
| 70 |
+
| 0.1028 | 69.23 | 9000 | 0.0582 | 0.1726 |
|
| 71 |
+
| 0.1015 | 73.08 | 9500 | 0.0584 | 0.1728 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.32.1
|
| 77 |
+
- Pytorch 2.0.1+cu117
|
| 78 |
+
- Datasets 2.14.4
|
| 79 |
+
- 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 sha256:3b87bc099580bd55ba0bab4c92c6de4e575408f95c77b1ce32ca7e9d969ef8c0
|
| 3 |
size 377855649
|