Commit
•
7ec2d4c
1
Parent(s):
4d3f921
End of training
Browse files- README.md +108 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 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
|
| 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: 0.0491
|
| 21 |
+
- Wer: 0.2007
|
| 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: 16
|
| 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: 100
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 53 |
+
| 19.8101 | 2.05 | 500 | 17.9020 | 1.0 |
|
| 54 |
+
| 12.7254 | 4.1 | 1000 | 13.4585 | 1.0 |
|
| 55 |
+
| 8.6927 | 6.15 | 1500 | 8.4217 | 1.0 |
|
| 56 |
+
| 5.6269 | 8.2 | 2000 | 5.1617 | 1.0 |
|
| 57 |
+
| 3.9616 | 10.25 | 2500 | 3.6167 | 1.0 |
|
| 58 |
+
| 3.2881 | 12.3 | 3000 | 3.2056 | 1.0 |
|
| 59 |
+
| 3.1381 | 14.34 | 3500 | 3.1174 | 1.0 |
|
| 60 |
+
| 3.092 | 16.39 | 4000 | 3.1044 | 1.0 |
|
| 61 |
+
| 3.0222 | 18.44 | 4500 | 2.9461 | 1.0 |
|
| 62 |
+
| 2.8394 | 20.49 | 5000 | 2.7133 | 1.0 |
|
| 63 |
+
| 2.6096 | 22.54 | 5500 | 2.3871 | 1.0 |
|
| 64 |
+
| 2.3244 | 24.59 | 6000 | 2.0311 | 1.0 |
|
| 65 |
+
| 1.9785 | 26.64 | 6500 | 1.6117 | 1.0 |
|
| 66 |
+
| 1.6346 | 28.69 | 7000 | 1.2173 | 1.0 |
|
| 67 |
+
| 1.3122 | 30.74 | 7500 | 0.9547 | 1.0 |
|
| 68 |
+
| 1.0927 | 32.79 | 8000 | 0.7738 | 1.0 |
|
| 69 |
+
| 0.9261 | 34.84 | 8500 | 0.6172 | 0.8970 |
|
| 70 |
+
| 0.7336 | 36.89 | 9000 | 0.4357 | 0.3654 |
|
| 71 |
+
| 0.5754 | 38.93 | 9500 | 0.3304 | 0.3071 |
|
| 72 |
+
| 0.4791 | 40.98 | 10000 | 0.2668 | 0.2785 |
|
| 73 |
+
| 0.4212 | 43.03 | 10500 | 0.2240 | 0.2548 |
|
| 74 |
+
| 0.3439 | 45.08 | 11000 | 0.1852 | 0.2329 |
|
| 75 |
+
| 0.3048 | 47.13 | 11500 | 0.1607 | 0.2119 |
|
| 76 |
+
| 0.2684 | 49.18 | 12000 | 0.1376 | 0.2105 |
|
| 77 |
+
| 0.2298 | 51.23 | 12500 | 0.1227 | 0.2071 |
|
| 78 |
+
| 0.2192 | 53.28 | 13000 | 0.1092 | 0.2055 |
|
| 79 |
+
| 0.2063 | 55.33 | 13500 | 0.0990 | 0.2039 |
|
| 80 |
+
| 0.1875 | 57.38 | 14000 | 0.0895 | 0.2039 |
|
| 81 |
+
| 0.1692 | 59.43 | 14500 | 0.0822 | 0.2039 |
|
| 82 |
+
| 0.1421 | 61.48 | 15000 | 0.0766 | 0.2029 |
|
| 83 |
+
| 0.1505 | 63.52 | 15500 | 0.0710 | 0.2031 |
|
| 84 |
+
| 0.1796 | 65.57 | 16000 | 0.0682 | 0.2019 |
|
| 85 |
+
| 0.1265 | 67.62 | 16500 | 0.0641 | 0.2015 |
|
| 86 |
+
| 0.1172 | 69.67 | 17000 | 0.0617 | 0.2019 |
|
| 87 |
+
| 0.1173 | 71.72 | 17500 | 0.0586 | 0.2011 |
|
| 88 |
+
| 0.1226 | 73.77 | 18000 | 0.0568 | 0.2015 |
|
| 89 |
+
| 0.1165 | 75.82 | 18500 | 0.0567 | 0.2011 |
|
| 90 |
+
| 0.1098 | 77.87 | 19000 | 0.0547 | 0.2007 |
|
| 91 |
+
| 0.0996 | 79.92 | 19500 | 0.0537 | 0.2009 |
|
| 92 |
+
| 0.1024 | 81.97 | 20000 | 0.0521 | 0.2009 |
|
| 93 |
+
| 0.0992 | 84.02 | 20500 | 0.0508 | 0.2009 |
|
| 94 |
+
| 0.1008 | 86.07 | 21000 | 0.0510 | 0.2009 |
|
| 95 |
+
| 0.1147 | 88.11 | 21500 | 0.0501 | 0.2007 |
|
| 96 |
+
| 0.1138 | 90.16 | 22000 | 0.0500 | 0.2005 |
|
| 97 |
+
| 0.0939 | 92.21 | 22500 | 0.0493 | 0.2007 |
|
| 98 |
+
| 0.1021 | 94.26 | 23000 | 0.0492 | 0.2005 |
|
| 99 |
+
| 0.1009 | 96.31 | 23500 | 0.0488 | 0.2009 |
|
| 100 |
+
| 0.0935 | 98.36 | 24000 | 0.0491 | 0.2007 |
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
### Framework versions
|
| 104 |
+
|
| 105 |
+
- Transformers 4.32.1
|
| 106 |
+
- Pytorch 2.0.1+cu117
|
| 107 |
+
- Datasets 2.14.4
|
| 108 |
+
- 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 sha256:714c64fe69a3fb4ffe8b12542f56e2ebe10fb6316d9a58f5da24156b454b03f7
|
| 3 |
size 377855649
|