Commit ·
72dd1dd
1
Parent(s): e8f99dd
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: model_phoneme_onSet3
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# model_phoneme_onSet3
|
| 13 |
+
|
| 14 |
+
This model was trained from scratch on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- eval_loss: 0.1119
|
| 17 |
+
- eval_0_precision: 1.0
|
| 18 |
+
- eval_0_recall: 0.9355
|
| 19 |
+
- eval_0_f1-score: 0.9667
|
| 20 |
+
- eval_0_support: 31
|
| 21 |
+
- eval_1_precision: 0.9231
|
| 22 |
+
- eval_1_recall: 1.0
|
| 23 |
+
- eval_1_f1-score: 0.9600
|
| 24 |
+
- eval_1_support: 24
|
| 25 |
+
- eval_2_precision: 1.0
|
| 26 |
+
- eval_2_recall: 0.9545
|
| 27 |
+
- eval_2_f1-score: 0.9767
|
| 28 |
+
- eval_2_support: 22
|
| 29 |
+
- eval_3_precision: 0.9524
|
| 30 |
+
- eval_3_recall: 1.0
|
| 31 |
+
- eval_3_f1-score: 0.9756
|
| 32 |
+
- eval_3_support: 20
|
| 33 |
+
- eval_accuracy: 0.9691
|
| 34 |
+
- eval_macro avg_precision: 0.9689
|
| 35 |
+
- eval_macro avg_recall: 0.9725
|
| 36 |
+
- eval_macro avg_f1-score: 0.9698
|
| 37 |
+
- eval_macro avg_support: 97
|
| 38 |
+
- eval_weighted avg_precision: 0.9711
|
| 39 |
+
- eval_weighted avg_recall: 0.9691
|
| 40 |
+
- eval_weighted avg_f1-score: 0.9691
|
| 41 |
+
- eval_weighted avg_support: 97
|
| 42 |
+
- eval_wer: 0.0986
|
| 43 |
+
- eval_mtrix: [[0, 1, 2, 3], [0, 29, 1, 0, 1], [1, 0, 24, 0, 0], [2, 0, 1, 21, 0], [3, 0, 0, 0, 20]]
|
| 44 |
+
- eval_runtime: 5.7078
|
| 45 |
+
- eval_samples_per_second: 16.994
|
| 46 |
+
- eval_steps_per_second: 2.278
|
| 47 |
+
- step: 0
|
| 48 |
+
|
| 49 |
+
## Model description
|
| 50 |
+
|
| 51 |
+
More information needed
|
| 52 |
+
|
| 53 |
+
## Intended uses & limitations
|
| 54 |
+
|
| 55 |
+
More information needed
|
| 56 |
+
|
| 57 |
+
## Training and evaluation data
|
| 58 |
+
|
| 59 |
+
More information needed
|
| 60 |
+
|
| 61 |
+
## Training procedure
|
| 62 |
+
|
| 63 |
+
### Training hyperparameters
|
| 64 |
+
|
| 65 |
+
The following hyperparameters were used during training:
|
| 66 |
+
- learning_rate: 0.0003
|
| 67 |
+
- train_batch_size: 8
|
| 68 |
+
- eval_batch_size: 8
|
| 69 |
+
- seed: 42
|
| 70 |
+
- gradient_accumulation_steps: 2
|
| 71 |
+
- total_train_batch_size: 16
|
| 72 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 73 |
+
- lr_scheduler_type: linear
|
| 74 |
+
- lr_scheduler_warmup_steps: 200
|
| 75 |
+
- num_epochs: 70
|
| 76 |
+
- mixed_precision_training: Native AMP
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.25.1
|
| 81 |
+
- Pytorch 1.13.0+cu116
|
| 82 |
+
- Datasets 2.8.0
|
| 83 |
+
- Tokenizers 0.13.2
|