update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-base-finetuned-ks
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# wav2vec2-base-finetuned-ks
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.7101
|
| 20 |
+
- Accuracy: 0.7538
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 3e-05
|
| 40 |
+
- train_batch_size: 32
|
| 41 |
+
- eval_batch_size: 32
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 128
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 20
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| No log | 1.0 | 7 | 1.1448 | 0.5769 |
|
| 55 |
+
| 1.0433 | 2.0 | 14 | 1.0463 | 0.6077 |
|
| 56 |
+
| 0.9904 | 3.0 | 21 | 1.0912 | 0.5923 |
|
| 57 |
+
| 0.9904 | 4.0 | 28 | 1.0639 | 0.5769 |
|
| 58 |
+
| 0.8697 | 5.0 | 35 | 1.0283 | 0.6 |
|
| 59 |
+
| 0.7873 | 6.0 | 42 | 0.8870 | 0.7077 |
|
| 60 |
+
| 0.7873 | 7.0 | 49 | 0.8815 | 0.6538 |
|
| 61 |
+
| 0.7124 | 8.0 | 56 | 0.8828 | 0.6538 |
|
| 62 |
+
| 0.666 | 9.0 | 63 | 0.8701 | 0.6846 |
|
| 63 |
+
| 0.6376 | 10.0 | 70 | 0.8704 | 0.6692 |
|
| 64 |
+
| 0.6376 | 11.0 | 77 | 0.8934 | 0.7077 |
|
| 65 |
+
| 0.6552 | 12.0 | 84 | 0.8678 | 0.6692 |
|
| 66 |
+
| 0.5827 | 13.0 | 91 | 0.8471 | 0.7 |
|
| 67 |
+
| 0.5827 | 14.0 | 98 | 0.7986 | 0.7154 |
|
| 68 |
+
| 0.5557 | 15.0 | 105 | 0.7614 | 0.7462 |
|
| 69 |
+
| 0.5255 | 16.0 | 112 | 0.7847 | 0.7231 |
|
| 70 |
+
| 0.5255 | 17.0 | 119 | 0.7917 | 0.7154 |
|
| 71 |
+
| 0.5129 | 18.0 | 126 | 0.7101 | 0.7538 |
|
| 72 |
+
| 0.4621 | 19.0 | 133 | 0.7437 | 0.7385 |
|
| 73 |
+
| 0.4552 | 20.0 | 140 | 0.7404 | 0.7308 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.11.3
|
| 79 |
+
- Pytorch 1.10.0+cu111
|
| 80 |
+
- Datasets 2.0.0
|
| 81 |
+
- Tokenizers 0.10.3
|