update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-base-vios-google-colab
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# wav2vec2-base-vios-google-colab
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.5647
|
| 18 |
+
- Wer: 0.4970
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0001
|
| 38 |
+
- train_batch_size: 16
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 32
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 1000
|
| 46 |
+
- num_epochs: 30
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 7.7292 | 2.0 | 500 | 3.4159 | 1.0 |
|
| 54 |
+
| 3.0762 | 4.0 | 1000 | 1.3005 | 0.9615 |
|
| 55 |
+
| 0.8812 | 6.0 | 1500 | 0.4664 | 0.4740 |
|
| 56 |
+
| 0.5076 | 8.0 | 2000 | 0.4101 | 0.4180 |
|
| 57 |
+
| 0.4075 | 10.0 | 2500 | 0.3815 | 0.3802 |
|
| 58 |
+
| 0.3724 | 12.0 | 3000 | 0.3785 | 0.3741 |
|
| 59 |
+
| 0.3762 | 14.0 | 3500 | 0.4404 | 0.3766 |
|
| 60 |
+
| 0.4541 | 16.0 | 4000 | 0.4671 | 0.3822 |
|
| 61 |
+
| 0.6391 | 18.0 | 4500 | 0.5643 | 0.4200 |
|
| 62 |
+
| 0.7681 | 20.0 | 5000 | 0.6564 | 0.5214 |
|
| 63 |
+
| 0.8131 | 22.0 | 5500 | 0.5786 | 0.4934 |
|
| 64 |
+
| 0.7448 | 24.0 | 6000 | 0.5561 | 0.4920 |
|
| 65 |
+
| 0.7337 | 26.0 | 6500 | 0.5631 | 0.4964 |
|
| 66 |
+
| 0.7359 | 28.0 | 7000 | 0.5647 | 0.4968 |
|
| 67 |
+
| 0.7397 | 30.0 | 7500 | 0.5647 | 0.4970 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.17.0
|
| 73 |
+
- Pytorch 1.11.0+cu113
|
| 74 |
+
- Datasets 1.18.3
|
| 75 |
+
- Tokenizers 0.12.1
|