update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: Wav2Vec2_FullDataset
|
| 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_FullDataset
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.5144
|
| 18 |
+
- Wer: 0.3292
|
| 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: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 1000
|
| 44 |
+
- num_epochs: 30
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 50 |
+
| 3.5171 | 1.0 | 500 | 1.8108 | 1.0014 |
|
| 51 |
+
| 0.8397 | 2.01 | 1000 | 0.5559 | 0.5358 |
|
| 52 |
+
| 0.431 | 3.01 | 1500 | 0.4265 | 0.4469 |
|
| 53 |
+
| 0.2931 | 4.02 | 2000 | 0.4034 | 0.4193 |
|
| 54 |
+
| 0.2247 | 5.02 | 2500 | 0.4595 | 0.4076 |
|
| 55 |
+
| 0.1855 | 6.02 | 3000 | 0.4543 | 0.3991 |
|
| 56 |
+
| 0.1497 | 7.03 | 3500 | 0.4894 | 0.3839 |
|
| 57 |
+
| 0.1339 | 8.03 | 4000 | 0.4514 | 0.3836 |
|
| 58 |
+
| 0.1166 | 9.04 | 4500 | 0.4432 | 0.3682 |
|
| 59 |
+
| 0.1063 | 10.04 | 5000 | 0.4781 | 0.3773 |
|
| 60 |
+
| 0.0923 | 11.04 | 5500 | 0.4548 | 0.3699 |
|
| 61 |
+
| 0.0899 | 12.05 | 6000 | 0.4836 | 0.3636 |
|
| 62 |
+
| 0.0802 | 13.05 | 6500 | 0.5117 | 0.3637 |
|
| 63 |
+
| 0.0726 | 14.06 | 7000 | 0.4453 | 0.3653 |
|
| 64 |
+
| 0.07 | 15.06 | 7500 | 0.4983 | 0.3581 |
|
| 65 |
+
| 0.0641 | 16.06 | 8000 | 0.4922 | 0.3603 |
|
| 66 |
+
| 0.0561 | 17.07 | 8500 | 0.4947 | 0.3517 |
|
| 67 |
+
| 0.0522 | 18.07 | 9000 | 0.5132 | 0.3513 |
|
| 68 |
+
| 0.0483 | 19.08 | 9500 | 0.4815 | 0.3453 |
|
| 69 |
+
| 0.0419 | 20.08 | 10000 | 0.5556 | 0.3459 |
|
| 70 |
+
| 0.0402 | 21.08 | 10500 | 0.5141 | 0.3428 |
|
| 71 |
+
| 0.0368 | 22.09 | 11000 | 0.5176 | 0.3437 |
|
| 72 |
+
| 0.0322 | 23.09 | 11500 | 0.5326 | 0.3403 |
|
| 73 |
+
| 0.0305 | 24.1 | 12000 | 0.5046 | 0.3366 |
|
| 74 |
+
| 0.0258 | 25.1 | 12500 | 0.5219 | 0.3315 |
|
| 75 |
+
| 0.0254 | 26.1 | 13000 | 0.5166 | 0.3289 |
|
| 76 |
+
| 0.0226 | 27.11 | 13500 | 0.5177 | 0.3311 |
|
| 77 |
+
| 0.0226 | 28.11 | 14000 | 0.5187 | 0.3302 |
|
| 78 |
+
| 0.0209 | 29.12 | 14500 | 0.5144 | 0.3292 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.17.0
|
| 84 |
+
- Pytorch 2.5.1+cu121
|
| 85 |
+
- Datasets 1.18.3
|
| 86 |
+
- Tokenizers 0.20.3
|