Commit
•
db53b73
1
Parent(s):
3c3d364
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec_cv
|
| 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 |
+
# wav2vec_cv
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 4.1760
|
| 18 |
+
- Wer: 1.0
|
| 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: 0.003
|
| 38 |
+
- train_batch_size: 6
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 12
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 20
|
| 46 |
+
- num_epochs: 60
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:---:|
|
| 52 |
+
| 7.1467 | 4.29 | 30 | 4.2173 | 1.0 |
|
| 53 |
+
| 6.8918 | 8.57 | 60 | 4.2004 | 1.0 |
|
| 54 |
+
| 5.4913 | 12.86 | 90 | 4.2007 | 1.0 |
|
| 55 |
+
| 5.3906 | 17.14 | 120 | 4.1765 | 1.0 |
|
| 56 |
+
| 4.9212 | 21.43 | 150 | 4.1714 | 1.0 |
|
| 57 |
+
| 4.3916 | 25.71 | 180 | 4.1811 | 1.0 |
|
| 58 |
+
| 5.2255 | 30.0 | 210 | 4.1633 | 1.0 |
|
| 59 |
+
| 4.501 | 34.29 | 240 | 4.2050 | 1.0 |
|
| 60 |
+
| 4.4328 | 38.57 | 270 | 4.1572 | 1.0 |
|
| 61 |
+
| 4.2136 | 42.86 | 300 | 4.1698 | 1.0 |
|
| 62 |
+
| 4.3353 | 47.14 | 330 | 4.1721 | 1.0 |
|
| 63 |
+
| 4.1805 | 51.43 | 360 | 4.1804 | 1.0 |
|
| 64 |
+
| 4.1695 | 55.71 | 390 | 4.1801 | 1.0 |
|
| 65 |
+
| 4.2978 | 60.0 | 420 | 4.1760 | 1.0 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.17.0
|
| 71 |
+
- Pytorch 1.11.0+cu113
|
| 72 |
+
- Datasets 1.18.3
|
| 73 |
+
- Tokenizers 0.12.1
|