Commit
•
b797f45
1
Parent(s):
0f6d4c7
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 |
+
datasets:
|
| 6 |
+
- common_voice_1_0
|
| 7 |
+
model-index:
|
| 8 |
+
- name: dat259-wav2vec2-en2-copy
|
| 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 |
+
# dat259-wav2vec2-en2-copy
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the common_voice_1_0 dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.5429
|
| 20 |
+
- Wer: 0.5569
|
| 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: 0.0001
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 300
|
| 48 |
+
- num_epochs: 20
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 4.5149 | 1.82 | 200 | 3.0474 | 1.0 |
|
| 56 |
+
| 2.0483 | 3.64 | 400 | 1.8004 | 0.7808 |
|
| 57 |
+
| 0.5464 | 5.45 | 600 | 1.5242 | 0.6529 |
|
| 58 |
+
| 0.3269 | 7.27 | 800 | 1.3820 | 0.6046 |
|
| 59 |
+
| 0.2337 | 9.09 | 1000 | 1.4605 | 0.5866 |
|
| 60 |
+
| 0.1863 | 10.91 | 1200 | 1.5567 | 0.5864 |
|
| 61 |
+
| 0.1531 | 12.73 | 1400 | 1.5787 | 0.5871 |
|
| 62 |
+
| 0.1326 | 14.55 | 1600 | 1.5766 | 0.5679 |
|
| 63 |
+
| 0.1118 | 16.36 | 1800 | 1.4709 | 0.5566 |
|
| 64 |
+
| 0.1017 | 18.18 | 2000 | 1.5455 | 0.5598 |
|
| 65 |
+
| 0.0955 | 20.0 | 2200 | 1.5429 | 0.5569 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.21.1
|
| 71 |
+
- Pytorch 1.12.1+cu102
|
| 72 |
+
- Datasets 2.4.0
|
| 73 |
+
- Tokenizers 0.12.1
|