update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- wer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: libri-smallw2v2-no-copy-mse-alpha-0.75-T-1-take-5
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# libri-smallw2v2-no-copy-mse-alpha-0.75-T-1-take-5
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [rohitp1/libri-smallw2v2-no-copy-mse-alpha-0.75-T-1-take-3](https://huggingface.co/rohitp1/libri-smallw2v2-no-copy-mse-alpha-0.75-T-1-take-3) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 30.3050
|
| 19 |
+
- Wer: 0.2650
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.002
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 16
|
| 43 |
+
- total_train_batch_size: 64
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.2
|
| 47 |
+
- num_epochs: 100
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 54 |
+
| 239.4865 | 1.12 | 400 | 31.0836 | 0.2908 |
|
| 55 |
+
| 210.2046 | 2.25 | 800 | 29.7831 | 0.2742 |
|
| 56 |
+
| 195.0478 | 3.37 | 1200 | 28.8794 | 0.2636 |
|
| 57 |
+
| 188.8096 | 4.49 | 1600 | 28.7458 | 0.2600 |
|
| 58 |
+
| 183.6592 | 5.62 | 2000 | 29.1159 | 0.2573 |
|
| 59 |
+
| 181.5025 | 6.74 | 2400 | 29.0081 | 0.2564 |
|
| 60 |
+
| 181.9954 | 7.86 | 2800 | 28.7132 | 0.2588 |
|
| 61 |
+
| 181.8548 | 8.99 | 3200 | 29.3207 | 0.2630 |
|
| 62 |
+
| 186.2524 | 10.11 | 3600 | 29.9119 | 0.2593 |
|
| 63 |
+
| 188.3838 | 11.24 | 4000 | 30.2963 | 0.2627 |
|
| 64 |
+
| 192.2623 | 12.36 | 4400 | 30.3050 | 0.2650 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.24.0
|
| 70 |
+
- Pytorch 1.12.1
|
| 71 |
+
- Datasets 2.7.1
|
| 72 |
+
- Tokenizers 0.11.0
|