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: urdumodel
|
| 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 |
+
# urdumodel
|
| 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: 0.4889
|
| 18 |
+
- Wer: 0.3744
|
| 19 |
+
- Cer: 0.1488
|
| 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: 0.0003
|
| 39 |
+
- train_batch_size: 24
|
| 40 |
+
- eval_batch_size: 24
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 96
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 15
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
| 53 |
+
| 2.8998 | 1.0 | 508 | 1.0261 | 0.7004 | 0.2832 |
|
| 54 |
+
| 0.7426 | 2.0 | 1016 | 0.6532 | 0.5236 | 0.2026 |
|
| 55 |
+
| 0.5694 | 3.0 | 1524 | 0.5495 | 0.4611 | 0.1799 |
|
| 56 |
+
| 0.4966 | 4.0 | 2032 | 0.5361 | 0.4350 | 0.1729 |
|
| 57 |
+
| 0.4555 | 5.0 | 2540 | 0.5335 | 0.4266 | 0.1684 |
|
| 58 |
+
| 0.4203 | 6.0 | 3048 | 0.5040 | 0.4107 | 0.1641 |
|
| 59 |
+
| 0.3951 | 7.0 | 3556 | 0.5213 | 0.4037 | 0.1579 |
|
| 60 |
+
| 0.3675 | 8.0 | 4064 | 0.4949 | 0.3973 | 0.1563 |
|
| 61 |
+
| 0.3555 | 9.0 | 4572 | 0.4968 | 0.3978 | 0.1581 |
|
| 62 |
+
| 0.3408 | 10.0 | 5080 | 0.4827 | 0.3925 | 0.1561 |
|
| 63 |
+
| 0.3286 | 11.0 | 5588 | 0.5011 | 0.3858 | 0.1524 |
|
| 64 |
+
| 0.3156 | 12.0 | 6096 | 0.4871 | 0.3833 | 0.1524 |
|
| 65 |
+
| 0.3047 | 13.0 | 6604 | 0.4835 | 0.3774 | 0.1499 |
|
| 66 |
+
| 0.2929 | 14.0 | 7112 | 0.4844 | 0.3751 | 0.1489 |
|
| 67 |
+
| 0.2912 | 15.0 | 7620 | 0.4889 | 0.3744 | 0.1488 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.21.1
|
| 73 |
+
- Pytorch 1.12.0
|
| 74 |
+
- Datasets 2.4.0
|
| 75 |
+
- Tokenizers 0.12.1
|