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: output
|
| 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 |
+
# output
|
| 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: 0.2822
|
| 18 |
+
- Wer: 0.2423
|
| 19 |
+
- Cer: 0.0842
|
| 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: 48
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 192
|
| 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 | Cer | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:------:|:---------------:|:------:|
|
| 53 |
+
| No log | 1.0 | 174 | 0.9860 | 3.1257 | 1.0 |
|
| 54 |
+
| No log | 2.0 | 348 | 0.9404 | 2.4914 | 0.9997 |
|
| 55 |
+
| No log | 3.0 | 522 | 0.1889 | 0.5970 | 0.5376 |
|
| 56 |
+
| No log | 4.0 | 696 | 0.1428 | 0.4462 | 0.4121 |
|
| 57 |
+
| No log | 5.0 | 870 | 0.1211 | 0.3775 | 0.3525 |
|
| 58 |
+
| 1.7 | 6.0 | 1044 | 0.1113 | 0.3594 | 0.3264 |
|
| 59 |
+
| 1.7 | 7.0 | 1218 | 0.1032 | 0.3354 | 0.3013 |
|
| 60 |
+
| 1.7 | 8.0 | 1392 | 0.1005 | 0.3171 | 0.2843 |
|
| 61 |
+
| 1.7 | 9.0 | 1566 | 0.0953 | 0.3115 | 0.2717 |
|
| 62 |
+
| 1.7 | 10.0 | 1740 | 0.0934 | 0.3058 | 0.2671 |
|
| 63 |
+
| 1.7 | 11.0 | 1914 | 0.0926 | 0.3060 | 0.2656 |
|
| 64 |
+
| 0.3585 | 12.0 | 2088 | 0.0899 | 0.3070 | 0.2566 |
|
| 65 |
+
| 0.3585 | 13.0 | 2262 | 0.0888 | 0.2979 | 0.2509 |
|
| 66 |
+
| 0.3585 | 14.0 | 2436 | 0.0868 | 0.3005 | 0.2473 |
|
| 67 |
+
| 0.3585 | 15.0 | 2610 | 0.2822 | 0.2423 | 0.0842 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.21.0
|
| 73 |
+
- Pytorch 1.12.0
|
| 74 |
+
- Datasets 2.4.0
|
| 75 |
+
- Tokenizers 0.12.1
|