Commit
•
71cfa97
1
Parent(s):
b085492
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: ''
|
| 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 |
+
#
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.9584
|
| 20 |
+
- Wer: 0.5391
|
| 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: 7.5e-05
|
| 40 |
+
- train_batch_size: 8
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 50
|
| 48 |
+
- num_epochs: 50.0
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 5.3118 | 1.96 | 100 | 2.9093 | 0.9982 |
|
| 56 |
+
| 2.2071 | 3.92 | 200 | 1.1737 | 0.7779 |
|
| 57 |
+
| 1.6098 | 5.88 | 300 | 0.9984 | 0.7015 |
|
| 58 |
+
| 1.4333 | 7.84 | 400 | 0.9800 | 0.6705 |
|
| 59 |
+
| 1.2859 | 9.8 | 500 | 0.9582 | 0.6487 |
|
| 60 |
+
| 1.2073 | 11.76 | 600 | 0.8841 | 0.6077 |
|
| 61 |
+
| 1.1417 | 13.73 | 700 | 0.9118 | 0.6343 |
|
| 62 |
+
| 1.0988 | 15.69 | 800 | 0.9217 | 0.6196 |
|
| 63 |
+
| 1.0279 | 17.65 | 900 | 0.9165 | 0.5867 |
|
| 64 |
+
| 0.9765 | 19.61 | 1000 | 0.9306 | 0.5978 |
|
| 65 |
+
| 0.9161 | 21.57 | 1100 | 0.9305 | 0.5768 |
|
| 66 |
+
| 0.8395 | 23.53 | 1200 | 0.9828 | 0.5819 |
|
| 67 |
+
| 0.8306 | 25.49 | 1300 | 0.9397 | 0.5760 |
|
| 68 |
+
| 0.7819 | 27.45 | 1400 | 0.9544 | 0.5742 |
|
| 69 |
+
| 0.7509 | 29.41 | 1500 | 0.9278 | 0.5690 |
|
| 70 |
+
| 0.7218 | 31.37 | 1600 | 0.9003 | 0.5587 |
|
| 71 |
+
| 0.6725 | 33.33 | 1700 | 0.9659 | 0.5554 |
|
| 72 |
+
| 0.6287 | 35.29 | 1800 | 0.9522 | 0.5561 |
|
| 73 |
+
| 0.6077 | 37.25 | 1900 | 0.9154 | 0.5465 |
|
| 74 |
+
| 0.5873 | 39.22 | 2000 | 0.9331 | 0.5469 |
|
| 75 |
+
| 0.5621 | 41.18 | 2100 | 0.9335 | 0.5491 |
|
| 76 |
+
| 0.5168 | 43.14 | 2200 | 0.9632 | 0.5458 |
|
| 77 |
+
| 0.5114 | 45.1 | 2300 | 0.9349 | 0.5387 |
|
| 78 |
+
| 0.4986 | 47.06 | 2400 | 0.9364 | 0.5380 |
|
| 79 |
+
| 0.4761 | 49.02 | 2500 | 0.9584 | 0.5391 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.17.0.dev0
|
| 85 |
+
- Pytorch 1.10.2+cu102
|
| 86 |
+
- Datasets 1.18.3
|
| 87 |
+
- Tokenizers 0.11.0
|