Commit
•
68a6e57
1
Parent(s):
35fe490
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2318
|
| 20 |
+
- Wer: 0.2866
|
| 21 |
+
- Cer: 0.0667
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 7.5e-05
|
| 41 |
+
- train_batch_size: 64
|
| 42 |
+
- eval_batch_size: 64
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 128
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- training_steps: 8692
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
| 56 |
+
| 3.675 | 2.3 | 400 | 3.5052 | 1.0 | 1.0 |
|
| 57 |
+
| 3.0446 | 4.6 | 800 | 2.2759 | 1.0052 | 0.5215 |
|
| 58 |
+
| 1.7276 | 6.9 | 1200 | 0.7083 | 0.6697 | 0.1969 |
|
| 59 |
+
| 1.5171 | 9.2 | 1600 | 0.5328 | 0.5733 | 0.1568 |
|
| 60 |
+
| 1.4176 | 11.49 | 2000 | 0.4571 | 0.5161 | 0.1381 |
|
| 61 |
+
| 1.343 | 13.79 | 2400 | 0.3910 | 0.4522 | 0.1160 |
|
| 62 |
+
| 1.2743 | 16.09 | 2800 | 0.3534 | 0.4137 | 0.1044 |
|
| 63 |
+
| 1.2396 | 18.39 | 3200 | 0.3278 | 0.3877 | 0.0959 |
|
| 64 |
+
| 1.2035 | 20.69 | 3600 | 0.3109 | 0.3741 | 0.0917 |
|
| 65 |
+
| 1.1745 | 22.99 | 4000 | 0.2972 | 0.3618 | 0.0882 |
|
| 66 |
+
| 1.1541 | 25.29 | 4400 | 0.2836 | 0.3427 | 0.0832 |
|
| 67 |
+
| 1.1372 | 27.59 | 4800 | 0.2759 | 0.3357 | 0.0812 |
|
| 68 |
+
| 1.1048 | 29.89 | 5200 | 0.2669 | 0.3284 | 0.0783 |
|
| 69 |
+
| 1.0966 | 32.18 | 5600 | 0.2678 | 0.3249 | 0.0775 |
|
| 70 |
+
| 1.0747 | 34.48 | 6000 | 0.2547 | 0.3134 | 0.0748 |
|
| 71 |
+
| 1.0593 | 36.78 | 6400 | 0.2491 | 0.3077 | 0.0728 |
|
| 72 |
+
| 1.0417 | 39.08 | 6800 | 0.2450 | 0.3012 | 0.0711 |
|
| 73 |
+
| 1.024 | 41.38 | 7200 | 0.2402 | 0.2956 | 0.0694 |
|
| 74 |
+
| 1.0106 | 43.68 | 7600 | 0.2351 | 0.2915 | 0.0681 |
|
| 75 |
+
| 1.0014 | 45.98 | 8000 | 0.2328 | 0.2896 | 0.0673 |
|
| 76 |
+
| 0.9999 | 48.28 | 8400 | 0.2318 | 0.2866 | 0.0667 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- Transformers 4.19.0.dev0
|
| 82 |
+
- Pytorch 1.11.0+cu102
|
| 83 |
+
- Datasets 2.1.1.dev0
|
| 84 |
+
- Tokenizers 0.12.1
|