Commit
•
f79b38b
1
Parent(s):
0c7343d
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: 0.1479
|
| 20 |
+
- Wer: 0.1611
|
| 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: 4
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 2000
|
| 48 |
+
- num_epochs: 2.0
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 55 |
+
| 1.1842 | 0.07 | 1000 | 0.4461 | 0.4918 |
|
| 56 |
+
| 1.1317 | 0.15 | 2000 | 0.2669 | 0.2748 |
|
| 57 |
+
| 1.1029 | 0.22 | 3000 | 0.2638 | 0.2706 |
|
| 58 |
+
| 1.0949 | 0.29 | 4000 | 0.2519 | 0.2627 |
|
| 59 |
+
| 1.0923 | 0.37 | 5000 | 0.2475 | 0.2577 |
|
| 60 |
+
| 1.0847 | 0.44 | 6000 | 0.2436 | 0.2612 |
|
| 61 |
+
| 1.0667 | 0.51 | 7000 | 0.2472 | 0.2661 |
|
| 62 |
+
| 1.0709 | 0.59 | 8000 | 0.2489 | 0.2610 |
|
| 63 |
+
| 1.0472 | 0.66 | 9000 | 0.2354 | 0.2500 |
|
| 64 |
+
| 1.0604 | 0.73 | 10000 | 0.2346 | 0.2485 |
|
| 65 |
+
| 1.0375 | 0.81 | 11000 | 0.2286 | 0.2390 |
|
| 66 |
+
| 1.0193 | 0.88 | 12000 | 0.2212 | 0.2338 |
|
| 67 |
+
| 1.0077 | 0.95 | 13000 | 0.2152 | 0.2269 |
|
| 68 |
+
| 1.0004 | 1.03 | 14000 | 0.2093 | 0.2207 |
|
| 69 |
+
| 0.9649 | 1.1 | 15000 | 0.1993 | 0.2113 |
|
| 70 |
+
| 0.9509 | 1.17 | 16000 | 0.1934 | 0.2089 |
|
| 71 |
+
| 0.9533 | 1.25 | 17000 | 0.1874 | 0.2023 |
|
| 72 |
+
| 0.9248 | 1.32 | 18000 | 0.1818 | 0.1974 |
|
| 73 |
+
| 0.9216 | 1.39 | 19000 | 0.1776 | 0.1926 |
|
| 74 |
+
| 0.8964 | 1.47 | 20000 | 0.1722 | 0.1904 |
|
| 75 |
+
| 0.8941 | 1.54 | 21000 | 0.1690 | 0.1852 |
|
| 76 |
+
| 0.871 | 1.61 | 22000 | 0.1627 | 0.1781 |
|
| 77 |
+
| 0.847 | 1.69 | 23000 | 0.1591 | 0.1751 |
|
| 78 |
+
| 0.822 | 1.76 | 24000 | 0.1551 | 0.1701 |
|
| 79 |
+
| 0.8188 | 1.83 | 25000 | 0.1528 | 0.1667 |
|
| 80 |
+
| 0.8305 | 1.91 | 26000 | 0.1492 | 0.1631 |
|
| 81 |
+
| 0.8122 | 1.98 | 27000 | 0.1479 | 0.1611 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
### Framework versions
|
| 85 |
+
|
| 86 |
+
- Transformers 4.17.0.dev0
|
| 87 |
+
- Pytorch 1.10.2+cu102
|
| 88 |
+
- Datasets 1.18.2.dev0
|
| 89 |
+
- Tokenizers 0.11.0
|