Commit
•
f2e517b
1
Parent(s):
48f0952
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: 0.2763
|
| 20 |
+
- Wer: 0.2281
|
| 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: 7.1e-05
|
| 40 |
+
- train_batch_size: 32
|
| 41 |
+
- eval_batch_size: 32
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 1000
|
| 46 |
+
- num_epochs: 100.0
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 3.3881 | 6.1 | 500 | 2.9710 | 1.0 |
|
| 54 |
+
| 2.6401 | 12.2 | 1000 | 1.7677 | 0.9734 |
|
| 55 |
+
| 1.5152 | 18.29 | 1500 | 0.5564 | 0.6011 |
|
| 56 |
+
| 1.2191 | 24.39 | 2000 | 0.4319 | 0.4390 |
|
| 57 |
+
| 1.0237 | 30.49 | 2500 | 0.3141 | 0.3175 |
|
| 58 |
+
| 0.8892 | 36.59 | 3000 | 0.2748 | 0.2689 |
|
| 59 |
+
| 0.8296 | 42.68 | 3500 | 0.2680 | 0.2534 |
|
| 60 |
+
| 0.7602 | 48.78 | 4000 | 0.2820 | 0.2506 |
|
| 61 |
+
| 0.7186 | 54.88 | 4500 | 0.2672 | 0.2398 |
|
| 62 |
+
| 0.6887 | 60.98 | 5000 | 0.2729 | 0.2402 |
|
| 63 |
+
| 0.6507 | 67.07 | 5500 | 0.2767 | 0.2361 |
|
| 64 |
+
| 0.6226 | 73.17 | 6000 | 0.2817 | 0.2332 |
|
| 65 |
+
| 0.6024 | 79.27 | 6500 | 0.2679 | 0.2279 |
|
| 66 |
+
| 0.5787 | 85.37 | 7000 | 0.2837 | 0.2316 |
|
| 67 |
+
| 0.5744 | 91.46 | 7500 | 0.2838 | 0.2284 |
|
| 68 |
+
| 0.5556 | 97.56 | 8000 | 0.2763 | 0.2281 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.17.0.dev0
|
| 74 |
+
- Pytorch 1.10.2+cu102
|
| 75 |
+
- Datasets 1.18.2.dev0
|
| 76 |
+
- Tokenizers 0.11.0
|