update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: xlsr-53-bemba-15hrs
|
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 |
+
# xlsr-53-bemba-15hrs
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.2789
|
18 |
+
- Wer: 0.3751
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.0003
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 2
|
42 |
+
- total_train_batch_size: 16
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_steps: 400
|
46 |
+
- num_epochs: 10
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
53 |
+
| 3.4138 | 0.71 | 400 | 0.4965 | 0.7239 |
|
54 |
+
| 0.5685 | 1.43 | 800 | 0.2939 | 0.4839 |
|
55 |
+
| 0.4471 | 2.15 | 1200 | 0.2728 | 0.4467 |
|
56 |
+
| 0.3579 | 2.86 | 1600 | 0.2397 | 0.3965 |
|
57 |
+
| 0.3087 | 3.58 | 2000 | 0.2427 | 0.4015 |
|
58 |
+
| 0.2702 | 4.29 | 2400 | 0.2539 | 0.4112 |
|
59 |
+
| 0.2406 | 5.01 | 2800 | 0.2376 | 0.3885 |
|
60 |
+
| 0.2015 | 5.72 | 3200 | 0.2492 | 0.3844 |
|
61 |
+
| 0.1759 | 6.44 | 3600 | 0.2562 | 0.3768 |
|
62 |
+
| 0.1572 | 7.16 | 4000 | 0.2789 | 0.3751 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.19.0.dev0
|
68 |
+
- Pytorch 1.10.0+cu111
|
69 |
+
- Datasets 2.1.0
|
70 |
+
- Tokenizers 0.12.1
|