Commit
•
6795e7a
1
Parent(s):
c7333f1
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- wer
|
7 |
+
model-index:
|
8 |
+
- name: xls-r-asr_af-run4
|
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 |
+
# xls-r-asr_af-run4
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.4952
|
20 |
+
- Wer: 0.4115
|
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: 0.0003
|
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: 500
|
48 |
+
- num_epochs: 30
|
49 |
+
- mixed_precision_training: Native AMP
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
55 |
+
| 8.6153 | 0.59 | 100 | 4.0306 | 1.0 |
|
56 |
+
| 3.2623 | 1.17 | 200 | 3.0277 | 1.0 |
|
57 |
+
| 2.9667 | 1.76 | 300 | 2.9436 | 1.0 |
|
58 |
+
| 2.4516 | 2.35 | 400 | 1.4571 | 0.9030 |
|
59 |
+
| 1.174 | 2.93 | 500 | 0.9461 | 0.7412 |
|
60 |
+
| 0.7792 | 3.52 | 600 | 0.6839 | 0.6080 |
|
61 |
+
| 0.5749 | 4.11 | 700 | 0.5418 | 0.5068 |
|
62 |
+
| 0.4187 | 4.69 | 800 | 0.5341 | 0.4902 |
|
63 |
+
| 0.36 | 5.28 | 900 | 0.5231 | 0.4746 |
|
64 |
+
| 0.2934 | 5.87 | 1000 | 0.4457 | 0.4133 |
|
65 |
+
| 0.2338 | 6.45 | 1100 | 0.4904 | 0.4157 |
|
66 |
+
| 0.2245 | 7.04 | 1200 | 0.4952 | 0.4115 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.28.0
|
72 |
+
- Pytorch 2.0.1+cu117
|
73 |
+
- Datasets 2.14.4
|
74 |
+
- Tokenizers 0.13.3
|