update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- common_voice_8_0
|
7 |
+
metrics:
|
8 |
+
- wer
|
9 |
+
model-index:
|
10 |
+
- name: wav2vec2-large-xls-r-1b-frisian-cv-8
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Automatic Speech Recognition
|
14 |
+
type: automatic-speech-recognition
|
15 |
+
dataset:
|
16 |
+
name: common_voice_8_0
|
17 |
+
type: common_voice_8_0
|
18 |
+
config: fy-NL
|
19 |
+
split: validation
|
20 |
+
args: fy-NL
|
21 |
+
metrics:
|
22 |
+
- name: Wer
|
23 |
+
type: wer
|
24 |
+
value: 0.15637051849735753
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# wav2vec2-large-xls-r-1b-frisian-cv-8
|
31 |
+
|
32 |
+
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_8_0 dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.2219
|
35 |
+
- Wer: 0.1564
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 7e-05
|
55 |
+
- train_batch_size: 30
|
56 |
+
- eval_batch_size: 8
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- lr_scheduler_warmup_ratio: 0.1
|
61 |
+
- num_epochs: 50
|
62 |
+
- mixed_precision_training: Native AMP
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
68 |
+
| 4.9356 | 2.42 | 300 | 3.0022 | 1.0 |
|
69 |
+
| 1.7278 | 4.84 | 600 | 0.4414 | 0.4147 |
|
70 |
+
| 0.9407 | 7.26 | 900 | 0.3058 | 0.2955 |
|
71 |
+
| 0.943 | 9.68 | 1200 | 0.2678 | 0.2530 |
|
72 |
+
| 0.7468 | 12.1 | 1500 | 0.2443 | 0.2237 |
|
73 |
+
| 0.6009 | 14.52 | 1800 | 0.2381 | 0.2097 |
|
74 |
+
| 0.6101 | 16.94 | 2100 | 0.2339 | 0.2003 |
|
75 |
+
| 0.5646 | 19.35 | 2400 | 0.2357 | 0.2047 |
|
76 |
+
| 0.5875 | 21.77 | 2700 | 0.2219 | 0.1914 |
|
77 |
+
| 0.5245 | 24.19 | 3000 | 0.2525 | 0.1807 |
|
78 |
+
| 0.5971 | 26.61 | 3300 | 0.2432 | 0.1784 |
|
79 |
+
| 0.563 | 29.03 | 3600 | 0.2454 | 0.1753 |
|
80 |
+
| 0.4441 | 31.45 | 3900 | 0.2237 | 0.1776 |
|
81 |
+
| 0.5552 | 33.87 | 4200 | 0.2313 | 0.1629 |
|
82 |
+
| 0.5568 | 36.29 | 4500 | 0.2318 | 0.1602 |
|
83 |
+
| 0.4342 | 38.71 | 4800 | 0.2324 | 0.1556 |
|
84 |
+
| 0.4723 | 41.13 | 5100 | 0.2296 | 0.1602 |
|
85 |
+
| 0.3357 | 43.55 | 5400 | 0.2267 | 0.1575 |
|
86 |
+
| 0.4588 | 45.97 | 5700 | 0.2243 | 0.1558 |
|
87 |
+
| 0.4594 | 48.39 | 6000 | 0.2219 | 0.1564 |
|
88 |
+
|
89 |
+
|
90 |
+
### Framework versions
|
91 |
+
|
92 |
+
- Transformers 4.28.1
|
93 |
+
- Pytorch 2.0.0+cu117
|
94 |
+
- Datasets 2.11.0
|
95 |
+
- Tokenizers 0.13.3
|