Commit
•
8d58382
1
Parent(s):
23b1976
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- hu
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- automatic-speech-recognition
|
7 |
+
- mozilla-foundation/common_voice_7_0
|
8 |
+
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- common_voice
|
11 |
+
model-index:
|
12 |
+
- name: wav2vec2-large-xls-r-300m-hungarian
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# wav2vec2-large-xls-r-300m-hungarian
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - HU dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.2562
|
24 |
+
- Wer: 0.3112
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 7e-05
|
44 |
+
- train_batch_size: 32
|
45 |
+
- eval_batch_size: 32
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- lr_scheduler_warmup_steps: 1000
|
50 |
+
- num_epochs: 50.0
|
51 |
+
- mixed_precision_training: Native AMP
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
56 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
57 |
+
| 2.3964 | 3.52 | 1000 | 1.2251 | 0.8781 |
|
58 |
+
| 1.3176 | 7.04 | 2000 | 0.3872 | 0.4462 |
|
59 |
+
| 1.1999 | 10.56 | 3000 | 0.3244 | 0.3922 |
|
60 |
+
| 1.1633 | 14.08 | 4000 | 0.3014 | 0.3704 |
|
61 |
+
| 1.1132 | 17.61 | 5000 | 0.2913 | 0.3623 |
|
62 |
+
| 1.0888 | 21.13 | 6000 | 0.2864 | 0.3498 |
|
63 |
+
| 1.0487 | 24.65 | 7000 | 0.2821 | 0.3435 |
|
64 |
+
| 1.0431 | 28.17 | 8000 | 0.2739 | 0.3308 |
|
65 |
+
| 0.9896 | 31.69 | 9000 | 0.2629 | 0.3243 |
|
66 |
+
| 0.9839 | 35.21 | 10000 | 0.2806 | 0.3308 |
|
67 |
+
| 0.9586 | 38.73 | 11000 | 0.2650 | 0.3235 |
|
68 |
+
| 0.9501 | 42.25 | 12000 | 0.2585 | 0.3173 |
|
69 |
+
| 0.938 | 45.77 | 13000 | 0.2561 | 0.3117 |
|
70 |
+
| 0.921 | 49.3 | 14000 | 0.2559 | 0.3115 |
|
71 |
+
|
72 |
+
|
73 |
+
### Framework versions
|
74 |
+
|
75 |
+
- Transformers 4.16.0.dev0
|
76 |
+
- Pytorch 1.10.1+cu102
|
77 |
+
- Datasets 1.17.1.dev0
|
78 |
+
- Tokenizers 0.11.0
|