Commit
•
f3736e3
1
Parent(s):
f9c3f13
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- common_voice
|
7 |
+
metrics:
|
8 |
+
- wer
|
9 |
+
model-index:
|
10 |
+
- name: wav2vec2-xls-r-300m-en-ar-fr-es
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Automatic Speech Recognition
|
14 |
+
type: automatic-speech-recognition
|
15 |
+
dataset:
|
16 |
+
name: common_voice
|
17 |
+
type: common_voice
|
18 |
+
config: ar
|
19 |
+
split: test
|
20 |
+
args: ar
|
21 |
+
metrics:
|
22 |
+
- name: Wer
|
23 |
+
type: wer
|
24 |
+
value: 0.48692477711277227
|
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-xls-r-300m-en-ar-fr-es
|
31 |
+
|
32 |
+
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.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.8565
|
35 |
+
- Wer: 0.4869
|
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: 0.0003
|
55 |
+
- train_batch_size: 16
|
56 |
+
- eval_batch_size: 8
|
57 |
+
- seed: 42
|
58 |
+
- gradient_accumulation_steps: 2
|
59 |
+
- total_train_batch_size: 32
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- lr_scheduler_warmup_steps: 500
|
63 |
+
- num_epochs: 20
|
64 |
+
- mixed_precision_training: Native AMP
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
70 |
+
| 6.3938 | 0.59 | 400 | 3.3703 | 1.0 |
|
71 |
+
| 2.353 | 1.18 | 800 | 0.9696 | 0.7809 |
|
72 |
+
| 0.9859 | 1.77 | 1200 | 0.7031 | 0.6515 |
|
73 |
+
| 0.7685 | 2.35 | 1600 | 0.6575 | 0.6321 |
|
74 |
+
| 0.6892 | 2.94 | 2000 | 0.6030 | 0.5927 |
|
75 |
+
| 0.5866 | 3.53 | 2400 | 0.5552 | 0.5541 |
|
76 |
+
| 0.5496 | 4.12 | 2800 | 0.5805 | 0.5503 |
|
77 |
+
| 0.4897 | 4.71 | 3200 | 0.5526 | 0.5335 |
|
78 |
+
| 0.4671 | 5.3 | 3600 | 0.5622 | 0.5507 |
|
79 |
+
| 0.4346 | 5.89 | 4000 | 0.5641 | 0.5312 |
|
80 |
+
| 0.3859 | 6.48 | 4400 | 0.5685 | 0.5071 |
|
81 |
+
| 0.3728 | 7.06 | 4800 | 0.6106 | 0.5157 |
|
82 |
+
| 0.3243 | 7.65 | 5200 | 0.6782 | 0.5270 |
|
83 |
+
| 0.3073 | 8.24 | 5600 | 0.6121 | 0.5232 |
|
84 |
+
| 0.2748 | 8.83 | 6000 | 0.6318 | 0.5209 |
|
85 |
+
| 0.25 | 9.42 | 6400 | 0.6334 | 0.4906 |
|
86 |
+
| 0.2477 | 10.01 | 6800 | 0.6403 | 0.5169 |
|
87 |
+
| 0.2125 | 10.6 | 7200 | 0.6498 | 0.5080 |
|
88 |
+
| 0.1997 | 11.18 | 7600 | 0.7029 | 0.5153 |
|
89 |
+
| 0.1803 | 11.77 | 8000 | 0.6796 | 0.5193 |
|
90 |
+
| 0.1644 | 12.36 | 8400 | 0.7320 | 0.5080 |
|
91 |
+
| 0.1609 | 12.95 | 8800 | 0.6705 | 0.5081 |
|
92 |
+
| 0.1419 | 13.54 | 9200 | 0.7108 | 0.5120 |
|
93 |
+
| 0.1375 | 14.13 | 9600 | 0.7570 | 0.4909 |
|
94 |
+
| 0.1265 | 14.72 | 10000 | 0.7681 | 0.5044 |
|
95 |
+
| 0.1152 | 15.31 | 10400 | 0.8180 | 0.5011 |
|
96 |
+
| 0.1094 | 15.89 | 10800 | 0.7753 | 0.4947 |
|
97 |
+
| 0.0998 | 16.48 | 11200 | 0.8077 | 0.4972 |
|
98 |
+
| 0.1019 | 17.07 | 11600 | 0.8189 | 0.4921 |
|
99 |
+
| 0.0882 | 17.66 | 12000 | 0.8351 | 0.4922 |
|
100 |
+
| 0.0855 | 18.25 | 12400 | 0.8688 | 0.4902 |
|
101 |
+
| 0.0826 | 18.84 | 12800 | 0.8476 | 0.4916 |
|
102 |
+
| 0.0769 | 19.43 | 13200 | 0.8565 | 0.4869 |
|
103 |
+
|
104 |
+
|
105 |
+
### Framework versions
|
106 |
+
|
107 |
+
- Transformers 4.28.0
|
108 |
+
- Pytorch 2.0.1+cu118
|
109 |
+
- Datasets 1.18.3
|
110 |
+
- Tokenizers 0.13.3
|