Hugging Face's logo

nrshoudi
/
wav2vec2-large-xls-r-300m-Arabic-phoneme-Experiment3

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
nrshoudi commited on
Commit
ce98f00
•
1 Parent(s): 0a61f59

Model save

Browse files
Files changed (2) hide show
  1. README.md +90 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-xls-r-300m
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: wav2vec2-large-xls-r-300m-Arabic-phoneme-Experiment3
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # wav2vec2-large-xls-r-300m-Arabic-phoneme-Experiment3
15
+
16
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0054
19
+ - Per: 0.0179
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0005
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 6
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 32
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 250
47
+ - num_epochs: 30.0
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Per |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 11.0415 | 1.0 | 102 | 3.1505 | 1.0 |
54
+ | 3.1122 | 2.0 | 204 | 3.0968 | 1.0 |
55
+ | 3.0896 | 3.0 | 306 | 3.0042 | 1.0 |
56
+ | 2.953 | 4.0 | 408 | 2.8056 | 1.0 |
57
+ | 2.444 | 5.0 | 510 | 1.7510 | 0.6859 |
58
+ | 1.1295 | 6.0 | 612 | 0.3595 | 0.1672 |
59
+ | 0.3895 | 7.0 | 714 | 0.1119 | 0.0782 |
60
+ | 0.2175 | 8.0 | 816 | 0.0607 | 0.0477 |
61
+ | 0.1353 | 9.0 | 918 | 0.0317 | 0.0247 |
62
+ | 0.0946 | 10.0 | 1020 | 0.0288 | 0.0286 |
63
+ | 0.0835 | 11.0 | 1122 | 0.0291 | 0.0370 |
64
+ | 0.0673 | 12.0 | 1224 | 0.0231 | 0.0261 |
65
+ | 0.0583 | 13.0 | 1326 | 0.0181 | 0.0199 |
66
+ | 0.0444 | 14.0 | 1428 | 0.0190 | 0.0266 |
67
+ | 0.041 | 15.0 | 1530 | 0.0134 | 0.0254 |
68
+ | 0.0357 | 16.0 | 1632 | 0.0122 | 0.0233 |
69
+ | 0.0301 | 17.0 | 1734 | 0.0098 | 0.0338 |
70
+ | 0.0265 | 18.0 | 1836 | 0.0099 | 0.0241 |
71
+ | 0.0241 | 19.0 | 1938 | 0.0098 | 0.0207 |
72
+ | 0.0258 | 20.0 | 2040 | 0.0089 | 0.0203 |
73
+ | 0.0234 | 21.0 | 2142 | 0.0104 | 0.0242 |
74
+ | 0.0193 | 22.0 | 2244 | 0.0126 | 0.0301 |
75
+ | 0.0186 | 23.0 | 2346 | 0.0073 | 0.0274 |
76
+ | 0.0155 | 24.0 | 2448 | 0.0073 | 0.0238 |
77
+ | 0.0143 | 25.0 | 2550 | 0.0056 | 0.0164 |
78
+ | 0.0134 | 26.0 | 2652 | 0.0060 | 0.0199 |
79
+ | 0.012 | 27.0 | 2754 | 0.0052 | 0.0206 |
80
+ | 0.0122 | 28.0 | 2856 | 0.0054 | 0.0179 |
81
+ | 0.0105 | 29.0 | 2958 | 0.0055 | 0.0188 |
82
+ | 0.0098 | 30.0 | 3060 | 0.0054 | 0.0179 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.32.1
88
+ - Pytorch 2.0.1+cu118
89
+ - Datasets 1.18.3
90
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:139f0fce4ec340eee33fa80a906854cf7751c25e08ccff5b7d77691af4d4fbb6
3
  size 1262053549
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ae097ec3beeb1f11ed79043f35785cced8d69272bd1f91612f5d6fab4bd4b5
3
  size 1262053549