batoula187
commited on
Commit
•
dd4d4b1
1
Parent(s):
30c41f4
End of training
Browse files
README.md
CHANGED
@@ -1,12 +1,27 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
-
base_model: batoula187/wav2vec2-large-xls-r-300m-arabic-colab
|
5 |
datasets:
|
6 |
-
-
|
|
|
|
|
7 |
model-index:
|
8 |
- name: wav2vec2-large-xls-r-300m-arabic-colab
|
9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -14,15 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# wav2vec2-large-xls-r-300m-arabic-colab
|
16 |
|
17 |
-
This model is a fine-tuned version of [batoula187/wav2vec2-large-xls-r-300m-arabic-colab](https://huggingface.co/batoula187/wav2vec2-large-xls-r-300m-arabic-colab) on the
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
-
|
20 |
-
-
|
21 |
-
- eval_runtime: 98.1821
|
22 |
-
- eval_samples_per_second: 15.94
|
23 |
-
- eval_steps_per_second: 1.996
|
24 |
-
- epoch: 19.2817
|
25 |
-
- step: 3400
|
26 |
|
27 |
## Model description
|
28 |
|
@@ -53,9 +63,32 @@ The following hyperparameters were used during training:
|
|
53 |
- num_epochs: 30
|
54 |
- mixed_precision_training: Native AMP
|
55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
### Framework versions
|
57 |
|
58 |
-
- Transformers 4.41.
|
59 |
- Pytorch 2.3.0+cu121
|
60 |
-
- Datasets 2.19.
|
61 |
- Tokenizers 0.19.1
|
|
|
1 |
---
|
2 |
+
base_model: batoula187/wav2vec2-large-xls-r-300m-arabic-colab
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
5 |
datasets:
|
6 |
+
- common_voice_17_0
|
7 |
+
metrics:
|
8 |
+
- wer
|
9 |
model-index:
|
10 |
- name: wav2vec2-large-xls-r-300m-arabic-colab
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Automatic Speech Recognition
|
14 |
+
type: automatic-speech-recognition
|
15 |
+
dataset:
|
16 |
+
name: common_voice_17_0
|
17 |
+
type: common_voice_17_0
|
18 |
+
config: ar
|
19 |
+
split: test[:10%]
|
20 |
+
args: ar
|
21 |
+
metrics:
|
22 |
+
- name: Wer
|
23 |
+
type: wer
|
24 |
+
value: 0.627304825421734
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
29 |
|
30 |
# wav2vec2-large-xls-r-300m-arabic-colab
|
31 |
|
32 |
+
This model is a fine-tuned version of [batoula187/wav2vec2-large-xls-r-300m-arabic-colab](https://huggingface.co/batoula187/wav2vec2-large-xls-r-300m-arabic-colab) on the common_voice_17_0 dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 1.5330
|
35 |
+
- Wer: 0.6273
|
|
|
|
|
|
|
|
|
|
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
63 |
- num_epochs: 30
|
64 |
- mixed_precision_training: Native AMP
|
65 |
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
+
|:-------------:|:-------:|:----:|:---------------:|:------:|
|
70 |
+
| 0.0457 | 1.6901 | 200 | 1.5030 | 0.6377 |
|
71 |
+
| 0.0408 | 3.3803 | 400 | 1.4683 | 0.6503 |
|
72 |
+
| 0.0693 | 5.0704 | 600 | 1.6023 | 0.6897 |
|
73 |
+
| 0.0766 | 6.7606 | 800 | 1.3947 | 0.6709 |
|
74 |
+
| 0.0653 | 8.4507 | 1000 | 1.5052 | 0.6858 |
|
75 |
+
| 0.0542 | 10.1408 | 1200 | 1.6550 | 0.6999 |
|
76 |
+
| 0.0535 | 11.8310 | 1400 | 1.4820 | 0.6591 |
|
77 |
+
| 0.0645 | 13.5211 | 1600 | 1.5134 | 0.6732 |
|
78 |
+
| 0.0583 | 15.2113 | 1800 | 1.4606 | 0.6561 |
|
79 |
+
| 0.0551 | 16.9014 | 2000 | 1.4476 | 0.6534 |
|
80 |
+
| 0.0462 | 18.5915 | 2200 | 1.5556 | 0.6557 |
|
81 |
+
| 0.0447 | 20.2817 | 2400 | 1.5289 | 0.6503 |
|
82 |
+
| 0.0395 | 21.9718 | 2600 | 1.5145 | 0.6434 |
|
83 |
+
| 0.0327 | 23.6620 | 2800 | 1.5916 | 0.6475 |
|
84 |
+
| 0.0317 | 25.3521 | 3000 | 1.5830 | 0.6526 |
|
85 |
+
| 0.0276 | 27.0423 | 3200 | 1.5935 | 0.6432 |
|
86 |
+
| 0.026 | 28.7324 | 3400 | 1.5330 | 0.6273 |
|
87 |
+
|
88 |
+
|
89 |
### Framework versions
|
90 |
|
91 |
+
- Transformers 4.41.2
|
92 |
- Pytorch 2.3.0+cu121
|
93 |
+
- Datasets 2.19.2
|
94 |
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262180580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae69779b53dc4e18e80920e749611d43cca11eafdd04c5637e38b6d6208e56af
|
3 |
size 1262180580
|
runs/Jun10_10-56-35_da1d3259a50a/events.out.tfevents.1718017094.da1d3259a50a.924.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e76528bce524a30cc5f78cd36ac1972b98591829b5b141a73725b73f01b7371
|
3 |
+
size 15685
|