Hugging Face's logo

Hellina
/
es_ar

TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
Hellina commited on
Commit
36c2bf1
·
verified ·
1 Parent(s): 8b01d70

Model save

Browse files
Files changed (3) hide show
  1. README.md +99 -0
  2. model.safetensors +1 -1
  3. runs/Sep10_08-03-21_tripel/events.out.tfevents.1725980722.tripel.3145360.0 +2 -2
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-xls-r-300m
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: es_ar
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # es_ar
17
+
18
+ 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.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4940
21
+ - Wer: 0.3263
22
+ - Cer: 0.2414
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0003
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 16
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 500
48
+ - num_epochs: 15.0
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
54
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
55
+ | 3.6158 | 0.4 | 500 | 3.7004 | 0.9886 | 0.9625 |
56
+ | 1.0731 | 0.8 | 1000 | 1.0090 | 0.7501 | 0.4066 |
57
+ | 0.7529 | 1.2 | 1500 | 0.7609 | 0.6195 | 0.3460 |
58
+ | 0.6441 | 1.6 | 2000 | 0.6322 | 0.5524 | 0.3171 |
59
+ | 0.607 | 2.0 | 2500 | 0.5795 | 0.5202 | 0.3065 |
60
+ | 0.4744 | 2.4 | 3000 | 0.5848 | 0.5096 | 0.3056 |
61
+ | 0.4604 | 2.8 | 3500 | 0.5341 | 0.4666 | 0.2907 |
62
+ | 0.3763 | 3.2 | 4000 | 0.5060 | 0.4416 | 0.2812 |
63
+ | 0.3952 | 3.6 | 4500 | 0.5214 | 0.4566 | 0.2850 |
64
+ | 0.3962 | 4.0 | 5000 | 0.4890 | 0.4324 | 0.2784 |
65
+ | 0.3137 | 4.4 | 5500 | 0.4833 | 0.4165 | 0.2713 |
66
+ | 0.316 | 4.8 | 6000 | 0.5005 | 0.4182 | 0.2738 |
67
+ | 0.2721 | 5.2 | 6500 | 0.4961 | 0.4171 | 0.2732 |
68
+ | 0.2561 | 5.6 | 7000 | 0.4742 | 0.3997 | 0.2645 |
69
+ | 0.2854 | 6.0 | 7500 | 0.4600 | 0.3991 | 0.2662 |
70
+ | 0.2599 | 6.4 | 8000 | 0.4541 | 0.4022 | 0.2659 |
71
+ | 0.2249 | 6.8 | 8500 | 0.4586 | 0.3911 | 0.2615 |
72
+ | 0.1931 | 7.2 | 9000 | 0.4721 | 0.3871 | 0.2614 |
73
+ | 0.195 | 7.6 | 9500 | 0.4636 | 0.3898 | 0.2608 |
74
+ | 0.1991 | 8.0 | 10000 | 0.4259 | 0.3716 | 0.2555 |
75
+ | 0.1657 | 8.4 | 10500 | 0.4548 | 0.3714 | 0.2573 |
76
+ | 0.1802 | 8.8 | 11000 | 0.4540 | 0.3582 | 0.2526 |
77
+ | 0.1359 | 9.2 | 11500 | 0.4685 | 0.3652 | 0.2552 |
78
+ | 0.1419 | 9.6 | 12000 | 0.4524 | 0.3561 | 0.2512 |
79
+ | 0.1531 | 10.0 | 12500 | 0.4443 | 0.3578 | 0.2514 |
80
+ | 0.1313 | 10.4 | 13000 | 0.4536 | 0.3536 | 0.2495 |
81
+ | 0.1269 | 10.8 | 13500 | 0.4563 | 0.3517 | 0.2480 |
82
+ | 0.102 | 11.2 | 14000 | 0.4606 | 0.3424 | 0.2476 |
83
+ | 0.103 | 11.6 | 14500 | 0.4611 | 0.3489 | 0.2477 |
84
+ | 0.1088 | 12.0 | 15000 | 0.4505 | 0.3362 | 0.2447 |
85
+ | 0.0917 | 12.4 | 15500 | 0.4741 | 0.3404 | 0.2458 |
86
+ | 0.0847 | 12.8 | 16000 | 0.4714 | 0.3340 | 0.2440 |
87
+ | 0.0768 | 13.2 | 16500 | 0.4943 | 0.3286 | 0.2427 |
88
+ | 0.0789 | 13.6 | 17000 | 0.4813 | 0.3308 | 0.2429 |
89
+ | 0.0797 | 14.0 | 17500 | 0.4861 | 0.3288 | 0.2423 |
90
+ | 0.0698 | 14.4 | 18000 | 0.5003 | 0.3271 | 0.2416 |
91
+ | 0.0686 | 14.8 | 18500 | 0.4940 | 0.3263 | 0.2414 |
92
+
93
+
94
+ ### Framework versions
95
+
96
+ - Transformers 4.36.2
97
+ - Pytorch 1.13.0+cu116
98
+ - Datasets 2.15.0
99
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:270d37c619d580dd9488d147a80e37d478c6d71093f486bb43818b3cbafd24fe
3
  size 1262828340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82dc310e47a89124aeaa8554efce11e483ec72e3b63bedb6afd1679cd99f3f51
3
  size 1262828340
runs/Sep10_08-03-21_tripel/events.out.tfevents.1725980722.tripel.3145360.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da2d018f858a03a9817ee8290e20e70235648621aa0bd52b4c9069d062083165
3
- size 75683
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eda8c082bb6fc60dcc5b60217299f9fc7b59984110c846bff2a7003dc5dc565
3
+ size 78815