ylacombe HF staff commited on
Commit
067b8ec
1 Parent(s): 43dac66

End of training

Browse files
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ylacombe/w2v-bert-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_16_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: w2v-bert-2.0-600m-turkish-colab
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: common_voice_16_0
17
+ type: common_voice_16_0
18
+ config: tr
19
+ split: test
20
+ args: tr
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 0.13727393664832993
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
+ # w2v-bert-2.0-600m-turkish-colab
31
+
32
+ This model is a fine-tuned version of [ylacombe/w2v-bert-2.0](https://huggingface.co/ylacombe/w2v-bert-2.0) on the common_voice_16_0 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.1441
35
+ - Wer: 0.1373
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: 0.0001
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: 1000
63
+ - num_epochs: 5
64
+ - mixed_precision_training: Native AMP
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 0.252 | 0.29 | 400 | 0.3121 | 0.3150 |
71
+ | 0.2541 | 0.58 | 800 | 0.3786 | 0.3441 |
72
+ | 0.2505 | 0.88 | 1200 | 0.4106 | 0.3766 |
73
+ | 0.1958 | 1.17 | 1600 | 0.2974 | 0.2877 |
74
+ | 0.1686 | 1.46 | 2000 | 0.2854 | 0.2736 |
75
+ | 0.1498 | 1.75 | 2400 | 0.2508 | 0.2486 |
76
+ | 0.1343 | 2.05 | 2800 | 0.2315 | 0.2263 |
77
+ | 0.1045 | 2.34 | 3200 | 0.2207 | 0.2243 |
78
+ | 0.0983 | 2.63 | 3600 | 0.2109 | 0.2046 |
79
+ | 0.089 | 2.92 | 4000 | 0.1970 | 0.1896 |
80
+ | 0.0726 | 3.21 | 4400 | 0.1963 | 0.1799 |
81
+ | 0.0552 | 3.51 | 4800 | 0.1879 | 0.1778 |
82
+ | 0.0573 | 3.8 | 5200 | 0.1821 | 0.1693 |
83
+ | 0.0421 | 4.09 | 5600 | 0.1602 | 0.1517 |
84
+ | 0.0363 | 4.38 | 6000 | 0.1564 | 0.1485 |
85
+ | 0.0345 | 4.67 | 6400 | 0.1466 | 0.1437 |
86
+ | 0.0294 | 4.97 | 6800 | 0.1441 | 0.1373 |
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - Transformers 4.37.0.dev0
92
+ - Pytorch 2.1.0+cu121
93
+ - Datasets 2.16.1
94
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be98bbf2a0021fc10544e76a15820bcca0c1b4f0504913da0871d756ebe80432
3
  size 2422994960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbe3cb8a7bf4b9df98952a68992d3ba5f99bc94fe3b1c27f6a8cafa7a17bd179
3
  size 2422994960
runs/Jan09_13-05-45_ed9085e82d2d/events.out.tfevents.1704806071.ed9085e82d2d.32553.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3277356146d396f2e15dd580b42aa788a8af7f23a1807cb888a54ffb7468dd45
3
- size 15760
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b88f82078cadd212fe1facf0f0250982558a6a45fd7b1957ad65e4c410d808cc
3
+ size 16746