Hugging Face's logo

ctaguchi
/
w2v-bert-2.0-gui-ufe

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2-bert
Generated from Trainer
Model card Files
xet
 Community
ctaguchi commited on
Commit
cc6833c
·
verified ·
1 Parent(s): d09e50c

Model save

Browse files
Files changed (2) hide show
  1. README.md +85 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: facebook/w2v-bert-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: w2v-bert-2.0-gui-ufe
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # w2v-bert-2.0-gui-ufe
16
+
17
+ This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 2.9936
20
+ - Cer: 0.9839
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0003
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 16
45
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 500
48
+ - num_epochs: 10
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
54
+ |:-------------:|:------:|:----:|:---------------:|:------:|
55
+ | 20.8559 | 0.4329 | 100 | 6.4232 | 1.0 |
56
+ | 9.4526 | 0.8658 | 200 | 3.0903 | 1.0 |
57
+ | 5.9844 | 1.2987 | 300 | 2.9298 | 0.9839 |
58
+ | 5.8764 | 1.7316 | 400 | 2.9116 | 0.9839 |
59
+ | 6.0712 | 2.1645 | 500 | 2.9086 | 0.9839 |
60
+ | 5.9242 | 2.5974 | 600 | 2.9054 | 0.9839 |
61
+ | 5.9342 | 3.0303 | 700 | 2.8994 | 0.9672 |
62
+ | 5.8950 | 3.4632 | 800 | 2.9021 | 0.9672 |
63
+ | 5.8858 | 3.8961 | 900 | 2.8836 | 0.9564 |
64
+ | 5.8643 | 4.3290 | 1000 | 2.8842 | 0.9534 |
65
+ | 5.8924 | 4.7619 | 1100 | 2.8827 | 0.9564 |
66
+ | 5.9962 | 5.1948 | 1200 | 2.8866 | 0.9534 |
67
+ | 5.9483 | 5.6277 | 1300 | 2.9003 | 0.9839 |
68
+ | 6.2299 | 6.0606 | 1400 | 2.9700 | 0.9839 |
69
+ | 6.0203 | 6.4935 | 1500 | 2.9172 | 1.0 |
70
+ | 5.9405 | 6.9264 | 1600 | 2.9279 | 1.0 |
71
+ | 6.0172 | 7.3593 | 1700 | 2.9474 | 0.9839 |
72
+ | 6.0484 | 7.7922 | 1800 | 2.9436 | 0.9839 |
73
+ | 5.9753 | 8.2251 | 1900 | 2.9706 | 0.9839 |
74
+ | 6.0714 | 8.6580 | 2000 | 2.9838 | 0.9839 |
75
+ | 6.0902 | 9.0909 | 2100 | 2.9932 | 0.9839 |
76
+ | 6.0858 | 9.5238 | 2200 | 2.9935 | 0.9839 |
77
+ | 6.0465 | 9.9567 | 2300 | 2.9936 | 0.9839 |
78
+
79
+
80
+ ### Framework versions
81
+
82
+ - Transformers 5.1.0
83
+ - Pytorch 2.9.1+cu128
84
+ - Datasets 3.6.0
85
+ - Tokenizers 0.22.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:483babe9f181e73eeb10244ff5625fe7c8e4f8b9f2f350b654e160b10d637d10
3
  size 2322234612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e96662a0cd001e852217b7b47dc24f657b984f3b339c932c768d96c02265bd6
3
  size 2322234612