Hugging Face's logo

utakumi
/
Hubert-common_voice-phoneme-debug-warmup500

Automatic Speech Recognition
Transformers
Safetensors
Japanese
hubert
mozilla-foundation/common_voice_13_0
Generated from Trainer
Inference Endpoints
Model card Files Community
utakumi commited on
Commit
9ec9194
·
verified ·
1 Parent(s): fc5af87

Model save

Browse files
Files changed (2) hide show
  1. README.md +107 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: rinna/japanese-hubert-base
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: Hubert-common_voice-phoneme-debug-warmup500
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Hubert-common_voice-phoneme-debug-warmup500
18
+
19
+ This model is a fine-tuned version of [rinna/japanese-hubert-base](https://huggingface.co/rinna/japanese-hubert-base) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.9678
22
+ - Wer: 1.0
23
+ - Cer: 0.9851
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.0003
43
+ - train_batch_size: 16
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 32
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_steps: 500
51
+ - num_epochs: 30.0
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
57
+ |:-------------:|:-------:|:----:|:---------------:|:---:|:------:|
58
+ | No log | 0.7092 | 100 | 4.5669 | 1.0 | 0.9851 |
59
+ | No log | 1.4184 | 200 | 3.0119 | 1.0 | 0.9851 |
60
+ | No log | 2.1277 | 300 | 2.9840 | 1.0 | 0.9851 |
61
+ | No log | 2.8369 | 400 | 2.9764 | 1.0 | 0.9851 |
62
+ | 3.973 | 3.5461 | 500 | 2.9796 | 1.0 | 0.9851 |
63
+ | 3.973 | 4.2553 | 600 | 2.9758 | 1.0 | 0.9851 |
64
+ | 3.973 | 4.9645 | 700 | 2.9691 | 1.0 | 0.9851 |
65
+ | 3.973 | 5.6738 | 800 | 2.9858 | 1.0 | 0.9850 |
66
+ | 3.973 | 6.3830 | 900 | 2.9692 | 1.0 | 0.9851 |
67
+ | 2.9654 | 7.0922 | 1000 | 2.9895 | 1.0 | 0.9850 |
68
+ | 2.9654 | 7.8014 | 1100 | 2.9725 | 1.0 | 0.9850 |
69
+ | 2.9654 | 8.5106 | 1200 | 2.9713 | 1.0 | 0.9850 |
70
+ | 2.9654 | 9.2199 | 1300 | 2.9758 | 1.0 | 0.9851 |
71
+ | 2.9654 | 9.9291 | 1400 | 2.9784 | 1.0 | 0.9850 |
72
+ | 2.9643 | 10.6383 | 1500 | 2.9687 | 1.0 | 0.9851 |
73
+ | 2.9643 | 11.3475 | 1600 | 2.9779 | 1.0 | 0.9851 |
74
+ | 2.9643 | 12.0567 | 1700 | 2.9679 | 1.0 | 0.9850 |
75
+ | 2.9643 | 12.7660 | 1800 | 2.9769 | 1.0 | 0.9851 |
76
+ | 2.9643 | 13.4752 | 1900 | 2.9718 | 1.0 | 0.9851 |
77
+ | 2.9631 | 14.1844 | 2000 | 2.9686 | 1.0 | 0.9851 |
78
+ | 2.9631 | 14.8936 | 2100 | 2.9706 | 1.0 | 0.9850 |
79
+ | 2.9631 | 15.6028 | 2200 | 2.9791 | 1.0 | 0.9851 |
80
+ | 2.9631 | 16.3121 | 2300 | 2.9731 | 1.0 | 0.9851 |
81
+ | 2.9631 | 17.0213 | 2400 | 2.9722 | 1.0 | 0.9850 |
82
+ | 2.9627 | 17.7305 | 2500 | 2.9723 | 1.0 | 0.9851 |
83
+ | 2.9627 | 18.4397 | 2600 | 2.9689 | 1.0 | 0.9851 |
84
+ | 2.9627 | 19.1489 | 2700 | 2.9747 | 1.0 | 0.9851 |
85
+ | 2.9627 | 19.8582 | 2800 | 2.9801 | 1.0 | 0.9851 |
86
+ | 2.9627 | 20.5674 | 2900 | 2.9740 | 1.0 | 0.9851 |
87
+ | 2.9622 | 21.2766 | 3000 | 2.9736 | 1.0 | 0.9850 |
88
+ | 2.9622 | 21.9858 | 3100 | 2.9719 | 1.0 | 0.9851 |
89
+ | 2.9622 | 22.6950 | 3200 | 2.9710 | 1.0 | 0.9850 |
90
+ | 2.9622 | 23.4043 | 3300 | 2.9714 | 1.0 | 0.9850 |
91
+ | 2.9622 | 24.1135 | 3400 | 2.9701 | 1.0 | 0.9851 |
92
+ | 2.9609 | 24.8227 | 3500 | 2.9695 | 1.0 | 0.9851 |
93
+ | 2.9609 | 25.5319 | 3600 | 2.9669 | 1.0 | 0.9850 |
94
+ | 2.9609 | 26.2411 | 3700 | 2.9774 | 1.0 | 0.9851 |
95
+ | 2.9609 | 26.9504 | 3800 | 2.9712 | 1.0 | 0.9851 |
96
+ | 2.9609 | 27.6596 | 3900 | 2.9701 | 1.0 | 0.9851 |
97
+ | 2.962 | 28.3688 | 4000 | 2.9689 | 1.0 | 0.9851 |
98
+ | 2.962 | 29.0780 | 4100 | 2.9738 | 1.0 | 0.9850 |
99
+ | 2.962 | 29.7872 | 4200 | 2.9678 | 1.0 | 0.9851 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - Transformers 4.47.0.dev0
105
+ - Pytorch 2.5.1+cu124
106
+ - Datasets 3.1.0
107
+ - Tokenizers 0.20.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cae9878138a094ff11b628360b7ad43a6e0983a8b8fb3ce61559b8a04a6df8ae
3
  size 377644548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:991cb742d3e2a2f3ab781c923e86eab264624e9c2935aa49c3c39c22992e497c
3
  size 377644548