Hugging Face's logo

Ussen
/
wav2vec2-mms-1b-all-swc-kat6

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Model card Files
xet
Community
Ussen commited on
Commit
46c0ac7
·
1 Parent(s): 49be5c4

End of training

Browse files
Files changed (3) hide show
  1. README.md +129 -0
  2. adapter.swc.safetensors +3 -0
  3. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: facebook/mms-1b-all
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - audiofolder
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: wav2vec2-mms-1b-all-swc-kat6
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: audiofolder
18
+ type: audiofolder
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.37098445595854923
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # wav2vec2-mms-1b-all-swc-kat6
32
+
33
+ This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the audiofolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: inf
36
+ - Wer: 0.3710
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 0.001
56
+ - train_batch_size: 1
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 400
62
+ - num_epochs: 4
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
68
+ | 2.8349 | 0.07 | 400 | inf | 0.4899 |
69
+ | 0.8039 | 0.15 | 800 | inf | 0.4912 |
70
+ | 0.7335 | 0.22 | 1200 | inf | 0.4482 |
71
+ | 0.8395 | 0.3 | 1600 | inf | 0.4829 |
72
+ | 0.7626 | 0.37 | 2000 | inf | 0.4635 |
73
+ | 0.9035 | 0.44 | 2400 | inf | 0.4391 |
74
+ | 0.6281 | 0.52 | 2800 | inf | 0.4668 |
75
+ | 0.6756 | 0.59 | 3200 | inf | 0.4254 |
76
+ | 0.7866 | 0.67 | 3600 | inf | 0.4168 |
77
+ | 0.7413 | 0.74 | 4000 | inf | 0.4168 |
78
+ | 0.749 | 0.81 | 4400 | inf | 0.4148 |
79
+ | 0.8165 | 0.89 | 4800 | inf | 0.4241 |
80
+ | 0.7302 | 0.96 | 5200 | inf | 0.4124 |
81
+ | 0.7376 | 1.04 | 5600 | inf | 0.4368 |
82
+ | 0.6833 | 1.11 | 6000 | inf | 0.3953 |
83
+ | 0.6463 | 1.19 | 6400 | inf | 0.4363 |
84
+ | 0.7236 | 1.26 | 6800 | inf | 0.4383 |
85
+ | 0.8837 | 1.33 | 7200 | inf | 0.4811 |
86
+ | 0.6854 | 1.41 | 7600 | inf | 0.3930 |
87
+ | 0.6985 | 1.48 | 8000 | inf | 0.3979 |
88
+ | 0.7139 | 1.56 | 8400 | inf | 0.3977 |
89
+ | 0.6338 | 1.63 | 8800 | inf | 0.4039 |
90
+ | 0.7227 | 1.7 | 9200 | inf | 0.3922 |
91
+ | 0.6843 | 1.78 | 9600 | inf | 0.4111 |
92
+ | 0.6948 | 1.85 | 10000 | inf | 0.4093 |
93
+ | 0.6867 | 1.93 | 10400 | inf | 0.3927 |
94
+ | 0.5753 | 2.0 | 10800 | inf | 0.4080 |
95
+ | 0.6865 | 2.07 | 11200 | inf | 0.3938 |
96
+ | 0.6155 | 2.15 | 11600 | inf | 0.3920 |
97
+ | 0.6743 | 2.22 | 12000 | inf | 0.3977 |
98
+ | 0.5801 | 2.3 | 12400 | inf | 0.3801 |
99
+ | 0.8216 | 2.37 | 12800 | inf | 0.3917 |
100
+ | 0.6199 | 2.44 | 13200 | inf | 0.4052 |
101
+ | 0.6268 | 2.52 | 13600 | inf | 0.3811 |
102
+ | 0.6505 | 2.59 | 14000 | inf | 0.3855 |
103
+ | 0.6578 | 2.67 | 14400 | inf | 0.3933 |
104
+ | 0.6442 | 2.74 | 14800 | inf | 0.3868 |
105
+ | 0.5904 | 2.81 | 15200 | inf | 0.3782 |
106
+ | 0.6249 | 2.89 | 15600 | inf | 0.3788 |
107
+ | 0.5879 | 2.96 | 16000 | inf | 0.3904 |
108
+ | 0.4844 | 3.04 | 16400 | inf | 0.3728 |
109
+ | 0.6309 | 3.11 | 16800 | inf | 0.3687 |
110
+ | 0.5825 | 3.19 | 17200 | inf | 0.3663 |
111
+ | 0.7171 | 3.26 | 17600 | inf | 0.3772 |
112
+ | 0.5471 | 3.33 | 18000 | inf | 0.3718 |
113
+ | 0.5029 | 3.41 | 18400 | inf | 0.3756 |
114
+ | 0.5605 | 3.48 | 18800 | inf | 0.3751 |
115
+ | 0.5582 | 3.56 | 19200 | inf | 0.3728 |
116
+ | 0.6358 | 3.63 | 19600 | inf | 0.3712 |
117
+ | 0.4977 | 3.7 | 20000 | inf | 0.3655 |
118
+ | 0.4828 | 3.78 | 20400 | inf | 0.3671 |
119
+ | 0.6554 | 3.85 | 20800 | inf | 0.3689 |
120
+ | 0.561 | 3.93 | 21200 | inf | 0.3702 |
121
+ | 0.5515 | 4.0 | 21600 | inf | 0.3710 |
122
+
123
+
124
+ ### Framework versions
125
+
126
+ - Transformers 4.33.0.dev0
127
+ - Pytorch 1.13.1+cu117
128
+ - Datasets 2.13.1
129
+ - Tokenizers 0.12.1
adapter.swc.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6af6fc7f630611b2da397657469bc88101092354e8b03bd125fa77deaac334
3
+ size 8808780
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dd86872c31aa08abbe0c578b3fe471036b3d0a19919d241f38e00023fbff975
3
  size 3859144845
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94606f9b61482593490ad0c3bafe8c73386e404d7bbf9742c9a122b34337993e
3
  size 3859144845