Hugging Face's logo

BauyrjanQ
/
wav2vec2-large-mms-1b-kazakh-speech2ner-kscsyn-8b-4ep

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
BauyrjanQ commited on
Commit
1630581
•
1 Parent(s): 9072dad

End of training

Browse files
Files changed (1) hide show
  1. README.md +115 -0
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: facebook/mms-1b-all
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: wav2vec2-large-mms-1b-kazakh-speech2ner-kscsyn-8b-4ep
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
+ # wav2vec2-large-mms-1b-kazakh-speech2ner-kscsyn-8b-4ep
17
+
18
+ This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: nan
21
+ - Wer: 1.0
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 1000
48
+ - num_epochs: 4
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:------:|:---------------:|:------:|
54
+ | 6.6358 | 0.07 | 2000 | 6.5080 | 1.0000 |
55
+ | 6.6338 | 0.15 | 4000 | 6.5080 | 1.0000 |
56
+ | 0.0 | 0.22 | 6000 | nan | 1.0 |
57
+ | 0.0 | 0.3 | 8000 | nan | 1.0 |
58
+ | 0.0 | 0.37 | 10000 | nan | 1.0 |
59
+ | 0.0 | 0.44 | 12000 | nan | 1.0 |
60
+ | 0.0 | 0.52 | 14000 | nan | 1.0 |
61
+ | 0.0 | 0.59 | 16000 | nan | 1.0 |
62
+ | 0.0 | 0.66 | 18000 | nan | 1.0 |
63
+ | 0.0 | 0.74 | 20000 | nan | 1.0 |
64
+ | 0.0 | 0.81 | 22000 | nan | 1.0 |
65
+ | 0.0 | 0.89 | 24000 | nan | 1.0 |
66
+ | 0.0 | 0.96 | 26000 | nan | 1.0 |
67
+ | 0.0 | 1.03 | 28000 | nan | 1.0 |
68
+ | 0.0 | 1.11 | 30000 | nan | 1.0 |
69
+ | 0.0 | 1.18 | 32000 | nan | 1.0 |
70
+ | 0.0 | 1.25 | 34000 | nan | 1.0 |
71
+ | 0.0 | 1.33 | 36000 | nan | 1.0 |
72
+ | 0.0 | 1.4 | 38000 | nan | 1.0 |
73
+ | 0.0 | 1.48 | 40000 | nan | 1.0 |
74
+ | 0.0 | 1.55 | 42000 | nan | 1.0 |
75
+ | 0.0 | 1.62 | 44000 | nan | 1.0 |
76
+ | 0.0 | 1.7 | 46000 | nan | 1.0 |
77
+ | 0.0 | 1.77 | 48000 | nan | 1.0 |
78
+ | 0.0 | 1.84 | 50000 | nan | 1.0 |
79
+ | 0.0 | 1.92 | 52000 | nan | 1.0 |
80
+ | 0.0 | 1.99 | 54000 | nan | 1.0 |
81
+ | 0.0 | 2.07 | 56000 | nan | 1.0 |
82
+ | 0.0 | 2.14 | 58000 | nan | 1.0 |
83
+ | 0.0 | 2.21 | 60000 | nan | 1.0 |
84
+ | 0.0 | 2.29 | 62000 | nan | 1.0 |
85
+ | 0.0 | 2.36 | 64000 | nan | 1.0 |
86
+ | 0.0 | 2.43 | 66000 | nan | 1.0 |
87
+ | 0.0 | 2.51 | 68000 | nan | 1.0 |
88
+ | 0.0 | 2.58 | 70000 | nan | 1.0 |
89
+ | 0.0 | 2.66 | 72000 | nan | 1.0 |
90
+ | 0.0 | 2.73 | 74000 | nan | 1.0 |
91
+ | 0.0 | 2.8 | 76000 | nan | 1.0 |
92
+ | 0.0 | 2.88 | 78000 | nan | 1.0 |
93
+ | 0.0 | 2.95 | 80000 | nan | 1.0 |
94
+ | 0.0 | 3.02 | 82000 | nan | 1.0 |
95
+ | 0.0 | 3.1 | 84000 | nan | 1.0 |
96
+ | 0.0 | 3.17 | 86000 | nan | 1.0 |
97
+ | 0.0 | 3.25 | 88000 | nan | 1.0 |
98
+ | 0.0 | 3.32 | 90000 | nan | 1.0 |
99
+ | 0.0 | 3.39 | 92000 | nan | 1.0 |
100
+ | 0.0 | 3.47 | 94000 | nan | 1.0 |
101
+ | 0.0 | 3.54 | 96000 | nan | 1.0 |
102
+ | 0.0 | 3.61 | 98000 | nan | 1.0 |
103
+ | 0.0 | 3.69 | 100000 | nan | 1.0 |
104
+ | 0.0 | 3.76 | 102000 | nan | 1.0 |
105
+ | 0.0 | 3.84 | 104000 | nan | 1.0 |
106
+ | 0.0 | 3.91 | 106000 | nan | 1.0 |
107
+ | 0.0 | 3.98 | 108000 | nan | 1.0 |
108
+
109
+
110
+ ### Framework versions
111
+
112
+ - Transformers 4.33.0.dev0
113
+ - Pytorch 2.0.1+cu117
114
+ - Datasets 2.13.1
115
+ - Tokenizers 0.13.3