Hugging Face's logo

BauyrjanQ
/
wav2vec2-large-mms-1b-kazakh-speech2ner-ksc_synthetic-4b-10ep

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
BauyrjanQ commited on
Commit
d2d93db
·
1 Parent(s): cb7ee19

End of training

Browse files
Files changed (1) hide show
  1. README.md +128 -0
README.md ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-ksc_synthetic-4b-10ep
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-ksc_synthetic-4b-10ep
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: 4
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: 10
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:------:|:---------------:|:---:|
54
+ | 0.0 | 0.15 | 8000 | nan | 1.0 |
55
+ | 0.0 | 0.3 | 16000 | nan | 1.0 |
56
+ | 0.0 | 0.44 | 24000 | nan | 1.0 |
57
+ | 0.0 | 0.59 | 32000 | nan | 1.0 |
58
+ | 0.0 | 0.74 | 40000 | nan | 1.0 |
59
+ | 0.0 | 0.89 | 48000 | nan | 1.0 |
60
+ | 0.0 | 1.03 | 56000 | nan | 1.0 |
61
+ | 0.0 | 1.18 | 64000 | nan | 1.0 |
62
+ | 0.0 | 1.33 | 72000 | nan | 1.0 |
63
+ | 0.0 | 1.48 | 80000 | nan | 1.0 |
64
+ | 0.0 | 1.62 | 88000 | nan | 1.0 |
65
+ | 0.0 | 1.77 | 96000 | nan | 1.0 |
66
+ | 0.0 | 1.92 | 104000 | nan | 1.0 |
67
+ | 0.0 | 2.07 | 112000 | nan | 1.0 |
68
+ | 0.0 | 2.21 | 120000 | nan | 1.0 |
69
+ | 0.0 | 2.36 | 128000 | nan | 1.0 |
70
+ | 0.0 | 2.51 | 136000 | nan | 1.0 |
71
+ | 0.0 | 2.66 | 144000 | nan | 1.0 |
72
+ | 0.0 | 2.8 | 152000 | nan | 1.0 |
73
+ | 0.0 | 2.95 | 160000 | nan | 1.0 |
74
+ | 0.0 | 3.1 | 168000 | nan | 1.0 |
75
+ | 0.0 | 3.25 | 176000 | nan | 1.0 |
76
+ | 0.0 | 3.39 | 184000 | nan | 1.0 |
77
+ | 0.0 | 3.54 | 192000 | nan | 1.0 |
78
+ | 0.0 | 3.69 | 200000 | nan | 1.0 |
79
+ | 0.0 | 3.84 | 208000 | nan | 1.0 |
80
+ | 0.0 | 3.98 | 216000 | nan | 1.0 |
81
+ | 0.0 | 4.13 | 224000 | nan | 1.0 |
82
+ | 0.0 | 4.28 | 232000 | nan | 1.0 |
83
+ | 0.0 | 4.43 | 240000 | nan | 1.0 |
84
+ | 0.0 | 4.57 | 248000 | nan | 1.0 |
85
+ | 0.0 | 4.72 | 256000 | nan | 1.0 |
86
+ | 0.0 | 4.87 | 264000 | nan | 1.0 |
87
+ | 0.0 | 5.02 | 272000 | nan | 1.0 |
88
+ | 0.0 | 5.16 | 280000 | nan | 1.0 |
89
+ | 0.0 | 5.31 | 288000 | nan | 1.0 |
90
+ | 0.0 | 5.46 | 296000 | nan | 1.0 |
91
+ | 0.0 | 5.61 | 304000 | nan | 1.0 |
92
+ | 0.0 | 5.75 | 312000 | nan | 1.0 |
93
+ | 0.0 | 5.9 | 320000 | nan | 1.0 |
94
+ | 0.0 | 6.05 | 328000 | nan | 1.0 |
95
+ | 0.0 | 6.2 | 336000 | nan | 1.0 |
96
+ | 0.0 | 6.34 | 344000 | nan | 1.0 |
97
+ | 0.0 | 6.49 | 352000 | nan | 1.0 |
98
+ | 0.0 | 6.64 | 360000 | nan | 1.0 |
99
+ | 0.0 | 6.79 | 368000 | nan | 1.0 |
100
+ | 0.0 | 6.93 | 376000 | nan | 1.0 |
101
+ | 0.0 | 7.08 | 384000 | nan | 1.0 |
102
+ | 0.0 | 7.23 | 392000 | nan | 1.0 |
103
+ | 0.0 | 7.38 | 400000 | nan | 1.0 |
104
+ | 0.0 | 7.52 | 408000 | nan | 1.0 |
105
+ | 0.0 | 7.67 | 416000 | nan | 1.0 |
106
+ | 0.0 | 7.82 | 424000 | nan | 1.0 |
107
+ | 0.0 | 7.97 | 432000 | nan | 1.0 |
108
+ | 0.0 | 8.11 | 440000 | nan | 1.0 |
109
+ | 0.0 | 8.26 | 448000 | nan | 1.0 |
110
+ | 0.0 | 8.41 | 456000 | nan | 1.0 |
111
+ | 0.0 | 8.56 | 464000 | nan | 1.0 |
112
+ | 0.0 | 8.7 | 472000 | nan | 1.0 |
113
+ | 0.0 | 8.85 | 480000 | nan | 1.0 |
114
+ | 0.0 | 9.0 | 488000 | nan | 1.0 |
115
+ | 0.0 | 9.15 | 496000 | nan | 1.0 |
116
+ | 0.0 | 9.29 | 504000 | nan | 1.0 |
117
+ | 0.0 | 9.44 | 512000 | nan | 1.0 |
118
+ | 0.0 | 9.59 | 520000 | nan | 1.0 |
119
+ | 0.0 | 9.74 | 528000 | nan | 1.0 |
120
+ | 0.0 | 9.88 | 536000 | nan | 1.0 |
121
+
122
+
123
+ ### Framework versions
124
+
125
+ - Transformers 4.33.0.dev0
126
+ - Pytorch 2.0.1+cu117
127
+ - Datasets 2.13.1
128
+ - Tokenizers 0.13.3