Hugging Face's logo

kiranpantha
/
wav2vec2-large-xls-r-300m-nepali

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Nepali
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
kiranpantha commited on
Commit
f97b638
•
1 Parent(s): 06a2158

End of training

Browse files
Files changed (1) hide show
  1. README.md +51 -63
README.md CHANGED
@@ -1,40 +1,42 @@
1
  ---
2
- base_model: facebook/wav2vec2-xls-r-300m
3
- datasets:
4
- - arrow
5
  library_name: transformers
 
 
6
  license: apache-2.0
7
- metrics:
8
- - wer
9
  tags:
10
  - generated_from_trainer
 
 
 
 
11
  model-index:
12
- - name: wav2vec2-large-xls-r-300m-nepali
13
  results:
14
  - task:
15
- type: automatic-speech-recognition
16
  name: Automatic Speech Recognition
 
17
  dataset:
18
- name: arrow
19
- type: arrow
20
  config: default
21
  split: test
22
- args: default
23
  metrics:
24
- - type: wer
25
- value: 0.3861111111111111
26
- name: Wer
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
  should probably proofread and complete it, then remove this comment. -->
31
 
32
- # wav2vec2-large-xls-r-300m-nepali
33
 
34
- This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the arrow dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.4180
37
- - Wer: 0.3861
38
 
39
  ## Model description
40
 
@@ -53,66 +55,52 @@ More information needed
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
- - learning_rate: 0.0003
57
  - train_batch_size: 8
58
  - eval_batch_size: 8
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_steps: 500
63
- - num_epochs: 10
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Wer |
69
- |:-------------:|:------:|:-----:|:---------------:|:------:|
70
- | 9.4498 | 0.2400 | 400 | 3.5557 | 1.0 |
71
- | 2.5378 | 0.4799 | 800 | 1.4012 | 0.9519 |
72
- | 1.3227 | 0.7199 | 1200 | 1.0083 | 0.8840 |
73
- | 1.097 | 0.9598 | 1600 | 0.8357 | 0.8076 |
74
- | 0.9479 | 1.1998 | 2000 | 0.7550 | 0.7528 |
75
- | 0.8624 | 1.4397 | 2400 | 0.6826 | 0.7245 |
76
- | 0.8361 | 1.6797 | 2800 | 0.6142 | 0.6713 |
77
- | 0.7885 | 1.9196 | 3200 | 0.5969 | 0.6562 |
78
- | 0.6957 | 2.1596 | 3600 | 0.5807 | 0.6521 |
79
- | 0.6457 | 2.3995 | 4000 | 0.5448 | 0.5961 |
80
- | 0.6398 | 2.6395 | 4400 | 0.5329 | 0.5852 |
81
- | 0.6185 | 2.8794 | 4800 | 0.5240 | 0.6067 |
82
- | 0.5567 | 3.1194 | 5200 | 0.5118 | 0.5542 |
83
- | 0.506 | 3.3593 | 5600 | 0.4821 | 0.5345 |
84
- | 0.5072 | 3.5993 | 6000 | 0.4828 | 0.5437 |
85
- | 0.4974 | 3.8392 | 6400 | 0.4588 | 0.5236 |
86
- | 0.4545 | 4.0792 | 6800 | 0.4607 | 0.5134 |
87
- | 0.399 | 4.3191 | 7200 | 0.4552 | 0.4956 |
88
- | 0.3918 | 4.5591 | 7600 | 0.4427 | 0.4968 |
89
- | 0.4084 | 4.7990 | 8000 | 0.4397 | 0.4887 |
90
- | 0.3978 | 5.0390 | 8400 | 0.4215 | 0.4681 |
91
- | 0.3342 | 5.2789 | 8800 | 0.4145 | 0.4727 |
92
- | 0.3299 | 5.5189 | 9200 | 0.4287 | 0.4674 |
93
- | 0.3133 | 5.7588 | 9600 | 0.4128 | 0.4525 |
94
- | 0.3226 | 5.9988 | 10000 | 0.3905 | 0.4537 |
95
- | 0.2512 | 6.2388 | 10400 | 0.4126 | 0.4352 |
96
- | 0.262 | 6.4787 | 10800 | 0.4091 | 0.4387 |
97
- | 0.2621 | 6.7187 | 11200 | 0.4119 | 0.4211 |
98
- | 0.2632 | 6.9586 | 11600 | 0.4037 | 0.4266 |
99
- | 0.2201 | 7.1986 | 12000 | 0.4239 | 0.4229 |
100
- | 0.2215 | 7.4385 | 12400 | 0.4266 | 0.4213 |
101
- | 0.213 | 7.6785 | 12800 | 0.4149 | 0.4229 |
102
- | 0.202 | 7.9184 | 13200 | 0.4154 | 0.4113 |
103
- | 0.2034 | 8.1584 | 13600 | 0.4193 | 0.4081 |
104
- | 0.1809 | 8.3983 | 14000 | 0.4164 | 0.4090 |
105
- | 0.185 | 8.6383 | 14400 | 0.4154 | 0.3942 |
106
- | 0.1813 | 8.8782 | 14800 | 0.4078 | 0.3914 |
107
- | 0.1625 | 9.1182 | 15200 | 0.4223 | 0.3956 |
108
- | 0.1642 | 9.3581 | 15600 | 0.4204 | 0.3926 |
109
- | 0.1561 | 9.5981 | 16000 | 0.4172 | 0.3880 |
110
- | 0.155 | 9.8380 | 16400 | 0.4180 | 0.3861 |
111
 
112
 
113
  ### Framework versions
114
 
115
  - Transformers 4.45.0.dev0
116
- - Pytorch 2.4.0+cu121
117
  - Datasets 2.21.0
118
  - Tokenizers 0.19.1
 
1
  ---
 
 
 
2
  library_name: transformers
3
+ language:
4
+ - ne
5
  license: apache-2.0
6
+ base_model: facebook/wav2vec2-xls-r-300m
 
7
  tags:
8
  - generated_from_trainer
9
+ datasets:
10
+ - kiranpantha/OpenSLR54-Balanced-Nepali
11
+ metrics:
12
+ - wer
13
  model-index:
14
+ - name: XLSR-300M-Nepali
15
  results:
16
  - task:
 
17
  name: Automatic Speech Recognition
18
+ type: automatic-speech-recognition
19
  dataset:
20
+ name: OpenSLR54
21
+ type: kiranpantha/OpenSLR54-Balanced-Nepali
22
  config: default
23
  split: test
24
+ args: 'config: ne, split: train,test'
25
  metrics:
26
+ - name: Wer
27
+ type: wer
28
+ value: 0.5244204160175937
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
  should probably proofread and complete it, then remove this comment. -->
33
 
34
+ # XLSR-300M-Nepali
35
 
36
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the OpenSLR54 dataset.
37
  It achieves the following results on the evaluation set:
38
+ - Loss: 0.2681
39
+ - Wer: 0.5244
40
 
41
  ## Model description
42
 
 
55
  ### Training hyperparameters
56
 
57
  The following hyperparameters were used during training:
58
+ - learning_rate: 5e-05
59
  - train_batch_size: 8
60
  - eval_batch_size: 8
61
  - seed: 42
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 500
65
+ - num_epochs: 2
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
71
+ |:-------------:|:------:|:----:|:---------------:|:------:|
72
+ | 3.2642 | 0.0722 | 300 | 2.9627 | 1.0 |
73
+ | 2.1949 | 0.1444 | 600 | 1.5526 | 1.0160 |
74
+ | 1.4595 | 0.2166 | 900 | 1.1674 | 0.9810 |
75
+ | 1.2128 | 0.2888 | 1200 | 0.9901 | 0.9668 |
76
+ | 0.976 | 0.3610 | 1500 | 0.6942 | 0.7696 |
77
+ | 0.8267 | 0.4332 | 1800 | 0.6314 | 0.7552 |
78
+ | 0.7542 | 0.5054 | 2100 | 0.5522 | 0.7156 |
79
+ | 0.7228 | 0.5776 | 2400 | 0.5210 | 0.6960 |
80
+ | 0.6707 | 0.6498 | 2700 | 0.4744 | 0.6581 |
81
+ | 0.6368 | 0.7220 | 3000 | 0.4529 | 0.6535 |
82
+ | 0.5944 | 0.7942 | 3300 | 0.4229 | 0.6264 |
83
+ | 0.5651 | 0.8664 | 3600 | 0.4061 | 0.6161 |
84
+ | 0.5469 | 0.9386 | 3900 | 0.3788 | 0.6103 |
85
+ | 0.5308 | 1.0108 | 4200 | 0.3668 | 0.5957 |
86
+ | 0.4684 | 1.0830 | 4500 | 0.3509 | 0.5920 |
87
+ | 0.4382 | 1.1552 | 4800 | 0.3398 | 0.5920 |
88
+ | 0.4424 | 1.2274 | 5100 | 0.3260 | 0.5767 |
89
+ | 0.4159 | 1.2996 | 5400 | 0.3189 | 0.5690 |
90
+ | 0.419 | 1.3718 | 5700 | 0.3067 | 0.5581 |
91
+ | 0.4114 | 1.4440 | 6000 | 0.3019 | 0.5568 |
92
+ | 0.3903 | 1.5162 | 6300 | 0.2982 | 0.5549 |
93
+ | 0.3915 | 1.5884 | 6600 | 0.2887 | 0.5493 |
94
+ | 0.3789 | 1.6606 | 6900 | 0.2813 | 0.5398 |
95
+ | 0.3725 | 1.7329 | 7200 | 0.2763 | 0.5339 |
96
+ | 0.3706 | 1.8051 | 7500 | 0.2704 | 0.5285 |
97
+ | 0.3624 | 1.8773 | 7800 | 0.2706 | 0.5264 |
98
+ | 0.357 | 1.9495 | 8100 | 0.2681 | 0.5244 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99
 
100
 
101
  ### Framework versions
102
 
103
  - Transformers 4.45.0.dev0
104
+ - Pytorch 2.4.1+cu121
105
  - Datasets 2.21.0
106
  - Tokenizers 0.19.1