Hugging Face's logo

shahukareem
/
xls-r-300m-dv

Automatic Speech Recognition
Transformers
PyTorch
Divehi
wav2vec2
Generated from Trainer
hf-asr-leaderboard
model_for_talk
mozilla-foundation/common_voice_8_0
robust-speech-event
Eval Results
Inference Endpoints
Model card Files Community
1
shahukareem commited on
Commit
d4582e9
•
1 Parent(s): 9236d2a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +82 -35
README.md CHANGED
@@ -1,29 +1,12 @@
1
  ---
2
  license: apache-2.0
3
  tags:
4
- - automatic-speech-recognition
5
- - mozilla-foundation/common_voice_8_0
6
  - generated_from_trainer
7
- - robust-speech-event
8
  datasets:
9
  - common_voice
10
  model-index:
11
  - name: xls-r-300m-dv
12
- results:
13
- - task:
14
- name: Automatic Speech Recognition
15
- type: automatic-speech-recognition
16
- dataset:
17
- name: Common Voice 8
18
- type: mozilla-foundation/common_voice_8_0
19
- args: dv
20
- metrics:
21
- - name: Test WER
22
- type: wer
23
- value:
24
- - name: Test CER
25
- type: cer
26
- value:
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  # xls-r-300m-dv
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 on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - dv dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.6182
37
- - Wer: 0.5481
38
 
39
  ## Model description
40
 
@@ -62,24 +45,88 @@ The following hyperparameters were used during training:
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: 30
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
- | Training Loss | Epoch | Step | Validation Loss | Wer |
71
- |:-------------:|:-----:|:----:|:---------------:|:------:|
72
- | 4.3529 | 2.63 | 400 | 1.2050 | 0.9526 |
73
- | 0.7191 | 5.26 | 800 | 0.6037 | 0.7216 |
74
- | 0.3981 | 7.89 | 1200 | 0.5048 | 0.6225 |
75
- | 0.2888 | 10.52 | 1600 | 0.5345 | 0.6170 |
76
- | 0.2229 | 13.16 | 2000 | 0.5261 | 0.6015 |
77
- | 0.1865 | 15.79 | 2400 | 0.5983 | 0.5924 |
78
- | 0.1542 | 18.42 | 2800 | 0.5900 | 0.5770 |
79
- | 0.1401 | 21.05 | 3200 | 0.6425 | 0.5783 |
80
- | 0.1205 | 23.68 | 3600 | 0.6322 | 0.5760 |
81
- | 0.1105 | 26.31 | 4000 | 0.6302 | 0.5567 |
82
- | 0.0958 | 28.94 | 4400 | 0.6182 | 0.5481 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83
 
84
 
85
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
  tags:
 
 
4
  - generated_from_trainer
 
5
  datasets:
6
  - common_voice
7
  model-index:
8
  - name: xls-r-300m-dv
9
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
14
 
15
  # xls-r-300m-dv
16
 
17
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.3149
20
+ - Wer: 0.2947
21
 
22
  ## Model description
23
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 500
48
+ - num_epochs: 50
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
55
+ | 3.9617 | 0.66 | 400 | 1.4251 | 0.9768 |
56
+ | 0.9081 | 1.33 | 800 | 0.6068 | 0.7290 |
57
+ | 0.6575 | 1.99 | 1200 | 0.4700 | 0.6234 |
58
+ | 0.548 | 2.65 | 1600 | 0.4158 | 0.5868 |
59
+ | 0.5031 | 3.32 | 2000 | 0.4067 | 0.5728 |
60
+ | 0.4792 | 3.98 | 2400 | 0.3965 | 0.5673 |
61
+ | 0.4344 | 4.64 | 2800 | 0.3862 | 0.5383 |
62
+ | 0.4237 | 5.31 | 3200 | 0.3794 | 0.5316 |
63
+ | 0.3984 | 5.97 | 3600 | 0.3395 | 0.5177 |
64
+ | 0.3788 | 6.63 | 4000 | 0.3528 | 0.5329 |
65
+ | 0.3685 | 7.3 | 4400 | 0.3404 | 0.5060 |
66
+ | 0.3535 | 7.96 | 4800 | 0.3425 | 0.5069 |
67
+ | 0.3391 | 8.62 | 5200 | 0.3576 | 0.5118 |
68
+ | 0.331 | 9.29 | 5600 | 0.3259 | 0.4783 |
69
+ | 0.3192 | 9.95 | 6000 | 0.3145 | 0.4794 |
70
+ | 0.2956 | 10.61 | 6400 | 0.3111 | 0.4650 |
71
+ | 0.2936 | 11.28 | 6800 | 0.3303 | 0.4741 |
72
+ | 0.2868 | 11.94 | 7200 | 0.3109 | 0.4597 |
73
+ | 0.2743 | 12.6 | 7600 | 0.3191 | 0.4557 |
74
+ | 0.2654 | 13.27 | 8000 | 0.3286 | 0.4570 |
75
+ | 0.2556 | 13.93 | 8400 | 0.3186 | 0.4468 |
76
+ | 0.2452 | 14.59 | 8800 | 0.3405 | 0.4582 |
77
+ | 0.241 | 15.26 | 9200 | 0.3418 | 0.4533 |
78
+ | 0.2313 | 15.92 | 9600 | 0.3388 | 0.4405 |
79
+ | 0.2234 | 16.58 | 10000 | 0.3659 | 0.4421 |
80
+ | 0.2194 | 17.25 | 10400 | 0.3559 | 0.4490 |
81
+ | 0.2168 | 17.91 | 10800 | 0.3452 | 0.4355 |
82
+ | 0.2036 | 18.57 | 11200 | 0.3496 | 0.4259 |
83
+ | 0.2046 | 19.24 | 11600 | 0.3282 | 0.4245 |
84
+ | 0.1917 | 19.9 | 12000 | 0.3201 | 0.4052 |
85
+ | 0.1908 | 20.56 | 12400 | 0.3439 | 0.4165 |
86
+ | 0.1838 | 21.23 | 12800 | 0.3165 | 0.3950 |
87
+ | 0.1828 | 21.89 | 13200 | 0.3332 | 0.4079 |
88
+ | 0.1774 | 22.55 | 13600 | 0.3485 | 0.4072 |
89
+ | 0.1776 | 23.22 | 14000 | 0.3308 | 0.3868 |
90
+ | 0.1693 | 23.88 | 14400 | 0.3153 | 0.3906 |
91
+ | 0.1656 | 24.54 | 14800 | 0.3408 | 0.3899 |
92
+ | 0.1629 | 25.21 | 15200 | 0.3333 | 0.3854 |
93
+ | 0.164 | 25.87 | 15600 | 0.3172 | 0.3775 |
94
+ | 0.1505 | 26.53 | 16000 | 0.3105 | 0.3777 |
95
+ | 0.1524 | 27.2 | 16400 | 0.3136 | 0.3726 |
96
+ | 0.1482 | 27.86 | 16800 | 0.3110 | 0.3710 |
97
+ | 0.1423 | 28.52 | 17200 | 0.3299 | 0.3687 |
98
+ | 0.1419 | 29.19 | 17600 | 0.3271 | 0.3645 |
99
+ | 0.135 | 29.85 | 18000 | 0.3333 | 0.3638 |
100
+ | 0.1319 | 30.51 | 18400 | 0.3272 | 0.3640 |
101
+ | 0.131 | 31.18 | 18800 | 0.3438 | 0.3636 |
102
+ | 0.1252 | 31.84 | 19200 | 0.3266 | 0.3557 |
103
+ | 0.1238 | 32.5 | 19600 | 0.3195 | 0.3516 |
104
+ | 0.1203 | 33.17 | 20000 | 0.3405 | 0.3534 |
105
+ | 0.1159 | 33.83 | 20400 | 0.3287 | 0.3509 |
106
+ | 0.115 | 34.49 | 20800 | 0.3474 | 0.3433 |
107
+ | 0.108 | 35.16 | 21200 | 0.3245 | 0.3381 |
108
+ | 0.1091 | 35.82 | 21600 | 0.3185 | 0.3448 |
109
+ | 0.1043 | 36.48 | 22000 | 0.3309 | 0.3363 |
110
+ | 0.1034 | 37.15 | 22400 | 0.3288 | 0.3349 |
111
+ | 0.1015 | 37.81 | 22800 | 0.3222 | 0.3284 |
112
+ | 0.0953 | 38.47 | 23200 | 0.3272 | 0.3315 |
113
+ | 0.0966 | 39.14 | 23600 | 0.3196 | 0.3239 |
114
+ | 0.0938 | 39.8 | 24000 | 0.3199 | 0.3280 |
115
+ | 0.0905 | 40.46 | 24400 | 0.3193 | 0.3166 |
116
+ | 0.0893 | 41.13 | 24800 | 0.3224 | 0.3222 |
117
+ | 0.0858 | 41.79 | 25200 | 0.3216 | 0.3142 |
118
+ | 0.0839 | 42.45 | 25600 | 0.3241 | 0.3135 |
119
+ | 0.0819 | 43.12 | 26000 | 0.3260 | 0.3071 |
120
+ | 0.0782 | 43.78 | 26400 | 0.3202 | 0.3075 |
121
+ | 0.0775 | 44.44 | 26800 | 0.3140 | 0.3067 |
122
+ | 0.0751 | 45.11 | 27200 | 0.3118 | 0.3020 |
123
+ | 0.0736 | 45.77 | 27600 | 0.3155 | 0.2976 |
124
+ | 0.071 | 46.43 | 28000 | 0.3105 | 0.2998 |
125
+ | 0.0715 | 47.1 | 28400 | 0.3065 | 0.2993 |
126
+ | 0.0668 | 47.76 | 28800 | 0.3161 | 0.2972 |
127
+ | 0.0698 | 48.42 | 29200 | 0.3137 | 0.2967 |
128
+ | 0.0681 | 49.09 | 29600 | 0.3130 | 0.2971 |
129
+ | 0.0651 | 49.75 | 30000 | 0.3149 | 0.2947 |
130
 
131
 
132
  ### Framework versions