Hugging Face's logo

DrishtiSharma
/
wav2vec2-large-xls-r-300m-hi-wx1

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Hindi
wav2vec2
hf-asr-leaderboard
robust-speech-event
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
DrishtiSharma commited on
Commit
a742827
•
1 Parent(s): 26465e2

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -39
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.6966
20
- - Wer: 0.3424
21
 
22
  ## Model description
23
 
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
44
  - total_train_batch_size: 32
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - lr_scheduler_warmup_steps: 1500
48
  - num_epochs: 50
49
  - mixed_precision_training: Native AMP
50
 
@@ -52,42 +52,42 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
- | 11.0193 | 1.36 | 200 | 5.6992 | 1.0 |
56
- | 3.9285 | 2.72 | 400 | 3.4430 | 1.0 |
57
- | 3.293 | 4.08 | 600 | 2.7707 | 1.0 |
58
- | 1.2714 | 5.44 | 800 | 0.8479 | 0.6015 |
59
- | 0.6469 | 6.8 | 1000 | 0.7087 | 0.5412 |
60
- | 0.4982 | 8.16 | 1200 | 0.6655 | 0.5116 |
61
- | 0.4131 | 9.52 | 1400 | 0.6422 | 0.4845 |
62
- | 0.3653 | 10.88 | 1600 | 0.6452 | 0.4700 |
63
- | 0.3177 | 12.24 | 1800 | 0.7519 | 0.5236 |
64
- | 0.2771 | 13.6 | 2000 | 0.6238 | 0.4444 |
65
- | 0.2424 | 14.96 | 2200 | 0.6317 | 0.4458 |
66
- | 0.2207 | 16.33 | 2400 | 0.6634 | 0.4144 |
67
- | 0.1997 | 17.68 | 2600 | 0.6469 | 0.4110 |
68
- | 0.1843 | 19.05 | 2800 | 0.6958 | 0.4162 |
69
- | 0.1705 | 20.41 | 3000 | 0.6658 | 0.3992 |
70
- | 0.1535 | 21.77 | 3200 | 0.6829 | 0.4136 |
71
- | 0.1492 | 23.13 | 3400 | 0.6628 | 0.4018 |
72
- | 0.1383 | 24.49 | 3600 | 0.6603 | 0.4020 |
73
- | 0.1334 | 25.85 | 3800 | 0.7079 | 0.3914 |
74
- | 0.1215 | 27.21 | 4000 | 0.7016 | 0.3904 |
75
- | 0.1211 | 28.57 | 4200 | 0.7232 | 0.3963 |
76
- | 0.1125 | 29.93 | 4400 | 0.7258 | 0.3879 |
77
- | 0.1074 | 31.29 | 4600 | 0.7476 | 0.3900 |
78
- | 0.0965 | 32.65 | 4800 | 0.7120 | 0.3734 |
79
- | 0.0916 | 34.01 | 5000 | 0.6694 | 0.3730 |
80
- | 0.0865 | 35.37 | 5200 | 0.7181 | 0.3680 |
81
- | 0.0822 | 36.73 | 5400 | 0.6698 | 0.3554 |
82
- | 0.0757 | 38.09 | 5600 | 0.7035 | 0.3627 |
83
- | 0.0723 | 39.45 | 5800 | 0.6832 | 0.3575 |
84
- | 0.0746 | 40.81 | 6000 | 0.6942 | 0.3508 |
85
- | 0.0667 | 42.18 | 6200 | 0.7075 | 0.3523 |
86
- | 0.0638 | 43.54 | 6400 | 0.7009 | 0.3473 |
87
- | 0.0585 | 44.89 | 6600 | 0.6887 | 0.3443 |
88
- | 0.0562 | 46.26 | 6800 | 0.6888 | 0.3454 |
89
- | 0.0534 | 47.62 | 7000 | 0.7048 | 0.3438 |
90
- | 0.0481 | 48.98 | 7200 | 0.6966 | 0.3424 |
91
 
92
 
93
  ### Framework versions
 
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: 0.6552
20
+ - Wer: 0.3200
21
 
22
  ## Model description
23
 
 
44
  - total_train_batch_size: 32
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 1800
48
  - num_epochs: 50
49
  - mixed_precision_training: Native AMP
50
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 12.2663 | 1.36 | 200 | 5.9245 | 1.0 |
56
+ | 4.1856 | 2.72 | 400 | 3.4968 | 1.0 |
57
+ | 3.3908 | 4.08 | 600 | 2.9970 | 1.0 |
58
+ | 1.5444 | 5.44 | 800 | 0.9071 | 0.6139 |
59
+ | 0.7237 | 6.8 | 1000 | 0.6508 | 0.4862 |
60
+ | 0.5323 | 8.16 | 1200 | 0.6217 | 0.4647 |
61
+ | 0.4426 | 9.52 | 1400 | 0.5785 | 0.4288 |
62
+ | 0.3933 | 10.88 | 1600 | 0.5935 | 0.4217 |
63
+ | 0.3532 | 12.24 | 1800 | 0.6358 | 0.4465 |
64
+ | 0.3319 | 13.6 | 2000 | 0.5789 | 0.4118 |
65
+ | 0.2877 | 14.96 | 2200 | 0.6163 | 0.4056 |
66
+ | 0.2663 | 16.33 | 2400 | 0.6176 | 0.3893 |
67
+ | 0.2511 | 17.68 | 2600 | 0.6065 | 0.3999 |
68
+ | 0.2275 | 19.05 | 2800 | 0.6183 | 0.3842 |
69
+ | 0.2098 | 20.41 | 3000 | 0.6486 | 0.3864 |
70
+ | 0.1943 | 21.77 | 3200 | 0.6365 | 0.3885 |
71
+ | 0.1877 | 23.13 | 3400 | 0.6013 | 0.3677 |
72
+ | 0.1679 | 24.49 | 3600 | 0.6451 | 0.3795 |
73
+ | 0.1667 | 25.85 | 3800 | 0.6410 | 0.3635 |
74
+ | 0.1514 | 27.21 | 4000 | 0.6000 | 0.3577 |
75
+ | 0.1453 | 28.57 | 4200 | 0.6020 | 0.3518 |
76
+ | 0.134 | 29.93 | 4400 | 0.6531 | 0.3517 |
77
+ | 0.1354 | 31.29 | 4600 | 0.6874 | 0.3578 |
78
+ | 0.1224 | 32.65 | 4800 | 0.6519 | 0.3492 |
79
+ | 0.1199 | 34.01 | 5000 | 0.6553 | 0.3490 |
80
+ | 0.1077 | 35.37 | 5200 | 0.6621 | 0.3429 |
81
+ | 0.0997 | 36.73 | 5400 | 0.6641 | 0.3413 |
82
+ | 0.0964 | 38.09 | 5600 | 0.6722 | 0.3385 |
83
+ | 0.0931 | 39.45 | 5800 | 0.6365 | 0.3363 |
84
+ | 0.0944 | 40.81 | 6000 | 0.6454 | 0.3326 |
85
+ | 0.0862 | 42.18 | 6200 | 0.6497 | 0.3256 |
86
+ | 0.0848 | 43.54 | 6400 | 0.6599 | 0.3226 |
87
+ | 0.0793 | 44.89 | 6600 | 0.6625 | 0.3232 |
88
+ | 0.076 | 46.26 | 6800 | 0.6463 | 0.3186 |
89
+ | 0.0749 | 47.62 | 7000 | 0.6559 | 0.3225 |
90
+ | 0.0663 | 48.98 | 7200 | 0.6552 | 0.3200 |
91
 
92
 
93
  ### Framework versions