Hugging Face's logo

Priyanship
/
output

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files Community
Priyanship commited on
Commit
dd387a0
·
verified ·
1 Parent(s): ee8380f

Model save

Browse files
Files changed (2) hide show
  1. README.md +14 -43
  2. model.safetensors +1 -1
README.md CHANGED
@@ -11,14 +11,14 @@ model-index:
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/priyanshipal/huggingface/runs/ovuq4xne)
15
  # output
16
 
17
  This model was trained from scratch on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.0007
20
- - Cer: 0.3962
21
- - Wer: 0.6069
22
 
23
  ## Model description
24
 
@@ -45,49 +45,20 @@ The following hyperparameters were used during training:
45
  - total_train_batch_size: 32
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - lr_scheduler_warmup_steps: 1500
49
- - training_steps: 3500
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
55
- |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
56
- | 5.2909 | 0.16 | 100 | 5.7883 | 0.9933 | 1.0 |
57
- | 4.4471 | 0.32 | 200 | 3.7597 | 0.9812 | 1.0 |
58
- | 3.6763 | 0.48 | 300 | 3.7718 | 0.9769 | 1.0 |
59
- | 3.1272 | 0.64 | 400 | 3.4647 | 0.9826 | 1.0 |
60
- | 3.0699 | 0.8 | 500 | 2.7480 | 0.6002 | 0.8337 |
61
- | 1.7389 | 0.96 | 600 | 2.4468 | 0.4717 | 0.6782 |
62
- | 1.7013 | 1.12 | 700 | 2.1151 | 0.4489 | 0.6820 |
63
- | 1.2995 | 1.28 | 800 | 2.0757 | 0.4160 | 0.6245 |
64
- | 1.6852 | 1.44 | 900 | 1.9870 | 0.4112 | 0.6154 |
65
- | 1.3997 | 1.6 | 1000 | 2.0007 | 0.3962 | 0.6069 |
66
- | 1.768 | 1.76 | 1100 | 2.0712 | 0.4123 | 0.6448 |
67
- | 2.5192 | 1.92 | 1200 | 2.5729 | 0.6884 | 0.9178 |
68
- | 2.6077 | 2.08 | 1300 | 2.4078 | 0.4816 | 0.8066 |
69
- | 2.6928 | 2.24 | 1400 | 2.3596 | 0.4904 | 0.7915 |
70
- | 0.0 | 2.4 | 1500 | 2.4471 | 0.6019 | 0.8782 |
71
- | 0.0 | 2.56 | 1600 | 2.4490 | 0.6112 | 0.8888 |
72
- | 0.0 | 2.7200 | 1700 | nan | 1.0 | 1.0 |
73
- | 0.0 | 2.88 | 1800 | nan | 1.0 | 1.0 |
74
- | 0.0 | 3.04 | 1900 | nan | 1.0 | 1.0 |
75
- | 0.0 | 3.2 | 2000 | nan | 1.0 | 1.0 |
76
- | 0.0 | 3.36 | 2100 | nan | 1.0 | 1.0 |
77
- | 0.0 | 3.52 | 2200 | nan | 1.0 | 1.0 |
78
- | 0.0 | 3.68 | 2300 | nan | 1.0 | 1.0 |
79
- | 0.0 | 3.84 | 2400 | nan | 1.0 | 1.0 |
80
- | 0.0 | 4.0 | 2500 | nan | 1.0 | 1.0 |
81
- | 0.0 | 4.16 | 2600 | nan | 1.0 | 1.0 |
82
- | 0.0 | 4.32 | 2700 | nan | 1.0 | 1.0 |
83
- | 0.0 | 4.48 | 2800 | nan | 1.0 | 1.0 |
84
- | 0.0 | 4.64 | 2900 | nan | 1.0 | 1.0 |
85
- | 0.0 | 4.8 | 3000 | nan | 1.0 | 1.0 |
86
- | 0.0 | 4.96 | 3100 | nan | 1.0 | 1.0 |
87
- | 0.0 | 5.12 | 3200 | nan | 1.0 | 1.0 |
88
- | 0.0 | 5.28 | 3300 | nan | 1.0 | 1.0 |
89
- | 0.0 | 5.44 | 3400 | nan | 1.0 | 1.0 |
90
- | 0.0 | 5.6 | 3500 | nan | 1.0 | 1.0 |
91
 
92
 
93
  ### Framework versions
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/priyanshipal/huggingface/runs/hvo6b5jz)
15
  # output
16
 
17
  This model was trained from scratch on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 3.2885
20
+ - Cer: 0.5196
21
+ - Wer: 0.8050
22
 
23
  ## Model description
24
 
 
45
  - total_train_batch_size: 32
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 2000
49
+ - training_steps: 6000
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
55
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
56
+ | 1.5851 | 1.6 | 1000 | 1.9947 | 0.4133 | 0.6195 |
57
+ | 1.8352 | 3.2 | 2000 | 2.1491 | 0.4724 | 0.7895 |
58
+ | 2.3755 | 4.8 | 3000 | 2.3793 | 0.4433 | 0.7270 |
59
+ | 3.3134 | 6.4 | 4000 | 3.3025 | 0.5204 | 0.8033 |
60
+ | 3.4098 | 8.0 | 5000 | 3.2885 | 0.5196 | 0.8050 |
61
+ | 3.1155 | 9.6 | 6000 | 3.2885 | 0.5196 | 0.8050 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b23e14f7020868b89fa6a862673147b0ae7498934ba7b6bf47da4e6ef3eb791
3
  size 1262426580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11123f516d513f049ccf8eca7a64f45fe94183f0c16009563846a3cba3ca71e4
3
  size 1262426580