Hugging Face's logo

nurzhanit
/
whisper-enhanced-ml

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Hindi
whisper
hf-asr-leaderboard
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
nurzhanit commited on
Commit
93a8568
·
verified ·
1 Parent(s): 9e301e7

End of training

Browse files
Files changed (2) hide show
  1. README.md +17 -47
  2. model.safetensors +1 -1
README.md CHANGED
@@ -24,7 +24,7 @@ model-index:
24
  metrics:
25
  - name: Wer
26
  type: wer
27
- value: 0.0
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
34
 
35
  This model is a fine-tuned version of [nurzhanit/whisper-enhanced-ml](https://huggingface.co/nurzhanit/whisper-enhanced-ml) on the Common Voice 11.0 dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.0000
38
- - Wer: 0.0
39
 
40
  ## Model description
41
 
@@ -60,53 +60,23 @@ The following hyperparameters were used during training:
60
  - seed: 42
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
- - lr_scheduler_warmup_steps: 200
64
- - training_steps: 4000
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Wer |
69
- |:-------------:|:--------:|:----:|:---------------:|:---:|
70
- | 0.0 | 16.6667 | 100 | 0.0000 | 0.0 |
71
- | 0.0 | 33.3333 | 200 | 0.0000 | 0.0 |
72
- | 0.0 | 50.0 | 300 | 0.0000 | 0.0 |
73
- | 0.0 | 66.6667 | 400 | 0.0000 | 0.0 |
74
- | 0.0 | 83.3333 | 500 | 0.0000 | 0.0 |
75
- | 0.0 | 100.0 | 600 | 0.0000 | 0.0 |
76
- | 0.0 | 116.6667 | 700 | 0.0000 | 0.0 |
77
- | 0.0 | 133.3333 | 800 | 0.0000 | 0.0 |
78
- | 0.0 | 150.0 | 900 | 0.0000 | 0.0 |
79
- | 0.0 | 166.6667 | 1000 | 0.0000 | 0.0 |
80
- | 0.0 | 183.3333 | 1100 | 0.0000 | 0.0 |
81
- | 0.0 | 200.0 | 1200 | 0.0000 | 0.0 |
82
- | 0.0 | 216.6667 | 1300 | 0.0000 | 0.0 |
83
- | 0.0 | 233.3333 | 1400 | 0.0000 | 0.0 |
84
- | 0.0 | 250.0 | 1500 | 0.0000 | 0.0 |
85
- | 0.0 | 266.6667 | 1600 | 0.0000 | 0.0 |
86
- | 0.0 | 283.3333 | 1700 | 0.0000 | 0.0 |
87
- | 0.0 | 300.0 | 1800 | 0.0000 | 0.0 |
88
- | 0.0 | 316.6667 | 1900 | 0.0000 | 0.0 |
89
- | 0.0 | 333.3333 | 2000 | 0.0000 | 0.0 |
90
- | 0.0 | 350.0 | 2100 | 0.0000 | 0.0 |
91
- | 0.0 | 366.6667 | 2200 | 0.0000 | 0.0 |
92
- | 0.0 | 383.3333 | 2300 | 0.0000 | 0.0 |
93
- | 0.0 | 400.0 | 2400 | 0.0000 | 0.0 |
94
- | 0.0 | 416.6667 | 2500 | 0.0000 | 0.0 |
95
- | 0.0 | 433.3333 | 2600 | 0.0000 | 0.0 |
96
- | 0.0 | 450.0 | 2700 | 0.0000 | 0.0 |
97
- | 0.0 | 466.6667 | 2800 | 0.0000 | 0.0 |
98
- | 0.0 | 483.3333 | 2900 | 0.0000 | 0.0 |
99
- | 0.0 | 500.0 | 3000 | 0.0000 | 0.0 |
100
- | 0.0 | 516.6667 | 3100 | 0.0000 | 0.0 |
101
- | 0.0 | 533.3333 | 3200 | 0.0000 | 0.0 |
102
- | 0.0 | 550.0 | 3300 | 0.0000 | 0.0 |
103
- | 0.0 | 566.6667 | 3400 | 0.0000 | 0.0 |
104
- | 0.0 | 583.3333 | 3500 | 0.0000 | 0.0 |
105
- | 0.0 | 600.0 | 3600 | 0.0000 | 0.0 |
106
- | 0.0 | 616.6667 | 3700 | 0.0000 | 0.0 |
107
- | 0.0 | 633.3333 | 3800 | 0.0000 | 0.0 |
108
- | 0.0 | 650.0 | 3900 | 0.0000 | 0.0 |
109
- | 0.0 | 666.6667 | 4000 | 0.0000 | 0.0 |
110
 
111
 
112
  ### Framework versions
 
24
  metrics:
25
  - name: Wer
26
  type: wer
27
+ value: 22.35494880546075
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
34
 
35
  This model is a fine-tuned version of [nurzhanit/whisper-enhanced-ml](https://huggingface.co/nurzhanit/whisper-enhanced-ml) on the Common Voice 11.0 dataset.
36
  It achieves the following results on the evaluation set:
37
+ - Loss: 0.0010
38
+ - Wer: 22.3549
39
 
40
  ## Model description
41
 
 
60
  - seed: 42
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_steps: 50
64
+ - training_steps: 500
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
70
+ | 1.3416 | 10.0 | 50 | 0.7715 | 69.5819 |
71
+ | 0.1814 | 20.0 | 100 | 0.0861 | 33.4898 |
72
+ | 0.0174 | 30.0 | 150 | 0.0096 | 22.3549 |
73
+ | 0.0038 | 40.0 | 200 | 0.0029 | 22.3549 |
74
+ | 0.0022 | 50.0 | 250 | 0.0019 | 22.3549 |
75
+ | 0.0016 | 60.0 | 300 | 0.0015 | 22.3549 |
76
+ | 0.0013 | 70.0 | 350 | 0.0012 | 22.3549 |
77
+ | 0.0012 | 80.0 | 400 | 0.0011 | 22.3549 |
78
+ | 0.0011 | 90.0 | 450 | 0.0010 | 22.3549 |
79
+ | 0.001 | 100.0 | 500 | 0.0010 | 22.3549 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b52df335284059ea9101fa78a8b12fd43a712866002be16795d9eccbb657b76
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a20157d9a4b64df0b2bb46843fd5414f10c1f0444df20cf851fdb04adfaeeb
3
  size 966995080