Hugging Face's logo

gopikachu
/
whisper-medium-hi-4cycles

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Hindi
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
gopikachu commited on
Commit
891295f
•
1 Parent(s): 16a860c

End of training

Browse files
Files changed (2) hide show
  1. README.md +24 -24
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.026845637583892617
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Konnakol dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.2424
36
- - Wer: 0.0268
37
- - Cer: 0.0281
38
 
39
  ## Model description
40
 
@@ -67,26 +67,26 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
69
  |:-------------:|:--------:|:----:|:---------------:|:------:|:------:|
70
- | 2.6928 | 8.3333 | 50 | 0.7108 | 0.0593 | 0.0502 |
71
- | 0.1456 | 16.6667 | 100 | 0.1978 | 0.0503 | 0.0448 |
72
- | 0.0104 | 25.0 | 150 | 0.1970 | 0.0291 | 0.0293 |
73
- | 0.0145 | 33.3333 | 200 | 0.2114 | 0.0503 | 0.0387 |
74
- | 0.0123 | 41.6667 | 250 | 0.2174 | 0.0515 | 0.0511 |
75
- | 0.0086 | 50.0 | 300 | 0.2339 | 0.0246 | 0.0263 |
76
- | 0.0077 | 58.3333 | 350 | 0.2737 | 0.0336 | 0.0303 |
77
- | 0.0132 | 66.6667 | 400 | 0.1764 | 0.0268 | 0.0269 |
78
- | 0.005 | 75.0 | 450 | 0.2107 | 0.0336 | 0.0339 |
79
- | 0.0207 | 83.3333 | 500 | 0.2167 | 0.4955 | 0.4702 |
80
- | 0.0153 | 91.6667 | 550 | 0.1948 | 0.0358 | 0.0342 |
81
- | 0.013 | 100.0 | 600 | 0.1882 | 0.0257 | 0.0230 |
82
- | 0.001 | 108.3333 | 650 | 0.2405 | 0.0302 | 0.0324 |
83
- | 0.0018 | 116.6667 | 700 | 0.2377 | 0.0302 | 0.0290 |
84
- | 0.0 | 125.0 | 750 | 0.2385 | 0.0268 | 0.0281 |
85
- | 0.0 | 133.3333 | 800 | 0.2398 | 0.0268 | 0.0281 |
86
- | 0.0 | 141.6667 | 850 | 0.2409 | 0.0268 | 0.0281 |
87
- | 0.0 | 150.0 | 900 | 0.2418 | 0.0268 | 0.0281 |
88
- | 0.0 | 158.3333 | 950 | 0.2422 | 0.0268 | 0.0281 |
89
- | 0.0 | 166.6667 | 1000 | 0.2424 | 0.0268 | 0.0281 |
90
 
91
 
92
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.01805869074492099
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Konnakol dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.1982
36
+ - Wer: 0.0181
37
+ - Cer: 0.0187
38
 
39
  ## Model description
40
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
69
  |:-------------:|:--------:|:----:|:---------------:|:------:|:------:|
70
+ | 2.7311 | 8.3333 | 50 | 0.7476 | 0.0339 | 0.0218 |
71
+ | 0.1743 | 16.6667 | 100 | 0.1654 | 0.0339 | 0.0305 |
72
+ | 0.0109 | 25.0 | 150 | 0.1474 | 0.0181 | 0.0187 |
73
+ | 0.0126 | 33.3333 | 200 | 0.1857 | 0.0316 | 0.0262 |
74
+ | 0.0122 | 41.6667 | 250 | 0.1125 | 0.0135 | 0.0143 |
75
+ | 0.0031 | 50.0 | 300 | 0.1541 | 0.0226 | 0.0224 |
76
+ | 0.0102 | 58.3333 | 350 | 0.1160 | 0.0226 | 0.0206 |
77
+ | 0.0211 | 66.6667 | 400 | 0.1925 | 0.0248 | 0.0224 |
78
+ | 0.0179 | 75.0 | 450 | 0.1253 | 0.0181 | 0.0187 |
79
+ | 0.0185 | 83.3333 | 500 | 0.1218 | 0.0271 | 0.0243 |
80
+ | 0.017 | 91.6667 | 550 | 0.1543 | 0.0316 | 0.0299 |
81
+ | 0.0077 | 100.0 | 600 | 0.1376 | 0.0226 | 0.0212 |
82
+ | 0.0033 | 108.3333 | 650 | 0.1555 | 0.0226 | 0.0206 |
83
+ | 0.0019 | 116.6667 | 700 | 0.1871 | 0.0203 | 0.0206 |
84
+ | 0.0012 | 125.0 | 750 | 0.1614 | 0.0226 | 0.0237 |
85
+ | 0.0 | 133.3333 | 800 | 0.1911 | 0.0181 | 0.0187 |
86
+ | 0.0 | 141.6667 | 850 | 0.1948 | 0.0181 | 0.0187 |
87
+ | 0.0 | 150.0 | 900 | 0.1968 | 0.0181 | 0.0187 |
88
+ | 0.0 | 158.3333 | 950 | 0.1977 | 0.0181 | 0.0187 |
89
+ | 0.0 | 166.6667 | 1000 | 0.1982 | 0.0181 | 0.0187 |
90
 
91
 
92
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6c78842f9a6ed888036a27da7f0f2c7e9ee894896e94bc37222620334297c1d
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37406ad457acc07ffa2931fd4df52907638229db88a964218b0ed6f82600d1f
3
  size 3055544304