Hugging Face's logo

kiranpantha
/
whisper-base-ne

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Nepali
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
kiranpantha commited on
Commit
be08ff0
·
verified ·
1 Parent(s): af1436f

End of training

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -11,7 +11,7 @@ datasets:
11
  metrics:
12
  - wer
13
  model-index:
14
- - name: Whisper Medium - Kiran Pantha
15
  results:
16
  - task:
17
  name: Automatic Speech Recognition
@@ -25,18 +25,18 @@ model-index:
25
  metrics:
26
  - name: Wer
27
  type: wer
28
- value: 43.58105012370567
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
  should probably proofread and complete it, then remove this comment. -->
33
 
34
- # Whisper Medium - Kiran Pantha
35
 
36
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the OpenSLR54 dataset.
37
  It achieves the following results on the evaluation set:
38
- - Loss: 0.2096
39
- - Wer: 43.5811
40
 
41
  ## Model description
42
 
@@ -69,16 +69,16 @@ The following hyperparameters were used during training:
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Wer |
71
  |:-------------:|:------:|:----:|:---------------:|:-------:|
72
- | 0.5243 | 0.1200 | 500 | 0.4983 | 77.1832 |
73
- | 0.3685 | 0.2399 | 1000 | 0.3600 | 64.9684 |
74
- | 0.3007 | 0.3599 | 1500 | 0.3094 | 58.0592 |
75
- | 0.2704 | 0.4798 | 2000 | 0.2785 | 54.5038 |
76
- | 0.2529 | 0.5998 | 2500 | 0.2560 | 50.7560 |
77
- | 0.2479 | 0.7198 | 3000 | 0.2407 | 48.4193 |
78
- | 0.2349 | 0.8397 | 3500 | 0.2262 | 46.3850 |
79
- | 0.211 | 0.9597 | 4000 | 0.2170 | 45.2305 |
80
- | 0.1707 | 1.0797 | 4500 | 0.2132 | 44.6990 |
81
- | 0.1506 | 1.1996 | 5000 | 0.2096 | 43.5811 |
82
 
83
 
84
  ### Framework versions
 
11
  metrics:
12
  - wer
13
  model-index:
14
+ - name: Whisper Base - Kiran Pantha
15
  results:
16
  - task:
17
  name: Automatic Speech Recognition
 
25
  metrics:
26
  - name: Wer
27
  type: wer
28
+ value: 43.282127708357216
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
  should probably proofread and complete it, then remove this comment. -->
33
 
34
+ # Whisper Base - Kiran Pantha
35
 
36
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the OpenSLR54 dataset.
37
  It achieves the following results on the evaluation set:
38
+ - Loss: 0.2056
39
+ - Wer: 43.2821
40
 
41
  ## Model description
42
 
 
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Wer |
71
  |:-------------:|:------:|:----:|:---------------:|:-------:|
72
+ | 0.5029 | 0.0750 | 500 | 0.4922 | 77.0205 |
73
+ | 0.351 | 0.1499 | 1000 | 0.3561 | 65.6941 |
74
+ | 0.3034 | 0.2249 | 1500 | 0.2988 | 57.0618 |
75
+ | 0.2689 | 0.2999 | 2000 | 0.2714 | 53.2844 |
76
+ | 0.2584 | 0.3749 | 2500 | 0.2537 | 50.8369 |
77
+ | 0.2325 | 0.4498 | 3000 | 0.2393 | 48.0282 |
78
+ | 0.2238 | 0.5248 | 3500 | 0.2271 | 46.5723 |
79
+ | 0.2149 | 0.5998 | 4000 | 0.2149 | 44.4056 |
80
+ | 0.2038 | 0.6748 | 4500 | 0.2091 | 43.6834 |
81
+ | 0.2026 | 0.7497 | 5000 | 0.2056 | 43.2821 |
82
 
83
 
84
  ### Framework versions