Hugging Face's logo

kiranpantha
/
whisper-small-np

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Nepali
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
kiranpantha commited on
Commit
9fe8564
•
1 Parent(s): 9f3dfc3

End of training

Browse files
Files changed (3) hide show
  1. README.md +14 -14
  2. model.safetensors +1 -1
  3. runs/Aug24_11-14-24_kiran/events.out.tfevents.1724477389.kiran.5565.0 +2 -2
README.md CHANGED
@@ -25,7 +25,7 @@ model-index:
25
  metrics:
26
  - name: Wer
27
  type: wer
28
- value: 48.043676069153776
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
35
 
36
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the OpenSLR54 dataset.
37
  It achieves the following results on the evaluation set:
38
- - Loss: 0.3013
39
- - Wer: 48.0437
40
 
41
  ## Model description
42
 
@@ -62,23 +62,23 @@ The following hyperparameters were used during training:
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 100
65
- - training_steps: 1000
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Wer |
71
  |:-------------:|:------:|:----:|:---------------:|:-------:|
72
- | 0.8572 | 0.4785 | 100 | 0.4851 | 76.0692 |
73
- | 0.4 | 0.9569 | 200 | 0.3592 | 64.0582 |
74
- | 0.2329 | 1.4354 | 300 | 0.3153 | 56.2329 |
75
- | 0.2098 | 1.9139 | 400 | 0.2918 | 53.5032 |
76
- | 0.1189 | 2.3923 | 500 | 0.2865 | 51.4104 |
77
- | 0.096 | 2.8708 | 600 | 0.2835 | 50.7734 |
78
- | 0.0565 | 3.3493 | 700 | 0.2984 | 50.9554 |
79
- | 0.0425 | 3.8278 | 800 | 0.2947 | 48.7716 |
80
- | 0.027 | 4.3062 | 900 | 0.3007 | 49.4995 |
81
- | 0.0174 | 4.7847 | 1000 | 0.3013 | 48.0437 |
82
 
83
 
84
  ### Framework versions
 
25
  metrics:
26
  - name: Wer
27
  type: wer
28
+ value: 30.25462962962963
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
35
 
36
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the OpenSLR54 dataset.
37
  It achieves the following results on the evaluation set:
38
+ - Loss: 0.2112
39
+ - Wer: 30.2546
40
 
41
  ## Model description
42
 
 
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 100
65
+ - training_steps: 5000
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Wer |
71
  |:-------------:|:------:|:----:|:---------------:|:-------:|
72
+ | 0.2615 | 0.5995 | 500 | 0.2454 | 47.2685 |
73
+ | 0.123 | 1.1990 | 1000 | 0.1994 | 39.3287 |
74
+ | 0.1145 | 1.7986 | 1500 | 0.1835 | 36.1574 |
75
+ | 0.0547 | 2.3981 | 2000 | 0.1813 | 33.7037 |
76
+ | 0.0506 | 2.9976 | 2500 | 0.1730 | 32.2454 |
77
+ | 0.0204 | 3.5971 | 3000 | 0.1911 | 32.2454 |
78
+ | 0.0079 | 4.1966 | 3500 | 0.2009 | 31.6667 |
79
+ | 0.0061 | 4.7962 | 4000 | 0.2022 | 30.0926 |
80
+ | 0.0022 | 5.3957 | 4500 | 0.2097 | 30.2546 |
81
+ | 0.0022 | 5.9952 | 5000 | 0.2112 | 30.2546 |
82
 
83
 
84
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89a2f5f52fabbcf840883e37add1b2cb1d7b6025b7e78478820b547141b759e4
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97efcb29bf6a802a68da4e134ba2af015ed57c41468b56132ebcf544974a7b7a
3
  size 966995080
runs/Aug24_11-14-24_kiran/events.out.tfevents.1724477389.kiran.5565.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdd857becc2a2774f2ac1ed8bf9ef9d3ac152b71ad6e8708f6689d709d9bb4f2
3
- size 19024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c75a96864e3a06f18bace1ecfdd8cfe808ec99ce91e0e42e825a2abd05fb5b2
3
+ size 20751