Hugging Face's logo

Leotrim
/
whisper-tiny-en

Automatic Speech Recognition
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results
Model card Files Metrics Community
Leotrim commited on
Commit
fb8c546
•
1 Parent(s): a2da4b3

End of training

Browse files
Files changed (2) hide show
  1. README.md +10 -11
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,8 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 35.89887640449439
26
- pipeline_tag: automatic-speech-recognition
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 3.4448
37
- - Wer Ortho: 48.1176
38
- - Wer: 35.8989
39
 
40
  ## Model description
41
 
@@ -63,15 +62,15 @@ The following hyperparameters were used during training:
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: constant_with_warmup
65
  - lr_scheduler_warmup_steps: 50
66
- - training_steps: 2
67
  - mixed_precision_training: Native AMP
68
 
69
  ### Training results
70
 
71
- | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
72
- |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
73
- | 3.7692 | 0.0714 | 1 | 3.4448 | 48.1176 | 35.8989 |
74
- | 3.3965 | 0.1429 | 2 | 3.4448 | 48.1176 | 35.8989 |
75
 
76
 
77
  ### Framework versions
@@ -79,4 +78,4 @@ The following hyperparameters were used during training:
79
  - Transformers 4.42.3
80
  - Pytorch 2.1.2
81
  - Datasets 2.20.0
82
- - Tokenizers 0.19.1
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.28903857930189836
 
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-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.5945
36
+ - Wer Ortho: 0.2898
37
+ - Wer: 0.2890
38
 
39
  ## Model description
40
 
 
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: constant_with_warmup
64
  - lr_scheduler_warmup_steps: 50
65
+ - training_steps: 200
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
71
+ |:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|
72
+ | 0.2419 | 7.1429 | 100 | 0.4865 | 0.2942 | 0.2866 |
73
+ | 0.0048 | 14.2857 | 200 | 0.5945 | 0.2898 | 0.2890 |
74
 
75
 
76
  ### Framework versions
 
78
  - Transformers 4.42.3
79
  - Pytorch 2.1.2
80
  - Datasets 2.20.0
81
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ef96e5cb782b53e6c4bb39fb608363e1f7ec567ada900f5a0a8e2a2fca373ef
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1700609397770e4f8c35df755273419719565a3ffe26549798ac667e9c25d0c3
3
  size 151061672