Hugging Face's logo

ercaronte
/
whisper-tiny

Automatic Speech Recognition
Transformers
PyTorch
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
ercaronte commited on
Commit
6351dd9
•
1 Parent(s): 96a8f46

End of training

Browse files
Files changed (3) hide show
  1. README.md +11 -9
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.36717827626918537
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-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.7837
36
- - Wer Ortho: 0.3671
37
- - Wer: 0.3672
38
 
39
  ## Model description
40
 
@@ -60,16 +60,18 @@ The following hyperparameters were used during training:
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: constant_with_warmup
62
  - lr_scheduler_warmup_steps: 50
63
- - training_steps: 2000
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
68
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
69
- | 0.0007 | 17.86 | 500 | 0.6497 | 0.3448 | 0.3406 |
70
- | 0.0002 | 35.71 | 1000 | 0.7130 | 0.3640 | 0.3625 |
71
- | 0.0001 | 53.57 | 1500 | 0.7534 | 0.3671 | 0.3672 |
72
- | 0.0001 | 71.43 | 2000 | 0.7837 | 0.3671 | 0.3672 |
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.3482880755608028
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: 0.6761
36
+ - Wer Ortho: 0.3516
37
+ - Wer: 0.3483
38
 
39
  ## Model description
40
 
 
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: constant_with_warmup
62
  - lr_scheduler_warmup_steps: 50
63
+ - training_steps: 750
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
68
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
69
+ | 0.2012 | 4.46 | 125 | 0.5011 | 0.3714 | 0.3542 |
70
+ | 0.0102 | 8.93 | 250 | 0.5741 | 0.3578 | 0.3459 |
71
+ | 0.0013 | 13.39 | 375 | 0.6115 | 0.3498 | 0.3418 |
72
+ | 0.0007 | 17.86 | 500 | 0.6403 | 0.3492 | 0.3447 |
73
+ | 0.0005 | 22.32 | 625 | 0.6610 | 0.3510 | 0.3465 |
74
+ | 0.0004 | 26.79 | 750 | 0.6761 | 0.3516 | 0.3483 |
75
 
76
 
77
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2a5cc2d5b94b63a2003c68f99a65931792c4704e1539866e594f1a0bf4189f9
3
  size 151099049
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:787c07d19a7a1b4e9af6e72325326f6e3769d357231be00a639a78136db15abf
3
  size 151099049
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aacdb5c07b37da7fdd760ef3485619133d783b6d9b11335fa60b20c023a444c7
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3ea9c9ce1f54bc0eb5a06b6b3a97f7385037c201626708a2a68ff73a245984
3
  size 4155