Hugging Face's logo

rambaldi47
/
whisper-tiny

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
rambaldi47 commited on
Commit
21201ae
•
1 Parent(s): a096a1d

End of training

Browse files
Files changed (3) hide show
  1. README.md +15 -8
  2. model.safetensors +1 -1
  3. runs/Feb04_11-32-00_MSI/events.out.tfevents.1707046324.MSI +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 67.9456906729634
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: 0.7255
36
- - Wer Ortho: 68.2295
37
- - Wer: 67.9457
38
 
39
  ## Model description
40
 
@@ -60,14 +60,21 @@ 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: 500
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
69
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
70
- | 0.0013 | 17.86 | 500 | 0.7255 | 68.2295 | 67.9457 |
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 72.78630460448642
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: 0.9515
36
+ - Wer Ortho: 72.7329
37
+ - Wer: 72.7863
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: 4000
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
69
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
70
+ | 0.0012 | 17.86 | 500 | 0.7266 | 67.7360 | 67.3554 |
71
+ | 0.0002 | 35.71 | 1000 | 0.7895 | 74.0284 | 73.9079 |
72
+ | 0.0001 | 53.57 | 1500 | 0.8302 | 74.9537 | 74.9115 |
73
+ | 0.0001 | 71.43 | 2000 | 0.8608 | 75.2622 | 75.0885 |
74
+ | 0.0 | 89.29 | 2500 | 0.8869 | 74.0284 | 73.9079 |
75
+ | 0.0 | 107.14 | 3000 | 0.9105 | 73.9667 | 73.9079 |
76
+ | 0.0 | 125.0 | 3500 | 0.9309 | 73.5965 | 73.5537 |
77
+ | 0.0 | 142.86 | 4000 | 0.9515 | 72.7329 | 72.7863 |
78
 
79
 
80
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4dcd1984d6cfee4de702edba1a2c1c5d66337081973f31d024c6b0ab204dd17
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aec8983b53e8f84a32b77d3100c2464ed852dd628d4081aa465251540568535
3
  size 151061672
runs/Feb04_11-32-00_MSI/events.out.tfevents.1707046324.MSI CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e4d45de9e94a6ee2b1990229c7c7405c15e422621175d546e29877ce7e1f29e
3
- size 30319
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:948ba90ad26712d80e4e92937730c16952cc81c72801393738e273e3a9fef433
3
+ size 34555