Hugging Face's logo

ChuGyouk
/
whisper-tiny-minds14-en

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ChuGyouk commited on
Commit
868ff5f
•
1 Parent(s): 1e13b81

End of training

Browse files
Files changed (3) hide show
  1. README.md +9 -10
  2. model.safetensors +1 -1
  3. runs/Feb14_16-19-18_rocket/events.out.tfevents.1707895160.rocket.2756443.0 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.3565525383707202
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: 0.5637
36
- - Wer Ortho: 0.3720
37
- - Wer: 0.3566
38
 
39
  ## Model description
40
 
@@ -60,18 +60,17 @@ The following hyperparameters were used during training:
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: cosine
62
  - lr_scheduler_warmup_ratio: 0.1
63
- - num_epochs: 10
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
70
- | 1.2092 | 2.0 | 56 | 0.6048 | 0.4065 | 0.3908 |
71
- | 0.2742 | 4.0 | 112 | 0.5197 | 0.3714 | 0.3577 |
72
- | 0.1131 | 6.0 | 168 | 0.5391 | 0.3671 | 0.3512 |
73
- | 0.0599 | 8.0 | 224 | 0.5592 | 0.3701 | 0.3548 |
74
- | 0.0382 | 10.0 | 280 | 0.5637 | 0.3720 | 0.3566 |
75
 
76
 
77
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.35596221959858326
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: 0.5304
36
+ - Wer Ortho: 0.3745
37
+ - Wer: 0.3560
38
 
39
  ## Model description
40
 
 
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: cosine
62
  - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 7
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
70
+ | 3.549 | 1.43 | 40 | 0.7274 | 0.4263 | 0.3967 |
71
+ | 0.3686 | 2.86 | 80 | 0.5389 | 0.3671 | 0.3501 |
72
+ | 0.2662 | 4.29 | 120 | 0.5264 | 0.3726 | 0.3577 |
73
+ | 0.1372 | 5.71 | 160 | 0.5304 | 0.3745 | 0.3560 |
 
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc16dfcbace81a3aac55253b57808452fef8a0116c7709e35c324d345a50c26c
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eeaef302c14cfc247299d6b2f03ec3db57c98bdda6d6602ca92acaab45ece27
3
  size 151061672
runs/Feb14_16-19-18_rocket/events.out.tfevents.1707895160.rocket.2756443.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:562024e10db96fe905fa9338a7303177e18f7c5b2235acaa06348afd45cfc664
3
- size 8564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ad91655fb74add4ddc1003dfcde3e1c1593905a2ce955aa3659ae375c6271f
3
+ size 9075