Hugging Face's logo

golesheed
/
whisper-non-native-children-0-dutch

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Dutch
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
golesheed commited on
Commit
8b5f200
•
1 Parent(s): 2ead7fd

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -10
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
README.md CHANGED
@@ -2,11 +2,11 @@
2
  language:
3
  - nl
4
  license: apache-2.0
 
5
  tags:
6
  - generated_from_trainer
7
  metrics:
8
  - wer
9
- base_model: openai/whisper-large-v2
10
  model-index:
11
  - name: Whisper Large V2
12
  results: []
@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.4187
23
- - Wer: 18.2001
24
 
25
  ## Model description
26
 
@@ -52,13 +52,13 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
55
- | 0.6744 | 0.71 | 30 | 0.4187 | 15.6079 |
56
- | 0.2734 | 1.43 | 60 | 0.3785 | 13.9467 |
57
- | 0.1699 | 2.14 | 90 | 0.3904 | 13.7459 |
58
- | 0.0806 | 2.86 | 120 | 0.3817 | 12.6871 |
59
- | 0.0436 | 3.57 | 150 | 0.3985 | 13.0522 |
60
- | 0.0245 | 4.29 | 180 | 0.4109 | 17.6707 |
61
- | 0.0117 | 5.0 | 210 | 0.4187 | 18.2001 |
62
 
63
 
64
  ### Framework versions
 
2
  language:
3
  - nl
4
  license: apache-2.0
5
+ base_model: openai/whisper-large-v2
6
  tags:
7
  - generated_from_trainer
8
  metrics:
9
  - wer
 
10
  model-index:
11
  - name: Whisper Large V2
12
  results: []
 
19
 
20
  This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.3707
23
+ - Wer: 12.5219
24
 
25
  ## Model description
26
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
55
+ | 0.6724 | 0.71 | 30 | 0.3868 | 19.2016 |
56
+ | 0.2748 | 1.43 | 60 | 0.3584 | 15.3846 |
57
+ | 0.1701 | 2.14 | 90 | 0.3415 | 13.5346 |
58
+ | 0.0814 | 2.86 | 120 | 0.3366 | 13.3398 |
59
+ | 0.0419 | 3.57 | 150 | 0.3567 | 13.3982 |
60
+ | 0.0254 | 4.29 | 180 | 0.3627 | 12.7167 |
61
+ | 0.0124 | 5.0 | 210 | 0.3707 | 12.5219 |
62
 
63
 
64
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bdd2bba0dcfc0279c596afb30d3b61f6d1d74889a29e88d9fd4701ecf7b7a7c
3
  size 4992706480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:902c04b9fe02c69e6957b337e2c06ce63d81678e4016b4dd06e55b24eda1ab86
3
  size 4992706480
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:750c7a8285bf6e2a32ac60fe744777bb7715d2e6cf97cd48983a3de106659bec
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7ac4f74ff1a9542a7c874564e6cd5738b3f541927663ac0d21eae858a7eca8
3
  size 1180663192