Hugging Face's logo

zuazo
/
whisper-tiny-eu-cv17_0

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Basque
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
zuazo commited on
Commit
5319162
·
verified ·
1 Parent(s): 5e5ebc0

Model save

Browse files
Files changed (2) hide show
  1. README.md +24 -24
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,43 +1,40 @@
1
  ---
2
  library_name: transformers
3
- language:
4
- - eu
5
  license: apache-2.0
6
  base_model: openai/whisper-tiny
7
  tags:
8
- - whisper-event
9
  - generated_from_trainer
10
  datasets:
11
- - mozilla-foundation/common_voice_17_0
12
  metrics:
13
  - wer
14
  model-index:
15
- - name: Whisper Tiny Basque
16
  results:
17
  - task:
18
  name: Automatic Speech Recognition
19
  type: automatic-speech-recognition
20
  dataset:
21
- name: mozilla-foundation/common_voice_17_0 eu
22
- type: mozilla-foundation/common_voice_17_0
23
  config: eu
24
  split: test
25
  args: eu
26
  metrics:
27
  - name: Wer
28
  type: wer
29
- value: 20.06852577961816
30
  ---
31
 
32
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
33
  should probably proofread and complete it, then remove this comment. -->
34
 
35
- # Whisper Tiny Basque
36
 
37
- This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the mozilla-foundation/common_voice_17_0 eu dataset.
38
  It achieves the following results on the evaluation set:
39
- - Loss: 0.4785
40
- - Wer: 20.0685
41
 
42
  ## Model description
43
 
@@ -70,18 +67,21 @@ The following hyperparameters were used during training:
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Wer |
72
  |:-------------:|:--------:|:-----:|:---------------:|:-------:|
73
- | 0.0349 | 9.3458 | 1000 | 0.3364 | 22.5082 |
74
- | 0.0077 | 18.6916 | 2000 | 0.4031 | 22.2956 |
75
- | 0.0044 | 28.0374 | 3000 | 0.4228 | 21.8577 |
76
- | 0.0053 | 37.3832 | 4000 | 0.4443 | 21.8376 |
77
- | 0.0003 | 46.7290 | 5000 | 0.4470 | 20.1775 |
78
- | 0.0002 | 56.0748 | 6000 | 0.4631 | 20.0878 |
79
- | 0.0001 | 65.4206 | 7000 | 0.4785 | 20.0685 |
80
- | 0.0001 | 74.7664 | 8000 | 0.4942 | 20.0868 |
81
- | 0.0 | 84.1121 | 9000 | 0.5109 | 20.2792 |
82
- | 0.0 | 93.4579 | 10000 | 0.5286 | 20.2875 |
83
- | 0.0 | 102.8037 | 11000 | 0.5470 | 20.3424 |
84
- | 0.0 | 112.1495 | 12000 | 0.5671 | 20.3608 |
 
 
 
85
 
86
 
87
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  license: apache-2.0
4
  base_model: openai/whisper-tiny
5
  tags:
 
6
  - generated_from_trainer
7
  datasets:
8
+ - common_voice_17_0
9
  metrics:
10
  - wer
11
  model-index:
12
+ - name: openai/whisper-tiny
13
  results:
14
  - task:
15
  name: Automatic Speech Recognition
16
  type: automatic-speech-recognition
17
  dataset:
18
+ name: common_voice_17_0
19
+ type: common_voice_17_0
20
  config: eu
21
  split: test
22
  args: eu
23
  metrics:
24
  - name: Wer
25
  type: wer
26
+ value: 20.868298581846165
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
  should probably proofread and complete it, then remove this comment. -->
31
 
32
+ # openai/whisper-tiny
33
 
34
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_17_0 dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.6486
37
+ - Wer: 20.8683
38
 
39
  ## Model description
40
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:--------:|:-----:|:---------------:|:-------:|
70
+ | 0.0348 | 9.3458 | 1000 | 0.3382 | 22.7152 |
71
+ | 0.0021 | 18.6916 | 2000 | 0.4092 | 21.7844 |
72
+ | 0.0009 | 28.0374 | 3000 | 0.4509 | 21.9026 |
73
+ | 0.0023 | 37.3832 | 4000 | 0.4062 | 20.7181 |
74
+ | 0.0003 | 46.7290 | 5000 | 0.4350 | 20.1244 |
75
+ | 0.0002 | 56.0748 | 6000 | 0.4546 | 20.1702 |
76
+ | 0.0001 | 65.4206 | 7000 | 0.4745 | 20.2179 |
77
+ | 0.0001 | 74.7664 | 8000 | 0.4941 | 20.1995 |
78
+ | 0.0 | 84.1121 | 9000 | 0.5142 | 20.3342 |
79
+ | 0.0 | 93.4579 | 10000 | 0.5353 | 20.4386 |
80
+ | 0.0 | 102.8037 | 11000 | 0.5567 | 20.5495 |
81
+ | 0.0 | 112.1495 | 12000 | 0.5788 | 20.6100 |
82
+ | 0.0 | 121.4953 | 13000 | 0.6023 | 20.6988 |
83
+ | 0.0 | 130.8411 | 14000 | 0.6253 | 20.7767 |
84
+ | 0.0 | 140.1869 | 15000 | 0.6486 | 20.8683 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:271d12a58323a8b382e92200a84188a01cae1904fcce99bf3ade4e8032c0915b
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2e7110b9c131b483382647bd0970b0e481e8387d3377f648cdb2719590f905
3
  size 151061672