Hugging Face's logo

xezpeleta
/
whisper-medium-eu

Automatic Speech Recognition
Transformers
PyTorch
Safetensors
Basque
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
xezpeleta commited on
Commit
68c652e
·
verified ·
1 Parent(s): 219f22b

Model save

Browse files
Files changed (3) hide show
  1. README.md +26 -44
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -1,43 +1,25 @@
1
  ---
2
  library_name: transformers
3
- language:
4
- - eu
5
  license: apache-2.0
6
  base_model: openai/whisper-medium
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 Medium 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: 8.8020814247499
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 Medium Basque
36
 
37
- This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the mozilla-foundation/common_voice_17_0 eu dataset.
38
  It achieves the following results on the evaluation set:
39
- - Loss: 0.1787
40
- - Wer: 8.8021
41
 
42
  ## Model description
43
 
@@ -70,27 +52,27 @@ The following hyperparameters were used during training:
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Wer |
72
  |:-------------:|:------:|:----:|:---------------:|:-------:|
73
- | 0.3171 | 0.0625 | 500 | 0.3369 | 25.5304 |
74
- | 0.1852 | 0.125 | 1000 | 0.2409 | 17.3110 |
75
- | 0.2353 | 0.1875 | 1500 | 0.2050 | 14.2228 |
76
- | 0.1569 | 1.037 | 2000 | 0.1815 | 12.2861 |
77
- | 0.125 | 1.0995 | 2500 | 0.1692 | 11.1144 |
78
- | 0.12 | 1.162 | 3000 | 0.1600 | 10.6975 |
79
- | 0.069 | 2.0115 | 3500 | 0.1540 | 9.7649 |
80
- | 0.0606 | 2.074 | 4000 | 0.1550 | 9.8199 |
81
- | 0.0434 | 2.1365 | 4500 | 0.1580 | 9.4571 |
82
- | 0.0455 | 2.199 | 5000 | 0.1533 | 9.1410 |
83
- | 0.0216 | 3.0485 | 5500 | 0.1620 | 9.0842 |
84
- | 0.017 | 3.111 | 6000 | 0.1704 | 9.0980 |
85
- | 0.0174 | 3.1735 | 6500 | 0.1681 | 9.0723 |
86
- | 0.0098 | 4.023 | 7000 | 0.1725 | 8.8625 |
87
- | 0.0076 | 4.0855 | 7500 | 0.1765 | 8.8351 |
88
- | 0.007 | 4.148 | 8000 | 0.1787 | 8.8021 |
89
 
90
 
91
  ### Framework versions
92
 
93
- - Transformers 4.46.0.dev0
94
- - Pytorch 2.4.1+cu121
95
- - Datasets 3.0.2.dev0
96
- - Tokenizers 0.20.0
 
1
  ---
2
  library_name: transformers
 
 
3
  license: apache-2.0
4
  base_model: openai/whisper-medium
5
  tags:
 
6
  - generated_from_trainer
 
 
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: openai/whisper-medium
11
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ # openai/whisper-medium
18
 
19
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.2141
22
+ - Wer: 10.1290
23
 
24
  ## Model description
25
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:------:|:----:|:---------------:|:-------:|
55
+ | 0.3412 | 0.0625 | 500 | 0.4570 | 28.2182 |
56
+ | 0.1462 | 0.125 | 1000 | 0.3524 | 19.9402 |
57
+ | 0.2495 | 0.1875 | 1500 | 0.3077 | 17.5236 |
58
+ | 0.2617 | 0.25 | 2000 | 0.2811 | 16.5841 |
59
+ | 0.1646 | 0.3125 | 2500 | 0.2726 | 13.8917 |
60
+ | 0.0934 | 0.375 | 3000 | 0.2533 | 14.0273 |
61
+ | 0.1016 | 0.4375 | 3500 | 0.2331 | 12.1623 |
62
+ | 0.1454 | 0.5 | 4000 | 0.2299 | 11.5546 |
63
+ | 0.1502 | 0.5625 | 4500 | 0.2333 | 12.4007 |
64
+ | 0.0916 | 0.625 | 5000 | 0.2271 | 10.9657 |
65
+ | 0.0914 | 0.6875 | 5500 | 0.2343 | 10.5029 |
66
+ | 0.1093 | 0.75 | 6000 | 0.2191 | 9.9841 |
67
+ | 0.0948 | 0.8125 | 6500 | 0.2215 | 10.5357 |
68
+ | 0.0744 | 0.875 | 7000 | 0.2108 | 11.2368 |
69
+ | 0.1269 | 0.9375 | 7500 | 0.2158 | 10.0028 |
70
+ | 0.1408 | 1.0 | 8000 | 0.2141 | 10.1290 |
71
 
72
 
73
  ### Framework versions
74
 
75
+ - Transformers 4.49.0.dev0
76
+ - Pytorch 2.6.0+cu124
77
+ - Datasets 3.2.1.dev0
78
+ - Tokenizers 0.21.0
generation_config.json CHANGED
@@ -244,5 +244,5 @@
244
  "transcribe": 50359,
245
  "translate": 50358
246
  },
247
- "transformers_version": "4.46.0.dev0"
248
  }
 
244
  "transcribe": 50359,
245
  "translate": 50358
246
  },
247
+ "transformers_version": "4.49.0.dev0"
248
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c680aa1f462ad955cd4515980683d326c639e5b8a7101bba2fc9410426c36c86
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:470a6a9a9d104e4a27318ccdfbed1bd4a07685f954d9e92d5c18b042165a5126
3
  size 3055544304