Hugging Face's logo

DewiBrynJones
/
whisper-large-v3-ft-cy-en

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
DewiBrynJones commited on
Commit
8bc2f08
•
1 Parent(s): c55a0c3

Model save

Browse files
Files changed (4) hide show
  1. README.md +15 -21
  2. generation_config.json +2 -2
  3. model-00001-of-00002.safetensors +1 -1
  4. model-00002-of-00002.safetensors +1 -1
README.md CHANGED
@@ -6,12 +6,8 @@ tags:
6
  metrics:
7
  - wer
8
  model-index:
9
- - name: whisper-large-v3-ft-cy
10
  results: []
11
- language:
12
- - cy
13
- - en
14
- pipeline_tag: automatic-speech-recognition
15
  ---
16
 
17
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -19,12 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # whisper-large-v3-ft-cy-en
21
 
22
- This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on Welsh
23
- and English bilingual data originally from Mozilla's Common Voice dataset (see: [techiaith/commonvoice_16_1_en_cy](https://huggingface.co/datasets/techiaith/commonvoice_16_1_en_cy)).
24
-
25
  It achieves the following results on the evaluation set:
26
- - Loss: 0.1480
27
- - Wer: 25.1341
28
 
29
  ## Model description
30
 
@@ -45,7 +39,7 @@ More information needed
45
  The following hyperparameters were used during training:
46
  - learning_rate: 1e-05
47
  - train_batch_size: 4
48
- - eval_batch_size: 8
49
  - seed: 42
50
  - gradient_accumulation_steps: 8
51
  - total_train_batch_size: 32
@@ -56,17 +50,17 @@ The following hyperparameters were used during training:
56
 
57
  ### Training results
58
 
59
- | Training Loss | Epoch | Step | Validation Loss | Wer |
60
- |:-------------:|:-----:|:----:|:---------------:|:-------:|
61
- | 0.2078 | 0.25 | 1000 | 0.2198 | 28.7556 |
62
- | 0.1623 | 0.5 | 2000 | 0.1800 | 31.3698 |
63
- | 0.1417 | 0.75 | 3000 | 0.1585 | 18.7051 |
64
- | 0.1188 | 1.01 | 4000 | 0.1480 | 25.1341 |
65
 
66
 
67
  ### Framework versions
68
 
69
- - Transformers 4.37.1
70
- - Pytorch 2.1.2+cu121
71
- - Datasets 2.16.1
72
- - Tokenizers 0.15.1
 
6
  metrics:
7
  - wer
8
  model-index:
9
+ - name: whisper-large-v3-ft-cy-en
10
  results: []
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
15
 
16
  # whisper-large-v3-ft-cy-en
17
 
18
+ This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
 
 
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1505
21
+ - Wer: 9.5594
22
 
23
  ## Model description
24
 
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-05
41
  - train_batch_size: 4
42
+ - eval_batch_size: 1
43
  - seed: 42
44
  - gradient_accumulation_steps: 8
45
  - total_train_batch_size: 32
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:----:|:---------------:|:-------:|
55
+ | 0.2097 | 0.2497 | 1000 | 0.2169 | 14.2221 |
56
+ | 0.1621 | 0.4993 | 2000 | 0.1816 | 11.6845 |
57
+ | 0.1406 | 0.7490 | 3000 | 0.1609 | 10.2445 |
58
+ | 0.1242 | 0.9987 | 4000 | 0.1505 | 9.5594 |
59
 
60
 
61
  ### Framework versions
62
 
63
+ - Transformers 4.41.2
64
+ - Pytorch 2.3.1+cu121
65
+ - Datasets 2.20.0
66
+ - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -55,7 +55,7 @@
55
  ],
56
  [
57
  2,
58
- 50359
59
  ]
60
  ],
61
  "is_multilingual": true,
@@ -261,5 +261,5 @@
261
  "transcribe": 50360,
262
  "translate": 50359
263
  },
264
- "transformers_version": "4.37.1"
265
  }
 
55
  ],
56
  [
57
  2,
58
+ 50360
59
  ]
60
  ],
61
  "is_multilingual": true,
 
261
  "transcribe": 50360,
262
  "translate": 50359
263
  },
264
+ "transformers_version": "4.41.2"
265
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6686fe3c7690f628e5ab073f06e026348ba174fb5fdd60bb29da596b5b876cda
3
  size 4993448880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeac4c7c783ddd9a08930830ff734432479bc59efa7a96c546955f80e1cb192b
3
  size 4993448880
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d6beb4de5b782026f3ae2233a375c9c67631bb4cbf13783a2afdbf8b4441293
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d682caf14f5143a8bf317078201ed4111ef74d97eeccf9d63043c320dae16d6
3
  size 1180663192