Hugging Face's logo

ymoslem
/
whisper-small-ga2en-v5.4-r

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Irish
English
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ymoslem commited on
Commit
7c287e2
•
1 Parent(s): e7c5ebd

End of training

Browse files
Files changed (2) hide show
  1. README.md +71 -4
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,19 +1,50 @@
1
  ---
 
 
 
2
  license: apache-2.0
3
  base_model: openai/whisper-small
4
  tags:
5
  - generated_from_trainer
 
 
 
 
 
 
 
 
 
 
6
  model-index:
7
- - name: whisper-small-ga2en-v5.4-r
8
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
- # whisper-small-ga2en-v5.4-r
15
 
16
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
 
 
 
 
 
17
 
18
  ## Model description
19
 
@@ -41,6 +72,42 @@ The following hyperparameters were used during training:
41
  - training_steps: 3000
42
  - mixed_precision_training: Native AMP
43
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
  ### Framework versions
45
 
46
  - Transformers 4.40.2
 
1
  ---
2
+ language:
3
+ - ga
4
+ - en
5
  license: apache-2.0
6
  base_model: openai/whisper-small
7
  tags:
8
  - generated_from_trainer
9
+ datasets:
10
+ - ymoslem/IWSLT2023-GA-EN
11
+ - ymoslem/FLEURS-GA-EN
12
+ - ymoslem/BitesizeIrish-GA-EN
13
+ - ymoslem/SpokenWords-GA-EN-MTed
14
+ - ymoslem/Tatoeba-Speech-Irish
15
+ - ymoslem/Wikimedia-Speech-Irish
16
+ metrics:
17
+ - bleu
18
+ - wer
19
  model-index:
20
+ - name: Whisper Small GA-EN Speech Translation
21
+ results:
22
+ - task:
23
+ name: Automatic Speech Recognition
24
+ type: automatic-speech-recognition
25
+ dataset:
26
+ name: IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia + augmented
27
+ type: ymoslem/IWSLT2023-GA-EN
28
+ metrics:
29
+ - name: Bleu
30
+ type: bleu
31
+ value: 28.44
32
+ - name: Wer
33
+ type: wer
34
+ value: 72.62494371904548
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
38
  should probably proofread and complete it, then remove this comment. -->
39
 
40
+ # Whisper Small GA-EN Speech Translation
41
 
42
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia + augmented dataset.
43
+ It achieves the following results on the evaluation set:
44
+ - Loss: 1.3641
45
+ - Bleu: 28.44
46
+ - Chrf: 43.55
47
+ - Wer: 72.6249
48
 
49
  ## Model description
50
 
 
72
  - training_steps: 3000
73
  - mixed_precision_training: Native AMP
74
 
75
+ ### Training results
76
+
77
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf | Wer |
78
+ |:-------------:|:------:|:----:|:---------------:|:-----:|:-----:|:--------:|
79
+ | 2.3595 | 0.0438 | 100 | 1.7944 | 9.69 | 26.37 | 114.4529 |
80
+ | 1.9008 | 0.0876 | 200 | 1.5391 | 14.89 | 32.44 | 93.6065 |
81
+ | 1.535 | 0.1313 | 300 | 1.3972 | 18.24 | 33.57 | 81.9901 |
82
+ | 1.3307 | 0.1751 | 400 | 1.3684 | 21.34 | 37.37 | 72.8050 |
83
+ | 1.1263 | 0.2189 | 500 | 1.3284 | 19.33 | 39.83 | 91.8955 |
84
+ | 0.9805 | 0.2627 | 600 | 1.3301 | 23.67 | 38.68 | 78.3881 |
85
+ | 0.8989 | 0.3065 | 700 | 1.3123 | 20.32 | 36.94 | 76.3170 |
86
+ | 0.7557 | 0.3503 | 800 | 1.2717 | 25.74 | 40.16 | 72.4448 |
87
+ | 0.7216 | 0.3940 | 900 | 1.3090 | 22.34 | 37.79 | 78.9284 |
88
+ | 0.6131 | 0.4378 | 1000 | 1.2566 | 24.36 | 41.49 | 74.5160 |
89
+ | 0.5032 | 0.4816 | 1100 | 1.2742 | 21.69 | 41.12 | 83.3859 |
90
+ | 0.4567 | 0.5254 | 1200 | 1.2893 | 24.33 | 40.05 | 70.8690 |
91
+ | 0.3968 | 0.5692 | 1300 | 1.3000 | 26.97 | 41.45 | 69.6083 |
92
+ | 0.3353 | 0.6130 | 1400 | 1.2784 | 27.51 | 43.97 | 63.9352 |
93
+ | 0.2826 | 0.6567 | 1500 | 1.3165 | 24.36 | 39.83 | 70.6439 |
94
+ | 0.2643 | 0.7005 | 1600 | 1.3317 | 24.98 | 40.01 | 68.6628 |
95
+ | 0.2047 | 0.7443 | 1700 | 1.2905 | 28.01 | 42.72 | 65.8262 |
96
+ | 0.1946 | 0.7881 | 1800 | 1.2820 | 26.17 | 42.46 | 64.9257 |
97
+ | 0.1588 | 0.8319 | 1900 | 1.3172 | 26.9 | 43.02 | 63.5299 |
98
+ | 0.1322 | 0.8757 | 2000 | 1.3248 | 27.78 | 43.53 | 63.8001 |
99
+ | 0.1134 | 0.9194 | 2100 | 1.3198 | 28.98 | 45.27 | 72.7600 |
100
+ | 0.1031 | 0.9632 | 2200 | 1.3502 | 29.18 | 44.77 | 68.3476 |
101
+ | 0.0518 | 1.0070 | 2300 | 1.3433 | 28.6 | 42.96 | 69.0230 |
102
+ | 0.0481 | 1.0508 | 2400 | 1.3715 | 29.01 | 44.46 | 69.6983 |
103
+ | 0.0367 | 1.0946 | 2500 | 1.3696 | 26.94 | 42.39 | 73.6605 |
104
+ | 0.0309 | 1.1384 | 2600 | 1.3665 | 28.12 | 43.32 | 70.3737 |
105
+ | 0.0302 | 1.1821 | 2700 | 1.3836 | 29.6 | 44.56 | 67.2220 |
106
+ | 0.0302 | 1.2259 | 2800 | 1.3667 | 29.0 | 44.33 | 67.2220 |
107
+ | 0.0252 | 1.2697 | 2900 | 1.3633 | 29.07 | 44.09 | 70.6889 |
108
+ | 0.0257 | 1.3135 | 3000 | 1.3641 | 28.44 | 43.55 | 72.6249 |
109
+
110
+
111
  ### Framework versions
112
 
113
  - Transformers 4.40.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12f4893f48cb6bb233fe15830778706e987de40808d87b7e83c01cd99b4be485
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79abff56d1259efd585a3da55e42f8d9e658fc5e94bd2eb1b7a79a874cab35fc
3
  size 966995080