Hugging Face's logo

ymoslem
/
whisper-small-ga2en-v5.2.1-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
191e618
•
1 Parent(s): 5e43fa4

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-v3.1-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-v3.1-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: 30.11
32
+ - name: Wer
33
+ type: wer
34
+ value: 71.49932462854571
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: 1.3512
45
+ - Bleu: 30.11
46
+ - Chrf: 46.73
47
+ - Wer: 71.4993
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
+ | 2.3533 | 0.0438 | 100 | 1.7789 | 6.29 | 25.08 | 148.7618 |
80
+ | 1.9035 | 0.0876 | 200 | 1.5122 | 18.21 | 34.02 | 85.6821 |
81
+ | 1.5357 | 0.1313 | 300 | 1.3983 | 14.01 | 33.7 | 93.3363 |
82
+ | 1.3056 | 0.1751 | 400 | 1.3447 | 18.12 | 37.35 | 95.0023 |
83
+ | 1.1177 | 0.2189 | 500 | 1.3168 | 18.47 | 38.44 | 95.3624 |
84
+ | 0.984 | 0.2627 | 600 | 1.3202 | 26.82 | 41.23 | 67.3120 |
85
+ | 0.8945 | 0.3065 | 700 | 1.2947 | 26.73 | 42.53 | 67.1319 |
86
+ | 0.7508 | 0.3503 | 800 | 1.2476 | 25.67 | 42.06 | 74.2008 |
87
+ | 0.7127 | 0.3940 | 900 | 1.2630 | 22.59 | 41.05 | 75.7767 |
88
+ | 0.5944 | 0.4378 | 1000 | 1.2726 | 22.37 | 40.31 | 82.4854 |
89
+ | 0.4972 | 0.4816 | 1100 | 1.2898 | 22.88 | 42.52 | 82.5304 |
90
+ | 0.4517 | 0.5254 | 1200 | 1.2509 | 27.99 | 44.42 | 64.1603 |
91
+ | 0.3885 | 0.5692 | 1300 | 1.2887 | 29.58 | 44.8 | 63.1247 |
92
+ | 0.3337 | 0.6130 | 1400 | 1.2645 | 30.05 | 45.5 | 62.6294 |
93
+ | 0.2852 | 0.6567 | 1500 | 1.2972 | 28.2 | 43.57 | 68.6628 |
94
+ | 0.2583 | 0.7005 | 1600 | 1.2716 | 28.21 | 45.06 | 73.6155 |
95
+ | 0.2016 | 0.7443 | 1700 | 1.3346 | 27.55 | 43.21 | 74.3809 |
96
+ | 0.1883 | 0.7881 | 1800 | 1.3124 | 21.45 | 41.83 | 94.1018 |
97
+ | 0.1514 | 0.8319 | 1900 | 1.3178 | 28.2 | 44.09 | 63.7551 |
98
+ | 0.1311 | 0.8757 | 2000 | 1.3246 | 27.33 | 43.25 | 74.3359 |
99
+ | 0.1128 | 0.9194 | 2100 | 1.3464 | 25.21 | 42.93 | 83.2508 |
100
+ | 0.0994 | 0.9632 | 2200 | 1.3315 | 30.51 | 45.74 | 64.7456 |
101
+ | 0.0512 | 1.0070 | 2300 | 1.3377 | 30.89 | 46.44 | 63.3498 |
102
+ | 0.0447 | 1.0508 | 2400 | 1.3587 | 28.72 | 44.36 | 64.3404 |
103
+ | 0.0368 | 1.0946 | 2500 | 1.3619 | 31.53 | 46.56 | 61.9541 |
104
+ | 0.0281 | 1.1384 | 2600 | 1.3596 | 30.98 | 46.45 | 70.4638 |
105
+ | 0.0273 | 1.1821 | 2700 | 1.3656 | 32.09 | 46.85 | 62.1792 |
106
+ | 0.0287 | 1.2259 | 2800 | 1.3547 | 32.57 | 47.04 | 62.0891 |
107
+ | 0.025 | 1.2697 | 2900 | 1.3539 | 26.94 | 45.43 | 81.1796 |
108
+ | 0.0263 | 1.3135 | 3000 | 1.3512 | 30.11 | 46.73 | 71.4993 |
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 sha256:29c1bc04be912c53831970e0dddcc717c9240a98f9aeb59fcd79df7ec62c7461
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5e2498c53a29af8e6607de11dc14d250dd0133ecf3a75fb9947a864c2eeb0f
3
  size 966995080