Hugging Face's logo

ymoslem
/
whisper-medium-ga2en-v6.3.0-4k-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
a1f2b43
•
1 Parent(s): 4b2f0b4

End of training

Browse files
Files changed (1) hide show
  1. README.md +82 -4
README.md CHANGED
@@ -1,19 +1,51 @@
1
  ---
 
 
 
2
  license: apache-2.0
3
  base_model: openai/whisper-medium
4
  tags:
5
  - generated_from_trainer
 
 
 
 
 
 
 
 
 
 
 
6
  model-index:
7
- - name: whisper-medium-ga2en-v6.3.0-4k-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-medium-ga2en-v6.3.0-4k-r
15
 
16
- This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
 
 
 
 
 
17
 
18
  ## Model description
19
 
@@ -42,6 +74,52 @@ The following hyperparameters were used during training:
42
  - training_steps: 4000
43
  - mixed_precision_training: Native AMP
44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  ### Framework versions
46
 
47
  - Transformers 4.41.2
 
1
  ---
2
+ language:
3
+ - ga
4
+ - en
5
  license: apache-2.0
6
  base_model: openai/whisper-medium
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
+ - ymoslem/EUbookshop-Speech-Irish
17
+ metrics:
18
+ - bleu
19
+ - wer
20
  model-index:
21
+ - name: Whisper Medium GA-EN Speech Translation
22
+ results:
23
+ - task:
24
+ name: Automatic Speech Recognition
25
+ type: automatic-speech-recognition
26
+ dataset:
27
+ name: IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, Wikimedia, and EUbookshop
28
+ type: ymoslem/IWSLT2023-GA-EN
29
+ metrics:
30
+ - name: Bleu
31
+ type: bleu
32
+ value: 33.24
33
+ - name: Wer
34
+ type: wer
35
+ value: 61.50382710490771
36
  ---
37
 
38
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
39
  should probably proofread and complete it, then remove this comment. -->
40
 
41
+ # Whisper Medium GA-EN Speech Translation
42
 
43
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, Wikimedia, and EUbookshop dataset.
44
+ It achieves the following results on the evaluation set:
45
+ - Loss: 1.0552
46
+ - Bleu: 33.24
47
+ - Chrf: 55.16
48
+ - Wer: 61.5038
49
 
50
  ## Model description
51
 
 
74
  - training_steps: 4000
75
  - mixed_precision_training: Native AMP
76
 
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf | Wer |
80
+ |:-------------:|:------:|:----:|:---------------:|:-----:|:-----:|:--------:|
81
+ | 2.5219 | 0.0138 | 100 | 2.1106 | 0.44 | 10.48 | 107.2490 |
82
+ | 2.4608 | 0.0276 | 200 | 2.1816 | 3.3 | 20.43 | 179.1535 |
83
+ | 2.3008 | 0.0414 | 300 | 2.0587 | 3.66 | 21.59 | 206.4836 |
84
+ | 2.2095 | 0.0552 | 400 | 1.9459 | 8.79 | 27.66 | 100.3602 |
85
+ | 2.0454 | 0.0690 | 500 | 1.8681 | 8.14 | 27.36 | 122.1522 |
86
+ | 1.9937 | 0.0828 | 600 | 1.8717 | 11.05 | 30.26 | 97.2535 |
87
+ | 1.868 | 0.0966 | 700 | 1.7917 | 9.14 | 29.03 | 129.0410 |
88
+ | 1.9924 | 0.1103 | 800 | 1.7170 | 12.62 | 33.2 | 89.6443 |
89
+ | 1.8646 | 0.1241 | 900 | 1.7252 | 11.98 | 30.77 | 97.8838 |
90
+ | 1.7644 | 0.1379 | 1000 | 1.6832 | 10.87 | 31.0 | 109.1851 |
91
+ | 1.692 | 0.1517 | 1100 | 1.6837 | 13.05 | 34.46 | 93.3814 |
92
+ | 1.7044 | 0.1655 | 1200 | 1.5527 | 20.95 | 37.42 | 75.2364 |
93
+ | 1.6824 | 0.1793 | 1300 | 1.5611 | 14.91 | 35.56 | 92.6159 |
94
+ | 1.6557 | 0.1931 | 1400 | 1.5554 | 14.0 | 36.54 | 99.8199 |
95
+ | 1.5456 | 0.2069 | 1500 | 1.5058 | 19.72 | 39.81 | 83.5660 |
96
+ | 1.3755 | 0.2207 | 1600 | 1.5039 | 18.04 | 37.95 | 82.9806 |
97
+ | 1.3959 | 0.2345 | 1700 | 1.4374 | 17.01 | 39.5 | 85.2319 |
98
+ | 1.5012 | 0.2483 | 1800 | 1.4242 | 14.93 | 39.24 | 114.4079 |
99
+ | 1.4278 | 0.2621 | 1900 | 1.3904 | 23.85 | 42.69 | 73.0302 |
100
+ | 1.3285 | 0.2759 | 2000 | 1.4493 | 17.7 | 37.23 | 83.8811 |
101
+ | 1.2655 | 0.2897 | 2100 | 1.3661 | 20.1 | 40.32 | 79.7839 |
102
+ | 1.2074 | 0.3034 | 2200 | 1.3387 | 24.45 | 43.79 | 72.9851 |
103
+ | 1.1893 | 0.3172 | 2300 | 1.3308 | 21.45 | 42.61 | 82.3953 |
104
+ | 1.1236 | 0.3310 | 2400 | 1.3050 | 22.77 | 44.17 | 77.3075 |
105
+ | 1.0934 | 0.3448 | 2500 | 1.2793 | 25.54 | 46.32 | 72.2647 |
106
+ | 1.06 | 0.3586 | 2600 | 1.2396 | 28.27 | 47.32 | 65.6911 |
107
+ | 1.0327 | 0.3724 | 2700 | 1.2577 | 28.45 | 47.01 | 67.3570 |
108
+ | 1.1623 | 0.3862 | 2800 | 1.2194 | 24.54 | 47.43 | 73.6155 |
109
+ | 1.0215 | 0.4 | 2900 | 1.2039 | 27.4 | 49.6 | 69.2481 |
110
+ | 0.9185 | 0.4138 | 3000 | 1.1724 | 27.04 | 49.24 | 67.8973 |
111
+ | 0.9003 | 0.4276 | 3100 | 1.1674 | 31.08 | 50.11 | 63.8001 |
112
+ | 0.9839 | 0.4414 | 3200 | 1.1580 | 30.24 | 50.63 | 64.5655 |
113
+ | 0.9396 | 0.4552 | 3300 | 1.1202 | 30.79 | 51.72 | 64.9257 |
114
+ | 0.9051 | 0.4690 | 3400 | 1.1180 | 30.34 | 53.08 | 66.4566 |
115
+ | 0.8621 | 0.4828 | 3500 | 1.1042 | 33.3 | 53.86 | 60.7834 |
116
+ | 0.8236 | 0.4966 | 3600 | 1.1070 | 32.77 | 53.21 | 62.0441 |
117
+ | 0.829 | 0.5103 | 3700 | 1.0771 | 32.49 | 54.21 | 62.5844 |
118
+ | 0.8375 | 0.5241 | 3800 | 1.0780 | 32.27 | 53.98 | 63.0797 |
119
+ | 0.8206 | 0.5379 | 3900 | 1.0615 | 33.26 | 55.07 | 61.6389 |
120
+ | 0.8059 | 0.5517 | 4000 | 1.0552 | 33.24 | 55.16 | 61.5038 |
121
+
122
+
123
  ### Framework versions
124
 
125
  - Transformers 4.41.2