Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Irish
English
whisper
Generated from Trainer
Eval Results
Inference Endpoints
ymoslem commited on
Commit
d06e232
1 Parent(s): 1018d63

End of training

Browse files
Files changed (2) hide show
  1. README.md +81 -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-v5.2
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-v5.2
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
 
@@ -42,6 +73,52 @@ The following hyperparameters were used during training:
42
  - training_steps: 4000
43
  - mixed_precision_training: Native AMP
44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  ### Framework versions
46
 
47
  - Transformers 4.40.0
 
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
27
+ type: ymoslem/IWSLT2023-GA-EN
28
+ metrics:
29
+ - name: Bleu
30
+ type: bleu
31
+ value: 30.91
32
+ - name: Wer
33
+ type: wer
34
+ value: 65.10580819450698
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 dataset.
43
+ It achieves the following results on the evaluation set:
44
+ - Loss: 1.2924
45
+ - Bleu: 30.91
46
+ - Chrf: 47.99
47
+ - Wer: 65.1058
48
 
49
  ## Model description
50
 
 
73
  - training_steps: 4000
74
  - mixed_precision_training: Native AMP
75
 
76
+ ### Training results
77
+
78
+ | Training Loss | Epoch | Step | Bleu | Chrf | Validation Loss | Wer |
79
+ |:-------------:|:------:|:----:|:-----:|:-----:|:---------------:|:--------:|
80
+ | 2.7017 | 0.02 | 100 | 2.83 | 14.96 | 2.4392 | 169.5182 |
81
+ | 2.6732 | 0.04 | 200 | 7.27 | 22.72 | 1.9552 | 103.2868 |
82
+ | 2.1622 | 0.07 | 300 | 11.43 | 30.01 | 1.7297 | 108.2395 |
83
+ | 2.0314 | 0.09 | 400 | 12.96 | 31.0 | 1.6499 | 106.4385 |
84
+ | 1.7219 | 0.11 | 500 | 12.94 | 33.67 | 1.5543 | 107.6092 |
85
+ | 1.577 | 0.13 | 600 | 12.84 | 35.03 | 1.4812 | 118.5502 |
86
+ | 1.3569 | 0.1532 | 700 | 19.94 | 38.08 | 1.4559 | 84.2864 |
87
+ | 1.3401 | 0.1751 | 800 | 13.39 | 36.11 | 1.3855 | 126.4295 |
88
+ | 1.2272 | 0.1970 | 900 | 24.39 | 41.75 | 1.3764 | 70.7789 |
89
+ | 1.2793 | 0.2189 | 1000 | 23.01 | 42.13 | 1.3389 | 80.6844 |
90
+ | 1.0383 | 0.2408 | 1100 | 23.42 | 43.59 | 1.3125 | 82.3953 |
91
+ | 1.0485 | 0.2627 | 1200 | 25.42 | 42.99 | 1.2996 | 69.4732 |
92
+ | 1.0427 | 0.2846 | 1300 | 29.24 | 45.36 | 1.2996 | 65.6461 |
93
+ | 0.8174 | 0.3065 | 1400 | 27.28 | 45.67 | 1.2522 | 68.3926 |
94
+ | 0.7345 | 0.3284 | 1500 | 26.35 | 46.78 | 1.2349 | 79.1986 |
95
+ | 0.7551 | 0.3503 | 1600 | 27.81 | 46.49 | 1.2317 | 70.6439 |
96
+ | 0.6765 | 0.3722 | 1700 | 27.62 | 47.46 | 1.2062 | 70.9140 |
97
+ | 0.6613 | 0.3940 | 1800 | 26.56 | 47.12 | 1.2087 | 72.8050 |
98
+ | 0.6181 | 0.4159 | 1900 | 29.91 | 48.76 | 1.2139 | 65.2859 |
99
+ | 0.5809 | 0.4378 | 2000 | 30.93 | 49.09 | 1.2119 | 63.1247 |
100
+ | 0.5898 | 0.4597 | 2100 | 25.91 | 46.24 | 1.2540 | 73.9307 |
101
+ | 0.5926 | 0.4816 | 2200 | 25.19 | 44.72 | 1.2479 | 78.7933 |
102
+ | 0.5158 | 0.5035 | 2300 | 28.9 | 46.76 | 1.2532 | 66.3665 |
103
+ | 0.4511 | 0.5254 | 2400 | 28.89 | 46.83 | 1.2517 | 66.3215 |
104
+ | 0.4329 | 0.5473 | 2500 | 26.19 | 45.91 | 1.2573 | 72.6700 |
105
+ | 0.4106 | 0.5692 | 2600 | 26.91 | 46.84 | 1.2615 | 72.4899 |
106
+ | 0.4002 | 0.5911 | 2700 | 27.77 | 46.93 | 1.2396 | 71.0491 |
107
+ | 0.4047 | 0.6130 | 2800 | 29.9 | 47.79 | 1.2450 | 66.9968 |
108
+ | 0.3719 | 0.6349 | 2900 | 30.5 | 48.78 | 1.2522 | 65.1959 |
109
+ | 0.327 | 0.6567 | 3000 | 31.22 | 49.0 | 1.2493 | 64.1153 |
110
+ | 0.3138 | 0.6786 | 3100 | 1.2653| 30.1 | 47.82 | 65.1959 |
111
+ | 0.3349 | 0.7005 | 3200 | 1.2651| 30.37 | 48.64 | 63.9802 |
112
+ | 0.2807 | 0.7224 | 3300 | 1.2762| 26.02 | 45.46 | 76.8573 |
113
+ | 0.2648 | 0.7443 | 3400 | 1.2761| 30.65 | 47.58 | 64.6105 |
114
+ | 0.2633 | 0.7662 | 3500 | 1.2890| 29.73 | 47.74 | 65.5110 |
115
+ | 0.2316 | 0.7881 | 3600 | 1.2886| 29.94 | 47.33 | 66.4566 |
116
+ | 0.233 | 0.8100 | 3700 | 1.2905| 27.82 | 48.01 | 73.1202 |
117
+ | 0.2196 | 0.8319 | 3800 | 1.2994| 31.51 | 48.66 | 63.7100 |
118
+ | 0.2119 | 0.8538 | 3900 | 1.2910| 30.09 | 48.44 | 65.0158 |
119
+ | 0.2082 | 0.8757 | 4000 | 1.2924| 30.91 | 47.99 | 65.1058 |
120
+
121
+
122
  ### Framework versions
123
 
124
  - Transformers 4.40.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a4e58ad85b876fe6923f9d86a6b13d6bbee00e3cfe472ebae759958232ff2b6
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b492be49940ef2ac3f8e428b259527d7d6129cfc255ee7f7d0ef7d406082fa8
3
  size 966995080