End of training
Browse files- README.md +81 -4
- model.safetensors +1 -1
README.md
CHANGED
@@ -1,19 +1,50 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: openai/whisper-medium
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
-
- name:
|
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 |
-
#
|
15 |
|
16 |
-
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on
|
|
|
|
|
|
|
|
|
|
|
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 4.41.2
|
|
|
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 |
+
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: 28.6
|
32 |
+
- name: Wer
|
33 |
+
type: wer
|
34 |
+
value: 68.52769022962629
|
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-medium](https://huggingface.co/openai/whisper-medium) on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia dataset.
|
43 |
+
It achieves the following results on the evaluation set:
|
44 |
+
- Loss: 1.1842
|
45 |
+
- Bleu: 28.6
|
46 |
+
- Chrf: 49.54
|
47 |
+
- Wer: 68.5277
|
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 |
+
| 2.5585 | 0.0109 | 100 | 2.94 | 16.53 | 2.1737 | 176.2269 |
|
81 |
+
| 2.5748 | 0.0219 | 200 | 6.93 | 24.84 | 2.0289 | 101.8460 |
|
82 |
+
| 2.554 | 0.0328 | 300 | 7.16 | 25.31 | 1.8861 | 142.4584 |
|
83 |
+
| 2.276 | 0.0438 | 400 | 8.9 | 27.72 | 1.8568 | 119.7208 |
|
84 |
+
| 2.3077 | 0.0547 | 500 | 14.51 | 32.58 | 1.7492 | 88.3836 |
|
85 |
+
| 2.0852 | 0.0657 | 600 | 16.71 | 34.1 | 1.6548 | 83.6560 |
|
86 |
+
| 2.1602 | 0.0766 | 700 | 14.93 | 35.2 | 1.6063 | 106.4385 |
|
87 |
+
| 1.9556 | 0.0876 | 800 | 20.64 | 36.74 | 1.6190 | 77.5777 |
|
88 |
+
| 1.7516 | 0.0985 | 900 | 15.44 | 36.67 | 1.5614 | 95.0023 |
|
89 |
+
| 1.7502 | 0.1095 | 1000 | 20.65 | 38.42 | 1.5317 | 81.4948 |
|
90 |
+
| 1.6851 | 0.1204 | 1100 | 19.13 | 37.91 | 1.5289 | 87.7533 |
|
91 |
+
| 1.5154 | 0.1314 | 1200 | 19.79 | 41.21 | 1.4906 | 83.3408 |
|
92 |
+
| 1.3658 | 0.1423 | 1300 | 19.58 | 39.16 | 1.4623 | 96.3980 |
|
93 |
+
| 1.3828 | 0.1533 | 1400 | 22.84 | 42.83 | 1.4069 | 77.5777 |
|
94 |
+
| 1.5339 | 0.1642 | 1500 | 20.91 | 41.62 | 1.3909 | 86.5376 |
|
95 |
+
| 1.2441 | 0.1752 | 1600 | 23.35 | 43.43 | 1.3726 | 75.5966 |
|
96 |
+
| 1.1607 | 0.1861 | 1700 | 20.4 | 42.41 | 1.3471 | 85.4120 |
|
97 |
+
| 1.1043 | 0.1970 | 1800 | 21.13 | 43.4 | 1.3332 | 81.5849 |
|
98 |
+
| 1.0698 | 0.2080 | 1900 | 23.84 | 44.54 | 1.3413 | 73.3904 |
|
99 |
+
| 1.0698 | 0.2189 | 2000 | 28.34 | 47.2 | 1.2848 | 66.9068 |
|
100 |
+
| 1.053 | 0.2299 | 2100 | 25.19 | 46.75 | 1.2951 | 73.1652 |
|
101 |
+
| 0.9139 | 0.2408 | 2200 | 28.43 | 47.11 | 1.2852 | 70.7789 |
|
102 |
+
| 0.742 | 0.2518 | 2300 | 30.5 | 47.62 | 1.2580 | 63.6200 |
|
103 |
+
| 0.8627 | 0.2627 | 2400 | 29.97 | 48.38 | 1.2308 | 66.2314 |
|
104 |
+
| 0.7213 | 0.2737 | 2500 | 22.96 | 46.55 | 1.2176 | 83.7010 |
|
105 |
+
| 0.672 | 0.2846 | 2600 | 27.35 | 48.02 | 1.2272 | 71.7695 |
|
106 |
+
| 0.784 | 0.2956 | 2700 | 31.16 | 50.83 | 1.2010 | 65.3760 |
|
107 |
+
| 0.6463 | 0.3065 | 2800 | 30.67 | 51.24 | 1.1884 | 64.9257 |
|
108 |
+
| 0.6028 | 0.3175 | 2900 | 32.07 | 51.3 | 1.1866 | 61.4588 |
|
109 |
+
| 0.6494 | 0.3284 | 3000 | 32.04 | 50.96 | 1.1768 | 63.3048 |
|
110 |
+
| 0.657 | 0.3394 | 3100 | 1.2126| 30.55 | 50.18 | 66.0964 |
|
111 |
+
| 0.6239 | 0.3503 | 3200 | 1.1836| 33.69 | 52.06 | 60.2431 |
|
112 |
+
| 0.63 | 0.3612 | 3300 | 1.2201| 32.14 | 51.62 | 61.7290 |
|
113 |
+
| 0.5155 | 0.3722 | 3400 | 1.1956| 32.62 | 51.99 | 61.3688 |
|
114 |
+
| 0.5392 | 0.3831 | 3500 | 1.2010| 31.13 | 51.37 | 63.9802 |
|
115 |
+
| 0.5159 | 0.3941 | 3600 | 1.1831| 32.2 | 51.81 | 62.4043 |
|
116 |
+
| 0.4535 | 0.4050 | 3700 | 1.1744| 31.61 | 51.77 | 63.3949 |
|
117 |
+
| 0.3346 | 0.4160 | 3800 | 1.2066| 30.67 | 50.21 | 65.4660 |
|
118 |
+
| 0.3991 | 0.4269 | 3900 | 1.1870| 30.7 | 50.88 | 65.2409 |
|
119 |
+
| 0.395 | 0.4379 | 4000 | 1.1842| 28.6 | 49.54 | 68.5277 |
|
120 |
+
|
121 |
+
|
122 |
### Framework versions
|
123 |
|
124 |
- Transformers 4.41.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3055544304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d1be9c36eceaf01b06a810c82a638127bff7b2b1178366b95f1eb7b6859edb4
|
3 |
size 3055544304
|