End of training
Browse files
README.md
CHANGED
|
@@ -3,7 +3,7 @@ library_name: transformers
|
|
| 3 |
language:
|
| 4 |
- fa
|
| 5 |
license: apache-2.0
|
| 6 |
-
base_model:
|
| 7 |
tags:
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
|
@@ -23,7 +23,7 @@ model-index:
|
|
| 23 |
metrics:
|
| 24 |
- name: Wer
|
| 25 |
type: wer
|
| 26 |
-
value:
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -31,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 31 |
|
| 32 |
# whisper-base-fa - Sadegh Karimi
|
| 33 |
|
| 34 |
-
This model is a fine-tuned version of [
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss: 0.
|
| 37 |
-
- Wer:
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
@@ -67,46 +67,46 @@ The following hyperparameters were used during training:
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 69 |
|:-------------:|:------:|:-----:|:---------------:|:-------:|
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
|
| 111 |
|
| 112 |
### Framework versions
|
|
|
|
| 3 |
language:
|
| 4 |
- fa
|
| 5 |
license: apache-2.0
|
| 6 |
+
base_model: SadeghK/whisper-base
|
| 7 |
tags:
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
|
|
|
| 23 |
metrics:
|
| 24 |
- name: Wer
|
| 25 |
type: wer
|
| 26 |
+
value: 10.468362043705566
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 31 |
|
| 32 |
# whisper-base-fa - Sadegh Karimi
|
| 33 |
|
| 34 |
+
This model is a fine-tuned version of [SadeghK/whisper-base](https://huggingface.co/SadeghK/whisper-base) on the Common Voice 20.0 dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.0809
|
| 37 |
+
- Wer: 10.4684
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 69 |
|:-------------:|:------:|:-----:|:---------------:|:-------:|
|
| 70 |
+
| 0.1234 | 0.0493 | 1000 | 0.1698 | 21.8312 |
|
| 71 |
+
| 0.1303 | 0.0986 | 2000 | 0.1663 | 22.9153 |
|
| 72 |
+
| 0.1241 | 0.1479 | 3000 | 0.1623 | 20.8843 |
|
| 73 |
+
| 0.1223 | 0.1972 | 4000 | 0.1616 | 20.7470 |
|
| 74 |
+
| 0.1281 | 0.2465 | 5000 | 0.1522 | 19.3606 |
|
| 75 |
+
| 0.1111 | 0.2958 | 6000 | 0.1483 | 20.0901 |
|
| 76 |
+
| 0.1097 | 0.3451 | 7000 | 0.1452 | 19.0445 |
|
| 77 |
+
| 0.1439 | 0.3944 | 8000 | 0.1367 | 18.0251 |
|
| 78 |
+
| 0.1053 | 0.4437 | 9000 | 0.1347 | 17.5902 |
|
| 79 |
+
| 0.1248 | 0.4930 | 10000 | 0.1281 | 16.9486 |
|
| 80 |
+
| 0.1081 | 0.5423 | 11000 | 0.1252 | 15.9200 |
|
| 81 |
+
| 0.1062 | 0.5916 | 12000 | 0.1222 | 15.8167 |
|
| 82 |
+
| 0.1139 | 0.6409 | 13000 | 0.1181 | 15.6038 |
|
| 83 |
+
| 0.1011 | 0.6902 | 14000 | 0.1145 | 15.0918 |
|
| 84 |
+
| 0.098 | 0.7395 | 15000 | 0.1141 | 15.0194 |
|
| 85 |
+
| 0.1176 | 0.7888 | 16000 | 0.1091 | 14.1048 |
|
| 86 |
+
| 0.0933 | 0.8381 | 17000 | 0.1067 | 13.9028 |
|
| 87 |
+
| 0.0981 | 0.8874 | 18000 | 0.1042 | 13.6391 |
|
| 88 |
+
| 0.0909 | 0.9367 | 19000 | 0.1012 | 13.2119 |
|
| 89 |
+
| 0.0714 | 0.9860 | 20000 | 0.1001 | 13.1826 |
|
| 90 |
+
| 0.0491 | 1.0353 | 21000 | 0.0985 | 12.9251 |
|
| 91 |
+
| 0.059 | 1.0846 | 22000 | 0.0966 | 12.6799 |
|
| 92 |
+
| 0.0492 | 1.1339 | 23000 | 0.0959 | 12.4501 |
|
| 93 |
+
| 0.0625 | 1.1832 | 24000 | 0.0943 | 12.5241 |
|
| 94 |
+
| 0.0429 | 1.2325 | 25000 | 0.0946 | 12.4424 |
|
| 95 |
+
| 0.0403 | 1.2818 | 26000 | 0.0931 | 12.1370 |
|
| 96 |
+
| 0.0474 | 1.3311 | 27000 | 0.0921 | 11.7330 |
|
| 97 |
+
| 0.0484 | 1.3804 | 28000 | 0.0910 | 11.5710 |
|
| 98 |
+
| 0.0585 | 1.4297 | 29000 | 0.0896 | 11.7067 |
|
| 99 |
+
| 0.0431 | 1.4790 | 30000 | 0.0890 | 11.3875 |
|
| 100 |
+
| 0.045 | 1.5283 | 31000 | 0.0875 | 11.2842 |
|
| 101 |
+
| 0.0494 | 1.5776 | 32000 | 0.0862 | 11.5433 |
|
| 102 |
+
| 0.0448 | 1.6269 | 33000 | 0.0854 | 11.0282 |
|
| 103 |
+
| 0.0508 | 1.6762 | 34000 | 0.0849 | 11.0498 |
|
| 104 |
+
| 0.0432 | 1.7255 | 35000 | 0.0837 | 10.7583 |
|
| 105 |
+
| 0.0356 | 1.7748 | 36000 | 0.0826 | 10.8339 |
|
| 106 |
+
| 0.0353 | 1.8241 | 37000 | 0.0819 | 10.5300 |
|
| 107 |
+
| 0.043 | 1.8734 | 38000 | 0.0815 | 10.4838 |
|
| 108 |
+
| 0.0434 | 1.9227 | 39000 | 0.0812 | 10.5038 |
|
| 109 |
+
| 0.0382 | 1.9720 | 40000 | 0.0809 | 10.4684 |
|
| 110 |
|
| 111 |
|
| 112 |
### Framework versions
|