Training finished

README.md

@@ -20,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the quran-ayat-speech-to-text dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0145
-- Wer: 11.7672
-- Cer: 3.4896
+- Loss: 0.0139
+- Wer: 9.5114
+- Cer: 2.8698
 
 ## Model description
 
@@ -88,9 +88,9 @@ The following hyperparameters were used during training:
 | 0.0004        | 8.3966 | 23200 | 3.4639 | 0.0142          | 11.6590 |
 | 0.0003        | 8.6861 | 24000 | 3.4927 | 0.0143          | 11.7015 |
 | 0.0004        | 8.9756 | 24800 | 3.4977 | 0.0143          | 11.6861 |
-| 0.0003        | 9.2652 | 25600 | 0.0146 | 11.7440         | 3.4400  |
-| 0.0003        | 9.5547 | 26400 | 0.0145 | 11.7904         | 3.4954  |
-| 0.0003        | 9.8442 | 27200 | 0.0145 | 11.7672         | 3.4896  |
+| 0.0003        | 9.2652 | 25600 | 3.4400 | 0.0146          | 11.7440 |
+| 0.0003        | 9.5547 | 26400 | 3.4954 | 0.0145          | 11.7904 |
+| 0.0003        | 9.8442 | 27200 | 3.4896 | 0.0145          | 11.7672 |
 
 
 ### Framework versions

runs/Mar01_15-25-17_3d7f5f3cde60/events.out.tfevents.1740842723.3d7f5f3cde60.18.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad7c8034af7de8dcc18a9d2f86112e6ad204fb365ef7a4cc454e6ec5141b394
+size 6354

runs/Mar01_15-25-17_3d7f5f3cde60/events.out.tfevents.1740846837.3d7f5f3cde60.18.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22562538c9cdeb02b5110dd4a0f2edc54dd6e6a5c0b28d6154c0889d1d8e7cb1
+size 460

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1e03e34d5d506e9e296be634c9ee16a83e6b89a1770a68f3e2d900b0454317
+oid sha256:b73cbafdba4732919b3a7cab62ce96d98d0d0362ed9288558f4c8a75e41f7bff
 size 5560