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-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0076
-- Wer: 0.0833
-- Cer: 0.0326
+- Loss: 0.0089
+- Wer: 0.0818
+- Cer: 0.0316
 
 ## Model description
 
@@ -57,10 +57,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| 0.0027        | 1.0   | 157  | 0.0078          | 0.0829 | 0.0306 |
-| 0.0025        | 2.0   | 314  | 0.0088          | 0.0910 | 0.0307 |
-| 0.0013        | 3.0   | 471  | 0.0103          | 0.0963 | 0.0351 |
-| 0.0013        | 4.0   | 628  | 0.0116          | 0.0968 | 0.0338 |
+| 0.0013        | 1.0   | 157  | 0.0090          | 0.0833 | 0.0301 |
+| 0.0019        | 2.0   | 314  | 0.0096          | 0.0894 | 0.0309 |
+| 0.001         | 3.0   | 471  | 0.0107          | 0.0968 | 0.0353 |
+| 0.0015        | 4.0   | 628  | 0.0114          | 0.1035 | 0.0382 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f8e2f417d39111098febac1bca3f1efb9ed458f2f66ad3d1a33b54992702b49
+oid sha256:e9ef79c0c021550bba8304f58db1bba42c66845432ae1998909b887b15422025
 size 151061672

runs/Jan16_16-21-57_db73d2dae469/events.out.tfevents.1737047887.db73d2dae469.18.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce344222a4c082060c28e8d25c64a11f0647278f71c7c06a718170fa960be90
+size 453