End of training

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 63.6986301369863
+      value: 85.61643835616438
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +34,8 @@ 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-whisper-dataset dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7501
-- Wer: 63.6986
+- Loss: 3.8268
+- Wer: 85.6164
 
 ## Model description
 
@@ -66,12 +66,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0           | 200.0 | 1000 | 1.4774          | 72.6027 |
-| 0.0           | 400.0 | 2000 | 1.6503          | 61.6438 |
-| 0.0           | 600.0 | 3000 | 1.7314          | 63.0137 |
-| 0.0           | 800.0 | 4000 | 1.7501          | 63.6986 |
+| Training Loss | Epoch   | Step | Validation Loss | Wer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|
+| 0.0067        | 17.2414 | 1000 | 2.9626          | 87.5    |
+| 0.0022        | 34.4828 | 2000 | 3.5443          | 87.5856 |
+| 0.0           | 51.7241 | 3000 | 3.7999          | 85.6164 |
+| 0.0           | 68.9655 | 4000 | 3.8268          | 85.6164 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49ab5a9f1a93670f4f539d6336165a5c4efc0b8dcd0807ac68300c63bd49fbe0
+oid sha256:6e9e81001c6598d8b24a25cd9d52c2d8240d8651e270491eb87acb3738c8cf34
 size 151061672