Segementation

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: 0.0084
-- Wer: 0.0585
-- Cer: 0.0258
+- Loss: 0.0112
+- Wer: 0.0623
+- Cer: 0.0276
 
 ## Model description
 
@@ -57,11 +57,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer    | Cer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
-| 0.0034        | 1.0    | 1340 | 0.0047          | 0.0661 | 0.0298 |
-| 0.0023        | 2.0    | 2680 | 0.0049          | 0.0664 | 0.0320 |
-| 0.0009        | 3.0    | 4020 | 0.0055          | 0.0585 | 0.0263 |
-| 0.001         | 4.0    | 5360 | 0.0067          | 0.0630 | 0.0280 |
-| 0.0002        | 4.9966 | 6695 | 0.0086          | 0.0579 | 0.0270 |
+| 0.0009        | 1.0    | 1340 | 0.0072          | 0.0666 | 0.0296 |
+| 0.0007        | 2.0    | 2680 | 0.0068          | 0.0655 | 0.0289 |
+| 0.0005        | 3.0    | 4020 | 0.0079          | 0.0608 | 0.0280 |
+| 0.0003        | 4.0    | 5360 | 0.0097          | 0.0632 | 0.0290 |
+| 0.0001        | 4.9966 | 6695 | 0.0113          | 0.0559 | 0.0259 |
 
 
 ### Framework versions

runs/Apr27_19-53-35_73df15bcccb8/events.out.tfevents.1745818468.73df15bcccb8.19.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48cba9d8c3e394043e603ccb23f177ce48d1ded52a9f8dba87bfd29511ffdd6
+size 453