End of training

README.md

@@ -8,9 +8,21 @@ tags:
 - generated_from_trainer
 datasets:
 - bookbot/OpenBible_Swahili
+metrics:
+- wer
 model-index:
 - name: Whisper_Small_swahili_bible
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: OpenBible_Swahili_book_split
+      type: bookbot/OpenBible_Swahili
+    metrics:
+    - name: Wer
+      type: wer
+      value: 9.76996476224413
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -19,6 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 # Whisper_Small_swahili_bible
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the OpenBible_Swahili_book_split dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2541
+- Wer Ortho: 19.1300
+- Wer: 9.7700
 
 ## Model description
 
@@ -44,12 +60,19 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
+| 0.1659        | 1.0   | 1423 | 0.2541          | 19.1300   | 9.7700 |
+
+
 ### Framework versions
 
-- Transformers 4.48.3
+- Transformers 4.50.0
 - Pytorch 2.6.0+cu124
-- Datasets 3.4.0
-- Tokenizers 0.21.0
+- Datasets 3.5.0
+- Tokenizers 0.21.1

generation_config.json

@@ -258,5 +258,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.48.3"
+  "transformers_version": "4.50.0"
 }