NMutangana/swahiliModel

README.md

@@ -5,9 +5,24 @@ tags:
 - generated_from_trainer
 datasets:
 - common_voice_11_0
+metrics:
+- wer
 model-index:
 - name: whisper-small-swahili
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_11_0
+      type: common_voice_11_0
+      config: sw
+      split: None
+      args: sw
+    metrics:
+    - name: Wer
+      type: wer
+      value: 34.94378922684323
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,6 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
 # whisper-small-swahili
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_11_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6821
+- Wer: 34.9438
 
 ## Model description
 
@@ -44,6 +62,16 @@ The following hyperparameters were used during training:
 - training_steps: 4000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.3797        | 1.5625 | 1000 | 0.6029          | 40.2361 |
+| 0.1129        | 3.125  | 2000 | 0.5886          | 35.5841 |
+| 0.0507        | 4.6875 | 3000 | 0.6397          | 35.4404 |
+| 0.0161        | 6.25   | 4000 | 0.6821          | 34.9438 |
+
+
 ### Framework versions
 
 - Transformers 4.40.0