End of training

README.md

@@ -1,24 +1,24 @@
 ---
 license: apache-2.0
-base_model: openai/whisper-base
+base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 metrics:
 - wer
 model-index:
-- name: small-Cotrsc
+- name: Whisper-opus
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# small-Cotrsc
+# Whisper-opus
 
-This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0638
-- Wer: 49.1506
+- Loss: 0.0459
+- Wer: 36.6187
 
 ## Model description
 
@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 2.67e-05
 - train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.3978        | 0.4912 | 500  | 0.1159          | 69.1662 |
-| 0.0677        | 0.9823 | 1000 | 0.0638          | 49.1506 |
+| 0.1359        | 0.4902 | 500  | 0.0713          | 49.1419 |
+| 0.0452        | 0.9804 | 1000 | 0.0459          | 36.6187 |
 
 
 ### Framework versions