End of training

README.md

@@ -11,19 +11,19 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: Whisper-large-v3-spanish-transcription
+- name: Whisper-large-v3-spanish-transcription-v2
   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. -->
 
-# Whisper-large-v3-spanish-transcription
+# Whisper-large-v3-spanish-transcription-v2
 
 This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the covost2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1304
-- Wer: 9.3081
+- Loss: 0.1302
+- Wer: 9.3640
 
 ## Model description
 
@@ -44,7 +44,7 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 16
-- eval_batch_size: 16
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -56,7 +56,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.1146        | 1.0   | 4939 | 0.1304          | 9.3081 |
+| 0.113         | 1.0   | 4939 | 0.1302          | 9.3640 |
 
 
 ### Framework versions