update model card README.md

README.md

@@ -7,32 +7,32 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: juancopi81/whisper-medium-es
+- name: juancopi81/whisper-medium-es-train-valid-bs-64
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
       name: common_voice_11_0
-      type: mozilla-foundation/common_voice_11_0
+      type: common_voice_11_0
       config: es
       split: test
       args: es
     metrics:
     - name: Wer
       type: wer
-      value: 5.735798555168651
+      value: 5.696169637752716
 ---
 
 <!-- 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. -->
 
-# juancopi81/whisper-medium-es
+# juancopi81/whisper-medium-es-train-valid-bs-64
 
-This model is a fine-tuned version of [juancopi81/whisper-medium-es](https://huggingface.co/juancopi81/whisper-medium-es) on the common_voice_11_0 dataset.
+This model is a fine-tuned version of [juancopi81/whisper-medium-es-train-valid-bs-64](https://huggingface.co/juancopi81/whisper-medium-es-train-valid-bs-64) on the common_voice_11_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1683
-- Wer: 5.7358
+- Loss: 0.1700
+- Wer: 5.6962
 
 ## Model description
 
@@ -51,7 +51,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-06
+- learning_rate: 5e-07
 - train_batch_size: 64
 - eval_batch_size: 32
 - seed: 42
@@ -65,7 +65,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.1972        | 1.03  | 500  | 0.1683          | 5.7358 |
+| 0.1665        | 1.03  | 500  | 0.1700          | 5.6962 |
 
 
 ### Framework versions