update model card README.md

README.md

@@ -1,14 +1,13 @@
 ---
 license: apache-2.0
 tags:
-- whisper-event
 - generated_from_trainer
 datasets:
 - audiofolder
 metrics:
 - wer
 model-index:
-- name: Whisper Small Seneca
+- name: whisper-small-Seneca
   results:
   - task:
       name: Automatic Speech Recognition
@@ -22,18 +21,18 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 26.8453454387165
+      value: 27.49828990734407
 ---
 
 <!-- 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 Small Seneca
+# whisper-small-Seneca
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the audiofolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3327
-- Wer: 26.8453
+- Loss: 0.5983
+- Wer: 27.4983
 
 ## Model description
 
@@ -53,26 +52,27 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 2
+- train_batch_size: 16
 - eval_batch_size: 2
 - seed: 42
 - distributed_type: multi-GPU
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 6000
+- training_steps: 7768
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.4698        | 0.17  | 1000 | 0.5169          | 42.6155 |
-| 0.4237        | 0.33  | 2000 | 0.3953          | 35.0351 |
-| 0.2547        | 1.09  | 3000 | 0.3688          | 33.6857 |
-| 0.1923        | 1.25  | 4000 | 0.3500          | 30.6324 |
-| 0.1281        | 2.01  | 5000 | 0.3327          | 26.8453 |
-| 0.0701        | 2.17  | 6000 | 0.3436          | 27.2744 |
+| 0.1151        | 3.01  | 1000 | 0.4013          | 31.8326 |
+| 0.0185        | 6.02  | 2000 | 0.4796          | 30.1660 |
+| 0.0062        | 9.03  | 3000 | 0.5143          | 30.0417 |
+| 0.0022        | 12.04 | 4000 | 0.5469          | 28.6301 |
+| 0.0004        | 16.01 | 5000 | 0.5695          | 27.9522 |
+| 0.0001        | 19.01 | 6000 | 0.5891          | 27.5294 |
+| 0.0002        | 22.02 | 7000 | 0.5983          | 27.4983 |
 
 
 ### Framework versions