End of training

README.md

@@ -20,12 +20,12 @@ model-index:
       name: Common Voice 17.0
       type: mozilla-foundation/common_voice_17_0
       config: id
-      split: None
+      split: train+validation+test+validated
       args: 'config: id, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 5.884171475680132
+      value: 6.596506595218467
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 17.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0848
-- Wer: 5.8842
+- Loss: 0.0931
+- Wer: 6.5965
 
 ## Model description
 
@@ -56,11 +56,9 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 10
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 20
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
@@ -71,10 +69,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.1943        | 0.7505 | 1000 | 0.1830          | 13.1350 |
-| 0.0631        | 1.5009 | 2000 | 0.1227          | 8.9770  |
-| 0.0209        | 2.2514 | 3000 | 0.0948          | 7.2225  |
-| 0.0116        | 3.0019 | 4000 | 0.0848          | 5.8842  |
+| 0.2099        | 0.6002 | 1000 | 0.1998          | 14.0573 |
+| 0.0732        | 1.2005 | 2000 | 0.1336          | 9.9572  |
+| 0.0507        | 1.8007 | 3000 | 0.1034          | 7.5678  |
+| 0.0197        | 2.4010 | 4000 | 0.0931          | 6.5965  |
 
 
 ### Framework versions