End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.49506903353057197
+      value: 0.2868796736913664
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4859
-- Wer Ortho: 0.5045
-- Wer: 0.4951
+- Loss: 0.6398
+- Wer Ortho: 0.2934
+- Wer: 0.2869
 
 ## Model description
 
@@ -53,25 +53,25 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 16
+- learning_rate: 1e-05
+- train_batch_size: 32
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 2000
+- training_steps: 500
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
-| 0.0084        | 71.43 | 2000 | 1.4859          | 0.5045    | 0.4951 |
+| 0.0005        | 35.71 | 500  | 0.6398          | 0.2934    | 0.2869 |
 
 
 ### Framework versions
 
-- Transformers 4.32.0.dev0
+- Transformers 4.33.0.dev0
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.4
 - Tokenizers 0.13.3

generation_config.json

@@ -249,5 +249,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.32.0.dev0"
+  "transformers_version": "4.33.0.dev0"
 }