Model save

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5617
-- Wer: 21.2449
+- Loss: 0.5030
+- Wer: 19.3174
 
 ## Model description
 
@@ -38,22 +38,24 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 12
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 400
-- training_steps: 4000
+- lr_scheduler_warmup_steps: 100
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.2097        | 1.44  | 500  | 0.4706          | 21.2402 |
-| 0.0735        | 2.87  | 1000 | 0.5331          | 22.1757 |
-| 0.0178        | 4.31  | 1500 | 0.5617          | 21.2449 |
+| 0.3674        | 0.57  | 400  | 0.4892          | 21.0004 |
+| 0.1001        | 1.15  | 800  | 0.5216          | 21.6539 |
+| 0.0936        | 1.72  | 1200 | 0.5094          | 20.5303 |
+| 0.0347        | 2.3   | 1600 | 0.5013          | 19.2798 |
+| 0.0066        | 2.87  | 2000 | 0.5030          | 19.3174 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0d93e43cf8f3d8bb31de71741f175cb5c175e361f37790d222934d49fe17083
+oid sha256:7d89ff286450f8ac86bb09a903f335c98e31604b85f2955b38ba8786e020eb89
 size 290459230