Upload 2 files

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: openai/whisper-small
+base_model: openai/whisper-small.en
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-small-sv
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
+This model is a fine-tuned version of [openai/whisper-small.en](https://huggingface.co/openai/whisper-small.en) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2908
-- Wer: 55.7146
+- Loss: 0.6010
+- Wer: 49.3074
 
 ## Model description
 
@@ -44,20 +44,22 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 2000
+- training_steps: 4000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer      |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.1253        | 1.28  | 1000 | 0.2983          | 129.5722 |
-| 0.0616        | 2.55  | 2000 | 0.2908          | 55.7146  |
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.5121        | 1.27  | 1000 | 0.6973          | 58.2803 |
+| 0.2409        | 2.54  | 2000 | 0.5989          | 49.5818 |
+| 0.1565        | 3.81  | 3000 | 0.5806          | 48.0991 |
+| 0.0729        | 5.08  | 4000 | 0.6010          | 49.3074 |
 
 
 ### Framework versions
 
-- Transformers 4.36.0.dev0
-- Pytorch 2.1.0+cu118
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.0+cu121
 - Datasets 2.15.0
 - Tokenizers 0.15.0