End of training

README.md

@@ -20,8 +20,8 @@ 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 custom dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9237
-- Wer: 41.5842
+- Loss: 0.6622
+- Wer: 31.2916
 
 ## Model description
 
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch    | Step | Validation Loss | Wer     |
 |:-------------:|:--------:|:----:|:---------------:|:-------:|
-| 0.0           | 333.3333 | 1000 | 0.9237          | 41.5842 |
+| 0.0           | 333.3333 | 1000 | 0.6622          | 31.2916 |
 
 
 ### Framework versions
@@ -62,4 +62,4 @@ The following hyperparameters were used during training:
 - Transformers 4.45.2
 - Pytorch 2.4.1+cu121
 - Datasets 3.0.1
-- Tokenizers 0.20.0
+- Tokenizers 0.20.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15e78bd3b6c845ad1820183ea6ca6bcbe647588109074bac3d430f9f63a31cd2
+oid sha256:039ec2a02ee3d869ac15496afe58a0ce21152617867ab9a09bfea54cdaa50c8d
 size 966995080

runs/Oct16_09-22-12_a1d3e2c34e79/events.out.tfevents.1729070534.a1d3e2c34e79.3804.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0669049a9a293907ae3fbb438787e74fa16daef4ad846af5de8f5ba1a3043d12
+size 15806

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:068c03c609644d3c5f7446cd66be54f37e8fb47f4cfa755ac9386f99b4362c5a
+oid sha256:41d0e2552dee65a56af371ababb2d49ba60de9f788025f47d29d0ab8a9c54e16
 size 5368