End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 36.34686346863469
+      value: 36.24557260920897
 ---
 
 <!-- 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: 0.6276
-- Wer Ortho: 37.1943
-- Wer: 36.3469
+- Loss: 0.7136
+- Wer Ortho: 36.3973
+- Wer: 36.2456
 
 ## Model description
 
@@ -58,15 +58,16 @@ The following hyperparameters were used during training:
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
+- lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- training_steps: 1000
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 0.0026        | 17.24 | 500  | 0.6276          | 37.1943   | 36.3469 |
+| 0.0007        | 17.86 | 500  | 0.6500          | 34.4849   | 34.0614 |
+| 0.0002        | 35.71 | 1000 | 0.7136          | 36.3973   | 36.2456 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf63f4e919e86034c9cc716a1582ce1776517d16e0a8a7ff8f8c0f75de1db82
+oid sha256:968231f7741afdd6127a8f839392153566587a4557520b0fe35776b451d4a43c
 size 151097459