End of training

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-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2197
-- Wer: 33.3333
+- Loss: 0.0015
+- Wer: 0.0
 
 ## Model description
 
@@ -43,17 +43,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 13
-- training_steps: 100
+- lr_scheduler_warmup_steps: 50
+- training_steps: 500
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 1.3918        | 25.0  | 25   | 0.4022          | 33.3333 |
-| 0.3142        | 50.0  | 50   | 0.2668          | 33.3333 |
-| 0.2472        | 75.0  | 75   | 0.2310          | 33.3333 |
-| 0.2238        | 100.0 | 100  | 0.2197          | 33.3333 |
+| Training Loss | Epoch | Step | Validation Loss | Wer   |
+|:-------------:|:-----:|:----:|:---------------:|:-----:|
+| 0.1446        | 100.0 | 100  | 0.1172          | 100.0 |
+| 0.0161        | 200.0 | 200  | 0.0113          | 0.0   |
+| 0.003         | 300.0 | 300  | 0.0027          | 0.0   |
+| 0.0018        | 400.0 | 400  | 0.0017          | 0.0   |
+| 0.0015        | 500.0 | 500  | 0.0015          | 0.0   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beed5d4599657818aa8e489b2c857c2bb57483269df9a296b0850abb782b4079
+oid sha256:3eb704363b38f161cc8a21d52d8190f6a78f87a5c44881064dd8ca45e4852922
 size 151060136