End of training

README.md

@@ -20,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1406
-- Wer: 16.8660
-- Cer: 5.9563
+- Loss: 0.1203
+- Wer: 10.8852
+- Cer: 3.4179
 
 ## Model description
 
@@ -47,16 +47,18 @@ 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: 1
-- training_steps: 2
+- lr_scheduler_warmup_steps: 500
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
-| 0.1093        | 0.02  | 1    | 0.1154          | 16.0287 | 4.9761 |
-| 0.0147        | 0.04  | 2    | 0.1406          | 16.8660 | 5.9563 |
+| 0.0291        | 8.77  | 500  | 0.1099          | 14.2344 | 4.1970 |
+| 0.004         | 17.54 | 1000 | 0.1114          | 10.8852 | 3.4682 |
+| 0.0001        | 26.32 | 1500 | 0.1185          | 10.7656 | 3.3677 |
+| 0.0           | 35.09 | 2000 | 0.1203          | 10.8852 | 3.4179 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1de9e47d57197b1feb4a0f03e6c8731d663c4cf07c12687e2adadccf22b4a3b
+oid sha256:53dfd4cf4fcd0472a340ac0fa1681b49177c44864f8d4b331277c30c15b52cbd
 size 966995080