End of training

README.md

@@ -19,6 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 # jinkrsmodel
 
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the xppast/voice dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6485
+- Cer: 40.4444
 
 ## Model description
 
@@ -44,9 +47,19 @@ 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: 4000
+- training_steps: 400
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Cer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.0146        | 33.33  | 100  | 1.4532          | 35.5556 |
+| 0.0034        | 66.67  | 200  | 1.5364          | 40.8889 |
+| 0.0013        | 100.0  | 300  | 1.5890          | 41.3333 |
+| 0.0007        | 133.33 | 400  | 1.6485          | 40.4444 |
+
+
 ### Framework versions
 
 - Transformers 4.36.0.dev0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a1e97ec94f1534d7b3db4139dee5c3a863d89ac79d5ae9de092ab69828102e
+oid sha256:532c01e33b4df6169821ce7e717a732da0823fdc9e66ab0287e052c69cc2fd8f
 size 290403936