Training in progress, step 20

README.md

@@ -18,13 +18,13 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 4.2464
-- eval_wer: 157.5
-- eval_runtime: 6.907
-- eval_samples_per_second: 0.869
-- eval_steps_per_second: 0.145
-- epoch: 2.5
-- step: 10
+- eval_loss: 3.4094
+- eval_wer: 145.0
+- eval_runtime: 6.0126
+- eval_samples_per_second: 0.998
+- eval_steps_per_second: 0.166
+- epoch: 5.0
+- step: 20
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b9f224eef207761d1a45c1e0a6e257d63b7bef649cd95a2cb6e38048f36b7e
+oid sha256:25c70c2873bc625f80ed9ee5d5d90dacb2be6ec31a83e868af0a749524681679
 size 14176064