Training in progress, step 40

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: 2.9686
-- eval_wer: 145.0
-- eval_runtime: 6.2596
-- eval_samples_per_second: 0.959
-- eval_steps_per_second: 0.16
-- epoch: 7.5
-- step: 30
+- eval_loss: 2.7336
+- eval_wer: 160.0
+- eval_runtime: 7.5505
+- eval_samples_per_second: 0.795
+- eval_steps_per_second: 0.132
+- epoch: 10.0
+- step: 40
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ede79ae448ac59862a34ebdfed4b1ae63269275d25b7840ea7ba0a04015df0c7
+oid sha256:591a769da33b52773b97c359924d82a0f7e83ba7033f04d3d19b0819c7cdda06
 size 14176064