Training in progress, step 300

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: 3.2063
-- eval_wer: 97.1245
-- eval_runtime: 442.577
-- eval_samples_per_second: 0.904
-- eval_steps_per_second: 0.029
-- epoch: 3.0367
-- step: 200
+- eval_loss: 3.1067
+- eval_wer: 95.7479
+- eval_runtime: 382.1833
+- eval_samples_per_second: 1.047
+- eval_steps_per_second: 0.034
+- epoch: 4.16
+- step: 300
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4305b47cc5b87fab3cfd232fbb57b80bb6ab5b8f3e3b7d716fbe98f278333651
+oid sha256:b9afc7b7996d1814a8d9fbd07291c0a536d3f2db5cef79ff0777ed4d77cffbf1
 size 14176064