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: 2.4508
-- eval_wer: 89.4769
-- eval_runtime: 372.7904
-- eval_samples_per_second: 1.073
-- eval_steps_per_second: 0.035
-- epoch: 3.022
-- step: 200
+- eval_loss: 2.3149
+- eval_wer: 88.4980
+- eval_runtime: 268.4788
+- eval_samples_per_second: 1.49
+- eval_steps_per_second: 0.048
+- epoch: 4.096
+- step: 300
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7160c1a2daaf48dc797f7da6a11bdd73dd28980315021b694ab695d1ac5a533e
+oid sha256:9680ec36e219ca88d1bdba677965ca0c561d41bf47cb58b0c3426ebab351dd43
 size 14176064