Training in progress, step 250

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: 3.1292
-- eval_wer: 115.0000
-- eval_runtime: 32.3636
-- eval_samples_per_second: 0.185
-- eval_steps_per_second: 0.031
-- epoch: 99.0067
-- step: 200
+- eval_loss: 3.3052
+- eval_wer: 112.5
+- eval_runtime: 34.8832
+- eval_samples_per_second: 0.172
+- eval_steps_per_second: 0.029
+- epoch: 124.0067
+- step: 250
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd90f85b6b432e70f5fb0130996290b0d56dd1d6fae6319ffb111cf98c1b08b7
+oid sha256:9c7c88a14f4c17d11033bfd4afbffa1861002455f5ce094335a2424bdc5a8c42
 size 14176064