Training in progress, step 3000

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: 1.9378
-- eval_wer: 99.2149
-- eval_runtime: 880.9183
-- eval_samples_per_second: 0.284
-- eval_steps_per_second: 0.036
-- epoch: 1.1875
-- step: 2000
+- eval_loss: 2.1302
+- eval_wer: 75.3680
+- eval_runtime: 451.587
+- eval_samples_per_second: 0.554
+- eval_steps_per_second: 0.071
+- epoch: 2.125
+- step: 3000
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4633833b3224a96548b39d638422c2443c9406e26930edd9b66454c191f45c
+oid sha256:ac866cd1252d3b951d7f98b083ff456843e40e90fdb2dafeb900518772bd1a57
 size 14176064