Training in progress, step 100

README.md

@@ -20,13 +20,13 @@ 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 common_voice_16_1 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 3.5996
-- eval_wer: 121.1946
-- eval_runtime: 673.4766
-- eval_samples_per_second: 0.742
-- eval_steps_per_second: 0.048
-- epoch: 0.1667
-- step: 50
+- eval_loss: 2.6271
+- eval_wer: 89.9487
+- eval_runtime: 511.0164
+- eval_samples_per_second: 0.978
+- eval_steps_per_second: 0.063
+- epoch: 0.3333
+- step: 100
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:557f818b10add5d01b12f83e5530d262c118c29c178371cd0dac5d7dca8eb7fe
+oid sha256:a888339af2039d32a58117ec202f1cc1af94855cb9e43645984dcf320768c2b7
 size 14176064