Training in progress, step 100

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 common_voice_16_1 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 3.5013
-- eval_wer: 113.6364
-- eval_runtime: 22.7005
-- eval_samples_per_second: 0.176
-- eval_steps_per_second: 0.044
-- epoch: 74.01
-- step: 75
+- eval_loss: 3.2831
+- eval_wer: 109.0909
+- eval_runtime: 18.9581
+- eval_samples_per_second: 0.211
+- eval_steps_per_second: 0.053
+- epoch: 99.01
+- step: 100
 
 ## Model description
 

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38aca94322d79d35a09a0734ce23d976236ae2c2bce113057cdd92809d121c37
+oid sha256:c0617bede8580fff9bbdc4d6b909424140ad29929b7da4f7a294319932b4e8a0
 size 14208970