Training in progress, step 50

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-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_16_1 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.9223
-- eval_wer: 218.1818
-- eval_runtime: 9.3314
-- eval_samples_per_second: 0.429
-- eval_steps_per_second: 0.107
-- epoch: 24.02
-- step: 25
+- eval_loss: 2.1805
+- eval_wer: 163.6364
+- eval_runtime: 8.1444
+- eval_samples_per_second: 0.491
+- eval_steps_per_second: 0.123
+- epoch: 49.02
+- step: 50
 
 ## Model description
 

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6df6d40dfb035fcec155c3cfa4fabc79c7f5264f6601ffac386e91b24fc0d5
+oid sha256:d5b3adfd47dbd764029d7333027ab658643a9aa6609e86743308674c03424805
 size 2377150