Training in progress, step 100

README.md

@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the common_voice_16_1 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.7791
-- eval_wer: 61.7556
-- eval_runtime: 113.2924
-- eval_samples_per_second: 2.207
-- eval_steps_per_second: 0.282
-- epoch: 0.75
-- step: 75
+- eval_loss: 1.7258
+- eval_wer: 63.3877
+- eval_runtime: 108.0041
+- eval_samples_per_second: 2.315
+- eval_steps_per_second: 0.296
+- epoch: 1.0
+- step: 100
 
 ## Model description
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f8cd26bb1819f68788f5cb5d147c47661ec0e4c160173bf4454c7fb62e5108
+oid sha256:cba270d1bded117b61d97b709330dc075d5c8cfd20c4936fed2fca1b37d344e9
 size 3055755414