Training in progress, step 100

README.md

@@ -25,17 +25,17 @@ 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 hf-internal-testing/librispeech_asr_dummy dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.1279
-- eval_wer: 7.0866
-- eval_cer: 81.1080
-- eval_decode_time: 0.5388
-- eval_wer_time: 0.0079
-- eval_cer_time: 0.0038
-- eval_runtime: 1.2857
-- eval_samples_per_second: 7.778
-- eval_steps_per_second: 1.556
-- epoch: 4.14
-- step: 90
+- eval_loss: 0.1185
+- eval_wer: 5.9055
+- eval_cer: 83.2386
+- eval_decode_time: 0.5299
+- eval_wer_time: 0.0047
+- eval_cer_time: 0.0030
+- eval_runtime: 1.3526
+- eval_samples_per_second: 7.393
+- eval_steps_per_second: 1.479
+- epoch: 5.05
+- step: 100
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b727176a91679f211e2860c969bb68ca60a4372d0d383f1c88ec7f7bcfb4a2
+oid sha256:657bf78fae67ab7f060e521c89071af033d2ccaafb65ee8063a6a309b5d28838
 size 8668296

runs/Oct31_02-35-20_JacobdeMacBook-Pro.local/events.out.tfevents.1730313339.JacobdeMacBook-Pro.local.87069.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bea5a5e323712bdc7d44db21537447e77d5823d278a467d636cb636647f91dd1
-size 66708
+oid sha256:5db7cf00abc1a25d49ae2a758d5cb88eb3e758dede39e62f906544e1e55fa0d7
+size 73520