Training in progress, step 80

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: 0.2026
-- eval_wer: 9.0551
-- eval_cer: 83.5227
-- eval_decode_time: 0.5359
-- eval_wer_time: 0.0063
-- eval_cer_time: 0.0033
-- eval_runtime: 1.3431
-- eval_samples_per_second: 7.445
-- eval_steps_per_second: 1.489
-- epoch: 3.13
-- step: 70
+- eval_loss: 0.1665
+- eval_wer: 5.9055
+- eval_cer: 83.9489
+- eval_decode_time: 0.5316
+- eval_wer_time: 0.0056
+- eval_cer_time: 0.0029
+- eval_runtime: 1.2621
+- eval_samples_per_second: 7.924
+- eval_steps_per_second: 1.585
+- epoch: 4.04
+- step: 80
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66f6660bd73672b3675091a0d67850217bcf7e44f530e1d6bb4f07c7bc2ae294
+oid sha256:39d066622ea502e61392d0c8bb0a5a04d2c7b8c9b184b30cbf84dc5c5922afec
 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 sha256:33853af08508df974ca3189898aa0a95ff47d6caf1a2a08e06745a1d4b8f2d1e
-size 53114
+oid sha256:a8fb4b3c5be531e96f2dab81a43d45f956b36191a6548007d176f3a06e5e39d6
+size 59921