Saving weights and logs of step 9999 - epoch 34

README.md

@@ -19,6 +19,14 @@ probably proofread and complete it, then remove this comment. -->
 # salmon-whisper-medium-smj
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the NbAiLab/salmon-asr-smj dataset.
+It achieves the following results on the evaluation set:
+- step: 9999
+- validation_loss: 1.4491
+- train_loss: 0.2105
+- validation_wer: 15.6915
+- validation_cer: 4.6710
+- validation_exact_wer: 18.0851
+- validation_exact_cer: 4.9990
 
 ## Model description
 
@@ -72,6 +80,7 @@ The following hyperparameters were used during training:
 | 7000 | 1.2483          | 0.2359     | 15.2926        | 4.8335         | 18.6170              | 5.2579               |
 | 8000 | 1.4402          | 0.2701     | 15.4255        | 4.5695         | 18.2181              | 4.9592               |
 | 9000 | 1.5363          | 0.2244     | 15.5585        | 4.6304         | 18.3511              | 5.0189               |
+| 9999 | 1.4491          | 0.2105     | 15.6915        | 4.6710         | 18.0851              | 4.9990               |
 
 
 ### Framework versions

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2090f6ef519fd112f632f42131f9137c298b1ec8c610e9416554e60b4d89c8e
+oid sha256:cea46eaf9284b7198eef5282e059c5864b22b9742a8b0d9df5f58709a59d60a0
 size 3055465603

training_state.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c3349d7fa073dd02607a9fe38593256946c29788b2eabe67415ef1414f39dd
-size 2522
+oid sha256:bc6c6b265b4370f1db602572ba1c1b4746d86f8e0035f2da4415700db4a41b04
+size 2773