End of training

README.md

@@ -2,12 +2,12 @@
 language:
 - ko
 license: apache-2.0
+base_model: openai/whisper-medium
 tags:
 - hf-asr-leaderboard
 - generated_from_trainer
 datasets:
 - aihub.or.kr
-base_model: openai/whisper-medium
 model-index:
 - name: whisper_medium_ptt
   results: []
@@ -20,7 +20,7 @@ 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 telephone dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8240
+- Loss: 0.7810
 - Cer: 100.0
 
 ## Model description
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Cer   |
 |:-------------:|:------:|:----:|:---------------:|:-----:|
-| 0.0001        | 71.43  | 1000 | 0.7352          | 100.0 |
-| 0.0           | 142.86 | 2000 | 0.7866          | 100.0 |
-| 0.0           | 214.29 | 3000 | 0.8135          | 100.0 |
-| 0.0           | 285.71 | 4000 | 0.8240          | 100.0 |
+| 0.0001        | 71.43  | 1000 | 0.7159          | 100.0 |
+| 0.0           | 142.86 | 2000 | 0.7557          | 100.0 |
+| 0.0           | 214.29 | 3000 | 0.7740          | 100.0 |
+| 0.0           | 285.71 | 4000 | 0.7810          | 100.0 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54abbbc464c641d350f8da0feb2652d5f851076d73844bf6cf1715b3d9b6724
+oid sha256:3e9add5ec109e4eb4e3563e92fe21dd8d8cea7d04fd954e12b50d73db0a1727c
 size 3055544304