End of training

README.md

@@ -2,10 +2,10 @@
 language:
 - ko
 license: apache-2.0
+base_model: openai/whisper-medium
 tags:
 - hf-asr-leaderboard
 - generated_from_trainer
-base_model: openai/whisper-medium
 datasets:
 - aihub.or.kr
 model-index:
@@ -20,8 +20,8 @@ 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: 0.6867
-- Cer: 6.4516
+- Loss: 0.3286
+- Cer: 4.9724
 
 ## Model description
 
@@ -53,15 +53,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch     | Step | Validation Loss | Cer    |
 |:-------------:|:---------:|:----:|:---------------:|:------:|
-| 0.0           | 333.3333  | 1000 | 0.5950          | 6.4516 |
-| 0.0           | 666.6667  | 2000 | 0.6432          | 6.4516 |
-| 0.0           | 1000.0    | 3000 | 0.6765          | 6.4516 |
-| 0.0           | 1333.3333 | 4000 | 0.6867          | 6.4516 |
+| 0.0           | 333.3333  | 1000 | 0.2826          | 3.8674 |
+| 0.0           | 666.6667  | 2000 | 0.3079          | 4.9724 |
+| 0.0           | 1000.0    | 3000 | 0.3227          | 4.9724 |
+| 0.0           | 1333.3333 | 4000 | 0.3286          | 4.9724 |
 
 
 ### Framework versions
 
-- Transformers 4.40.0
-- Pytorch 2.2.2+cu121
-- Datasets 2.19.0
+- Transformers 4.43.3
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
 - Tokenizers 0.19.1

generation_config.json

@@ -245,5 +245,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.43.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d78d0ac5829f20f7ba07614c83841e88d5d8cffa15188bebd9293d51ba6e28
+oid sha256:27b58238ae503316bd36fd435ee97ea54e74e5c693c3833903c5e517310c4a34
 size 3055544304