End of training

README.md

@@ -1,8 +1,8 @@
 ---
 language:
 - ko
-license: apache-2.0
-base_model: openai/whisper-small
+license: mit
+base_model: openai/whisper-large-v3-turbo
 tags:
 - generated_from_trainer
 datasets:
@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 55.97826086956522
+      value: 52.71739130434783
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper Small ko
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the custom dataset.
+This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the custom dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5115
-- Wer: 55.9783
+- Loss: 1.4327
+- Wer: 52.7174
 
 ## Model description
 
@@ -66,7 +66,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 1.0506        | 0.2   | 10   | 1.5115          | 55.9783 |
+| 0.9079        | 0.2   | 10   | 1.4327          | 52.7174 |
 
 
 ### Framework versions

generation_config.json

@@ -1,44 +1,28 @@
 {
   "alignment_heads": [
     [
-      5,
-      3
-    ],
-    [
-      5,
-      9
-    ],
-    [
-      8,
-      0
-    ],
-    [
-      8,
+      2,
       4
     ],
     [
-      8,
-      7
+      2,
+      11
     ],
     [
-      8,
-      8
-    ],
-    [
-      9,
-      0
+      3,
+      3
     ],
     [
-      9,
-      7
+      3,
+      6
     ],
     [
-      9,
-      9
+      3,
+      11
     ],
     [
-      10,
-      5
+      3,
+      14
     ]
   ],
   "begin_suppress_tokens": [
@@ -148,14 +132,15 @@
     "<|vi|>": 50278,
     "<|yi|>": 50335,
     "<|yo|>": 50325,
+    "<|yue|>": 50358,
     "<|zh|>": 50260
   },
   "language": "ko",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
-  "no_timestamps_token_id": 50363,
+  "no_timestamps_token_id": 50364,
   "pad_token_id": 50257,
-  "prev_sot_token_id": 50361,
+  "prev_sot_token_id": 50362,
   "return_timestamps": false,
   "suppress_tokens": [
     1,
@@ -241,16 +226,16 @@
     49870,
     50254,
     50258,
-    50358,
     50359,
     50360,
     50361,
-    50362
+    50362,
+    50363
   ],
   "task": "transcribe",
   "task_to_id": {
-    "transcribe": 50359,
-    "translate": 50358
+    "transcribe": 50360,
+    "translate": 50359
   },
   "transformers_version": "4.42.3"
 }