End of training

README.md

@@ -2,23 +2,23 @@
 language:
 - ko
 license: apache-2.0
-base_model: openai/whisper-large
+base_model: openai/whisper-base
 tags:
 - hf-asr-leaderboard
 - generated_from_trainer
 datasets:
-- gingercake01/0528_1000freetalksamplewithnoise
+- gingercake01/0529_1000audio_base
 model-index:
-- name: largeWhisper_finetuned_with_noise
+- name: baseWhisper_finetune
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# largeWhisper_finetuned_with_noise
+# baseWhisper_finetune
 
-This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the 1000freetalksample dataset.
+This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the 1000freetalksample dataset.
 
 ## Model description
 
@@ -38,7 +38,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 16
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

generation_config.json

@@ -1,40 +1,36 @@
 {
   "alignment_heads": [
     [
-      9,
-      19
+      3,
+      1
     ],
     [
-      11,
+      4,
       2
     ],
     [
-      11,
-      4
-    ],
-    [
-      11,
-      17
+      4,
+      3
     ],
     [
-      22,
+      4,
       7
     ],
     [
-      22,
-      11
+      5,
+      1
     ],
     [
-      22,
-      17
+      5,
+      2
     ],
     [
-      23,
-      2
+      5,
+      4
     ],
     [
-      23,
-      15
+      5,
+      6
     ]
   ],
   "begin_suppress_tokens": [