Model save

README.md

@@ -1,12 +1,7 @@
 ---
-base_model: openai/whisper-medium
-datasets:
-- Marcusxx/chungnam_firestation
-language:
-- ko
 license: apache-2.0
+base_model: openai/whisper-medium
 tags:
-- hf-asr-leaderboard
 - generated_from_trainer
 model-index:
 - name: chungnam_firestation_model
@@ -18,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # chungnam_firestation_model
 
-This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Marcusxx/chungnam_firestation dataset.
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0693
-- Cer: 11.1079
+- Loss: 0.0638
+- Cer: 31.1655
 
 ## Model description
 
@@ -47,21 +42,25 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
-- training_steps: 2000
+- training_steps: 3000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss | Cer     |
 |:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 0.1482        | 1.6556  | 250  | 0.2164          | 44.3741 |
-| 0.0162        | 3.3113  | 500  | 0.0701          | 19.6547 |
-| 0.0074        | 4.9669  | 750  | 0.0648          | 15.8849 |
-| 0.0025        | 6.6225  | 1000 | 0.0600          | 17.9568 |
-| 0.0003        | 8.2781  | 1250 | 0.0651          | 15.0791 |
-| 0.0003        | 9.9338  | 1500 | 0.0674          | 11.6259 |
-| 0.0003        | 11.5894 | 1750 | 0.0688          | 11.1079 |
-| 0.0003        | 13.2450 | 2000 | 0.0693          | 11.1079 |
+| 0.1397        | 1.6556  | 250  | 0.2156          | 53.2086 |
+| 0.0187        | 3.3113  | 500  | 0.0887          | 15.2230 |
+| 0.0187        | 4.9669  | 750  | 0.0559          | 25.6978 |
+| 0.002         | 6.6225  | 1000 | 0.0626          | 20.4604 |
+| 0.0004        | 8.2781  | 1250 | 0.0588          | 28.5755 |
+| 0.0012        | 9.9338  | 1500 | 0.0603          | 34.9640 |
+| 0.0002        | 11.5894 | 1750 | 0.0597          | 34.0432 |
+| 0.0002        | 13.2450 | 2000 | 0.0603          | 28.8058 |
+| 0.0001        | 14.9007 | 2250 | 0.0620          | 28.1439 |
+| 0.0001        | 16.5563 | 2500 | 0.0630          | 31.6547 |
+| 0.0001        | 18.2119 | 2750 | 0.0636          | 31.1079 |
+| 0.0001        | 19.8675 | 3000 | 0.0638          | 31.1655 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88cebdb0f94677eb6f4617009b15ebe73b3d00bf0d6407022a238c449cf9b59b
+oid sha256:05b3b0299658e8d8f0ffd324e0fa27067663c13678884402503d31ddc64b9073
 size 3055544304

runs/Nov13_18-05-25_dev4.nectarsoft/events.out.tfevents.1731488727.dev4.nectarsoft.1708315.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a9250499d1780b07cee37f0855b9568d00e03586f919fa0ce0899a9688fa74
-size 34786
+oid sha256:e06d589293c51c51aadb0ab0dee7f0a986e1180ba6b409fee8bf455f079d24a4
+size 35140