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: 0.0648
-- Cer: 16.5180
+- Loss: 0.0756
+- Cer: 52.2014
 
 ## Model description
 
@@ -47,21 +42,23 @@ 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: 2500
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss | Cer     |
 |:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 0.1522        | 1.6556  | 250  | 0.2270          | 61.8129 |
-| 0.0178        | 3.3113  | 500  | 0.0794          | 71.1942 |
-| 0.0087        | 4.9669  | 750  | 0.0727          | 31.7698 |
-| 0.0037        | 6.6225  | 1000 | 0.0612          | 24.8345 |
-| 0.0004        | 8.2781  | 1250 | 0.0646          | 35.1367 |
-| 0.0004        | 9.9338  | 1500 | 0.0632          | 16.5468 |
-| 0.0004        | 11.5894 | 1750 | 0.0644          | 16.8921 |
-| 0.0004        | 13.2450 | 2000 | 0.0648          | 16.5180 |
+| 0.1473        | 1.6556  | 250  | 0.2276          | 54.4748 |
+| 0.0271        | 3.3113  | 500  | 0.0899          | 53.9281 |
+| 0.0082        | 4.9669  | 750  | 0.0735          | 64.8921 |
+| 0.0013        | 6.6225  | 1000 | 0.0682          | 35.7698 |
+| 0.0006        | 8.2781  | 1250 | 0.0703          | 60.6906 |
+| 0.0003        | 9.9338  | 1500 | 0.0705          | 54.7626 |
+| 0.0003        | 11.5894 | 1750 | 0.0710          | 56.8345 |
+| 0.0003        | 13.2450 | 2000 | 0.0737          | 53.5252 |
+| 0.0002        | 14.9007 | 2250 | 0.0752          | 52.4029 |
+| 0.0002        | 16.5563 | 2500 | 0.0756          | 52.2014 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b28705206244f0efadd489e0a5ee17437a70532191cfaf2bbfd46f1c80a893b4
+oid sha256:2af3b69ecba7c7da5e5ca03cab1b1cb4a17c867f0303247e2f9f8601b4c47b3d
 size 3055544304

runs/Nov14_12-51-57_dev4.nectarsoft/events.out.tfevents.1731556319.dev4.nectarsoft.685568.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dd70ff0f6a085fa965fc0c6408ff8f928cc97ae2cde85b2f8b2bd7862fd0f80
-size 29930
+oid sha256:a73e74c1ac2f332e8582ea5f47eba758029ace08b7b3ab86abebf51e8dc0b391
+size 30284