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: 0.0981
-- Cer: 7.6835
+- Loss: 0.0693
+- Cer: 11.1079
 
 ## Model description
 
@@ -47,23 +42,21 @@ 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: 5000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss | Cer     |
 |:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 0.0276        | 3.3113  | 500  | 0.0852          | 35.1942 |
-| 0.002         | 6.6225  | 1000 | 0.0692          | 10.1871 |
-| 0.0006        | 9.9338  | 1500 | 0.0783          | 12.0863 |
-| 0.0002        | 13.2450 | 2000 | 0.0900          | 7.7698  |
-| 0.0001        | 16.5563 | 2500 | 0.0923          | 8.6619  |
-| 0.0001        | 19.8675 | 3000 | 0.0939          | 7.7410  |
-| 0.0001        | 23.1788 | 3500 | 0.0954          | 6.7050  |
-| 0.0001        | 26.4901 | 4000 | 0.0967          | 6.8201  |
-| 0.0           | 29.8013 | 4500 | 0.0978          | 7.6259  |
-| 0.0           | 33.1126 | 5000 | 0.0981          | 7.6835  |
+| 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 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4a4921f27d1a773d370ef0c7d89c99dc297b49a560373472f3eee414420ac1
+oid sha256:fb374b4c043c6b19de611979546ad7d90dea154ef0296ec314bc449326c1284c
 size 3055544304

runs/Nov13_15-38-36_dev4.nectarsoft/events.out.tfevents.1731479921.dev4.nectarsoft.1339056.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a57bbce337bc12183f97f72a1fabd0461a3d168bfca15c54c698705cb77063
-size 25074
+oid sha256:244fd524453cd1ce5f2893f87168644cd27feb9f878c09369f6dd2873deb279f
+size 25428