Model save

README.md

@@ -1,29 +1,13 @@
 ---
-language:
-- ko
 license: apache-2.0
 base_model: openai/whisper-medium
 tags:
-- hf-asr-leaderboard
 - generated_from_trainer
-datasets:
-- Marcusxx/chungnamFireStation3Kfiles
 metrics:
 - wer
 model-index:
 - name: chungnam_firestation3Kfiles_WER_model
-  results:
-  - task:
-      type: automatic-speech-recognition
-      name: Automatic Speech Recognition
-    dataset:
-      name: Marcusxx/chungnamFireStation3Kfiles
-      type: Marcusxx/chungnamFireStation3Kfiles
-      args: 'config: ko, split: valid'
-    metrics:
-    - type: wer
-      value: 71.42857142857143
-      name: Wer
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # chungnam_firestation3Kfiles_WER_model
 
-This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Marcusxx/chungnamFireStation3Kfiles 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: 0.8160
-- Wer: 71.4286
+- Loss: 1.0247
+- Wer: 53.2091
 
 ## Model description
 
@@ -59,22 +43,24 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 200
-- training_steps: 2000
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 10000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer      |
-|:-------------:|:-------:|:----:|:---------------:|:--------:|
-| 0.4806        | 1.6667  | 250  | 0.6231          | 188.1988 |
-| 0.0995        | 3.3333  | 500  | 0.6420          | 99.3789  |
-| 0.0506        | 5.0     | 750  | 0.6920          | 72.2567  |
-| 0.0227        | 6.6667  | 1000 | 0.7302          | 72.5673  |
-| 0.0043        | 8.3333  | 1250 | 0.7620          | 77.0186  |
-| 0.0042        | 10.0    | 1500 | 0.8043          | 84.8861  |
-| 0.0016        | 11.6667 | 1750 | 0.8114          | 71.4286  |
-| 0.0005        | 13.3333 | 2000 | 0.8160          | 71.4286  |
+| Training Loss | Epoch   | Step  | Validation Loss | Wer      |
+|:-------------:|:-------:|:-----:|:---------------:|:--------:|
+| 0.0822        | 6.6667  | 1000  | 0.6869          | 122.9814 |
+| 0.0145        | 13.3333 | 2000  | 0.8470          | 58.6957  |
+| 0.0092        | 20.0    | 3000  | 0.8744          | 52.6915  |
+| 0.0041        | 26.6667 | 4000  | 0.9301          | 58.0745  |
+| 0.0009        | 33.3333 | 5000  | 0.9330          | 55.1760  |
+| 0.0004        | 40.0    | 6000  | 0.9455          | 52.7950  |
+| 0.0001        | 46.6667 | 7000  | 0.9811          | 52.3810  |
+| 0.0           | 53.3333 | 8000  | 1.0021          | 52.6915  |
+| 0.0           | 60.0    | 9000  | 1.0185          | 52.8986  |
+| 0.0           | 66.6667 | 10000 | 1.0247          | 53.2091  |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0de10bc605217d33473e945fea08cb3aba9b42d7374af1e82621015482aa10
+oid sha256:9051aac1b0cba68b0760e2455a78c7f919e40a58d7ba74233fde407e193905ca
 size 3055544304