End of training

README.md

@@ -2,10 +2,10 @@
 language:
 - ko
 license: apache-2.0
+base_model: openai/whisper-medium
 tags:
 - hf-asr-leaderboard
 - generated_from_trainer
-base_model: openai/whisper-medium
 datasets:
 - aihub.or.kr
 model-index:
@@ -19,6 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 # whisper_medium_ptt
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the telephone dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9243
+- Cer: 20.6774
 
 ## Model description
 
@@ -43,11 +46,17 @@ 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: 50
-- training_steps: 100
+- lr_scheduler_warmup_steps: 500
+- training_steps: 4000
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss | Cer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.0001        | 71.43  | 1000 | 0.8405          | 21.2121 |
+| 0.0           | 142.86 | 2000 | 0.8907          | 20.4991 |
+| 0.0           | 214.29 | 3000 | 0.9152          | 20.6774 |
+| 0.0           | 285.71 | 4000 | 0.9243          | 20.6774 |
 
 
 ### Framework versions

generation_config.json

@@ -144,6 +144,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
+  "language": "ko",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1ad5b09975b6386a2c6c389ae7b59dfe997866adac4a1a6818330002242a5d4
+oid sha256:5a2b6e604319dffadf38932fca956bee18aca47f055e5728e0e8cacfbc2c40dc
 size 3055544304