Model save

README.md

@@ -1,17 +1,36 @@
 ---
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
-- name: whisper-small-en
+- name: whisper-small.en
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# whisper-small-en
+# whisper-small.en
 
-This model was trained on OpenAI/Whisper-Small-en on the Medical Audios dataset.
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0244
+- Wer: 2.5393
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
 
 ### Training hyperparameters
 
@@ -26,10 +45,13 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 10
-- mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.1861        | 4.15  | 500  | 0.1216          | 4.5546 |
+| 0.028         | 8.31  | 1000 | 0.0244          | 2.5393 |
 
 
 ### Framework versions

generation_config.json

@@ -96,6 +96,7 @@
   "no_timestamps_token_id": 50362,
   "pad_token_id": 50256,
   "prev_sot_token_id": 50360,
+  "return_timestamps": false,
   "suppress_tokens": [
     1,
     2,

runs/May29_10-54-23_54265c3f29ef/events.out.tfevents.1748516064.54265c3f29ef.3117.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706bfc3435eb93dcc13c16f7956a2f70b5949bb918abbda813dccf3f15d77180
-size 8193
+oid sha256:643c843d10053448ba63eedf2740034f1ca8afff46493a3f4c24572b903a6aa7
+size 8861