Model save

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8962
+- Loss: 0.8963
 - Wer: 26.6667
 
 ## Model description
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0           | 350.0 | 350  | 0.8727          | 26.6667 |
-| 0.0           | 700.0 | 700  | 0.8962          | 26.6667 |
+| 0.0           | 350.0 | 350  | 0.8728          | 26.6667 |
+| 0.0           | 700.0 | 700  | 0.8963          | 26.6667 |
 
 
 ### Framework versions

all_results.json

@@ -6,8 +6,8 @@
     "eval_steps_per_second": 0.669,
     "eval_wer": 26.666666666666668,
     "total_flos": 2.857693741056e+18,
-    "train_loss": 0.007795538133268565,
-    "train_runtime": 870.9787,
-    "train_samples_per_second": 12.859,
-    "train_steps_per_second": 0.804
+    "train_loss": 0.00779592388232881,
+    "train_runtime": 872.7302,
+    "train_samples_per_second": 12.833,
+    "train_steps_per_second": 0.802
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e60df903b927e0b08904dbef9295571dda7421aa78bf8d4e25ebe9140411205c
+oid sha256:1edc41ed691335c0182e6c7d65fbe6793598ff30d3acb099416d5b953d15d1ef
 size 3055544304

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 700.0,
     "total_flos": 2.857693741056e+18,
-    "train_loss": 0.007795538133268565,
-    "train_runtime": 870.9787,
-    "train_samples_per_second": 12.859,
-    "train_steps_per_second": 0.804
+    "train_loss": 0.00779592388232881,
+    "train_runtime": 872.7302,
+    "train_samples_per_second": 12.833,
+    "train_steps_per_second": 0.802
 }