End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: openai/whisper-small
+base_model: openai/whisper-medium
 tags:
 - generated_from_trainer
 metrics:
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-medium-gronings
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
+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: 0.6553
-- Wer Ortho: 23.8621
-- Wer: 23.7195
+- Loss: 0.5036
+- Wer Ortho: 19.3896
+- Wer: 19.0964
 
 ## Model description
 
@@ -55,10 +55,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:-------:|:----:|:---------------:|:---------:|:-------:|
-| 0.0395        | 4.6948  | 500  | 0.5248          | 24.1515   | 24.0347 |
-| 0.0096        | 9.3897  | 1000 | 0.6062          | 23.4938   | 23.4043 |
-| 0.0028        | 14.0845 | 1500 | 0.6099          | 23.4412   | 23.2729 |
-| 0.004         | 18.7793 | 2000 | 0.6553          | 23.8621   | 23.7195 |
+| 0.0289        | 4.6948  | 500  | 0.4230          | 18.2584   | 18.0982 |
+| 0.0122        | 9.3897  | 1000 | 0.4559          | 17.6796   | 17.4678 |
+| 0.0076        | 14.0845 | 1500 | 0.4976          | 18.3899   | 18.1770 |
+| 0.0097        | 18.7793 | 2000 | 0.5036          | 19.3896   | 19.0964 |
 
 
 ### Framework versions

generation_config.json

@@ -1,44 +1,28 @@
 {
   "alignment_heads": [
     [
-      5,
-      3
+      13,
+      15
     ],
     [
-      5,
-      9
-    ],
-    [
-      8,
-      0
-    ],
-    [
-      8,
+      15,
       4
     ],
     [
-      8,
-      7
+      15,
+      15
     ],
     [
-      8,
-      8
+      16,
+      1
     ],
     [
-      9,
+      20,
       0
     ],
     [
-      9,
-      7
-    ],
-    [
-      9,
-      9
-    ],
-    [
-      10,
-      5
+      23,
+      4
     ]
   ],
   "begin_suppress_tokens": [
@@ -250,6 +234,8 @@
     49870,
     50254,
     50258,
+    50358,
+    50359,
     50360,
     50361,
     50362

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0bfc62fc6f5eb0b896a932e59af7689aacc0bdcd569033a3b32196f07eb9932
+oid sha256:2fda1c6f2de0712bf0a085f878adc4241656e04ffb5754acb0252771d2868b50
 size 3055544304