End of training

README.md

@@ -2,8 +2,7 @@
 library_name: transformers
 language:
 - fr
-license: apache-2.0
-base_model: openai/whisper-Tiny
+base_model: openai/whisper-tiny_2_
 tags:
 - generated_from_trainer
 datasets:
@@ -11,7 +10,7 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: Whisper Tiny fr - Naji
+- name: Whisper tiny fr _2_ Naji
   results:
   - task:
       name: Automatic Speech Recognition
@@ -25,19 +24,19 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 12.997234630929588
+      value: 32.53961922995107
 ---
 
 <!-- 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 Tiny fr - Naji
+# Whisper tiny fr _2_ Naji
 
-This model is a fine-tuned version of [openai/whisper-Tiny](https://huggingface.co/openai/whisper-Tiny) on the Common Voice 1 dataset.
+This model is a fine-tuned version of [openai/whisper-tiny_2_](https://huggingface.co/openai/whisper-tiny_2_) on the Common Voice 1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3040
-- Wer Ortho: 23.5542
-- Wer: 12.9972
+- Loss: 0.5924
+- Wer Ortho: 41.9920
+- Wer: 32.5396
 
 ## Model description
 
@@ -70,12 +69,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
-| 0.3183        | 0.2877 | 500  | 0.3040          | 23.5542   | 12.9972 |
+| 0.6189        | 0.2877 | 500  | 0.5924          | 41.9920   | 32.5396 |
 
 
 ### Framework versions
 
-- Transformers 4.51.3
+- Transformers 4.52.2
 - Pytorch 2.6.0+cu124
 - Datasets 2.14.6
 - Tokenizers 0.21.1

generation_config.json

@@ -1,43 +1,27 @@
 {
   "alignment_heads": [
     [
-      5,
-      3
-    ],
-    [
-      5,
-      9
+      2,
+      2
     ],
     [
-      8,
+      3,
       0
     ],
     [
-      8,
-      4
-    ],
-    [
-      8,
-      7
+      3,
+      2
     ],
     [
-      8,
-      8
-    ],
-    [
-      9,
-      0
-    ],
-    [
-      9,
-      7
+      3,
+      3
     ],
     [
-      9,
-      9
+      3,
+      4
     ],
     [
-      10,
+      3,
       5
     ]
   ],
@@ -250,6 +234,8 @@
     49870,
     50254,
     50258,
+    50358,
+    50359,
     50360,
     50361,
     50362
@@ -258,5 +244,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.51.3"
+  "transformers_version": "4.52.2"
 }