End of training

README.md

@@ -12,7 +12,7 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: whisper-small-finetuned-translation-common-voice-mr
+- name: whisper-small-finetuned-common-voice-mr-2.1
   results:
   - task:
       name: Automatic Speech Recognition
@@ -26,19 +26,19 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 17.817506151760156
+      value: 17.93049766484206
 ---
 
 <!-- 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-finetuned-translation-common-voice-mr
+# whisper-small-finetuned-common-voice-mr-2.1
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2483
-- Wer Ortho: 43.9028
-- Wer: 17.8175
+- Loss: 0.2478
+- Wer Ortho: 44.0374
+- Wer: 17.9305
 
 ## Model description
 
@@ -61,7 +61,7 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
 - training_steps: 500
@@ -71,12 +71,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
-| 0.182         | 1.1737 | 500  | 0.2483          | 43.9028   | 17.8175 |
+| 0.1802        | 1.1737 | 500  | 0.2478          | 44.0374   | 17.9305 |
 
 
 ### Framework versions
 
-- Transformers 4.45.1
-- Pytorch 2.4.0
-- Datasets 3.0.1
-- Tokenizers 0.20.0
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

generation_config.json

@@ -171,5 +171,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.45.1"
+  "transformers_version": "4.46.2"
 }