End of training

README.md

@@ -8,9 +8,24 @@ tags:
 - generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_11_0
+metrics:
+- wer
 model-index:
 - name: whisper-medium-id
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 11.0
+      type: mozilla-foundation/common_voice_11_0
+      config: id
+      split: test
+      args: 'config: id, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 13.595981208428299
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -20,13 +35,8 @@ 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 Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.2727
-- eval_wer: 12.4703
-- eval_runtime: 1243.9655
-- eval_samples_per_second: 2.908
-- eval_steps_per_second: 0.364
-- epoch: 7.7220
-- step: 4000
+- Loss: 0.2226
+- Wer: 13.5960
 
 ## Model description
 
@@ -45,7 +55,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 1e-06
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
@@ -55,6 +65,17 @@ The following hyperparameters were used during training:
 - training_steps: 5000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.2024        | 1.9305 | 1000 | 0.1830          | 13.1076 |
+| 0.109         | 3.8610 | 2000 | 0.1825          | 13.0750 |
+| 0.0608        | 5.7915 | 3000 | 0.1949          | 13.2797 |
+| 0.0327        | 7.7220 | 4000 | 0.2128          | 13.4750 |
+| 0.0258        | 9.6525 | 5000 | 0.2226          | 13.5960 |
+
+
 ### Framework versions
 
 - Transformers 4.44.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1b512cddbd82dd95dec8cf6a76f0f2ad1ba1582a880546f7538efb82c48eadc
+oid sha256:e543778c507f117534bd0b51eb25f209f1525482bfa45cfb8e352468031f0065
 size 3055544304

runs/Sep17_15-37-00_ae3cb5456c96/events.out.tfevents.1726587423.ae3cb5456c96.1149.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e94e0c7d098ea48496dfb4b0008827fa57f0fe57aa926cf7003871beb4521c9d
-size 50476
+oid sha256:eec81627a9964544750db0fbe92668ef66f6d16eafd764d15607bcc8cdb11c8a
+size 50830