End of training

README.md

@@ -1,4 +1,5 @@
 ---
+license: apache-2.0
 base_model: openai/whisper-small
 tags:
 - generated_from_trainer
@@ -21,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 64.86486486486487
+      value: 67.56756756756756
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the audiofolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9392
-- Wer Ortho: 64.8649
-- Wer: 64.8649
+- Loss: 0.9642
+- Wer Ortho: 67.5676
+- Wer: 67.5676
 
 ## Model description
 
@@ -53,9 +54,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 30
@@ -63,13 +66,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer      |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:--------:|
-| 0.8766        | 20.0  | 60   | 1.1552          | 72.9730   | 267.5676 |
-| 0.0002        | 40.0  | 120  | 0.9049          | 62.1622   | 64.8649  |
-| 0.0           | 60.0  | 180  | 0.9195          | 64.8649   | 64.8649  |
-| 0.0           | 80.0  | 240  | 0.9327          | 64.8649   | 64.8649  |
-| 0.0           | 100.0 | 300  | 0.9392          | 64.8649   | 64.8649  |
+| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
+| 0.8789        | 20.0  | 60   | 1.2473          | 70.2703   | 70.2703 |
+| 0.0015        | 40.0  | 120  | 0.9230          | 72.9730   | 72.9730 |
+| 0.0           | 60.0  | 180  | 0.9398          | 67.5676   | 67.5676 |
+| 0.0           | 80.0  | 240  | 0.9529          | 67.5676   | 67.5676 |
+| 0.0           | 100.0 | 300  | 0.9642          | 67.5676   | 67.5676 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2938fff89376e68729e266b3985f4a70f556c0e2756ec84732e1662a548be3cf
+oid sha256:69774a70c8c55baa3d41fc5a9cbbe463ae7fbd8ba38fd1248c03b222c59c03d8
 size 966995080

runs/Jun11_20-26-35_MSI/events.out.tfevents.1718108796.MSI.3740.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb777448fce7a0f5e645f8a858f67cde4533aa5b56099dbd564d3435770fa9e5
-size 9962
+oid sha256:080538124ba4717c181347c56bb2633ff2f505226b883d56b6a75baaf25f4c83
+size 11320