End of training

README.md

@@ -25,7 +25,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 34.577018249304054
+      value: 32.20306217135787
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the Common Voice 14.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5649
-- Wer: 34.5770
+- Loss: 0.5723
+- Wer: 32.2031
 
 ## Model description
 
@@ -56,8 +56,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 32
-- eval_batch_size: 16
+- train_batch_size: 64
+- eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -70,7 +70,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0023        | 7.09  | 1000 | 0.5649          | 34.5770 |
+| 0.0147        | 9.06  | 1000 | 0.5723          | 32.2031 |
 
 
 ### Framework versions

runs/Jan04_00-37-18_92c825c63a48/events.out.tfevents.1704328697.92c825c63a48.6400.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c4bd34d49689f8907ed5ef6c125a61c7817516024f6a4d80f2a827fa1a0c678
-size 11814
+oid sha256:aaa8487f9975c0ef8b7e4f04e2ed9ff343ffac8ced9f1a745a0452893392336c
+size 12168