End of training

README.md

@@ -6,6 +6,8 @@ license: apache-2.0
 base_model: openai/whisper-tiny
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: sumukhshadakshari/whisper-finetuned-all-3
   results: []
@@ -17,6 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 # sumukhshadakshari/whisper-finetuned-all-3
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the AtCO2_UWB, Atcosim, Bial dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0967
+- Wer: 7.6923
 
 ## Model description
 
@@ -41,15 +46,16 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 5
-- num_epochs: 1
+- lr_scheduler_warmup_steps: 1
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 1.0   | 1    | 0.4840          | 2.3256 |
+| 1.0967        | 1.0   | 1    | 1.0967          | 7.6923 |
+| 1.0967        | 2.0   | 2    | 1.0967          | 7.6923 |
 
 
 ### Framework versions

runs/Nov18_12-48-41_Sumukh_PC/events.out.tfevents.1731914324.Sumukh_PC.22400.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439bdf7a4b237d22d21e69942903bd0092306bc89e05fde2811931769ca913c3
+size 7244

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:695b3dcaf942f3d3e6c7a22a7aeaf06f88e51c32a3601d78dc42d488c5383ea8
+oid sha256:224c7a69fbf6c01d8d58bba19769f8fa31a3a6d82d45274aa12a8c2fa2277a04
 size 5368