End of training

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 33.64544319600499
+      value: 0.27901658090337333
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,9 +29,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7041
-- Wer Ortho: 33.8532
-- Wer: 33.6454
+- Loss: 0.6171
+- Wer Ortho: 27.4836
+- Wer: 0.2790
 
 ## Model description
 
@@ -57,14 +57,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 0.0015        | 17.86 | 500  | 0.7041          | 33.8532   | 33.6454 |
+| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
+| 0.0008        | 17.86 | 500  | 0.5203          | 26.2939   | 0.2647 |
+| 0.0002        | 35.71 | 1000 | 0.5680          | 25.9964   | 0.2630 |
+| 0.0001        | 53.57 | 1500 | 0.5961          | 26.1154   | 0.2653 |
+| 0.0001        | 71.43 | 2000 | 0.6171          | 27.4836   | 0.2790 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7736c51b88becb3321dde8eb1ab40d7da69d091ee1a350f496957da5717ab41a
+oid sha256:7b80fac159d734ddf5e8c55bf92ea0a80d9ea91a9b1905f93cfda4320a013af5
 size 151061672