End of training

README.md

@@ -5,9 +5,24 @@ tags:
 - generated_from_trainer
 datasets:
 - PolyAI/minds14
+metrics:
+- wer
 model-index:
 - name: whisper-tiny-dv
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: PolyAI/minds14
+      type: PolyAI/minds14
+      config: en-US
+      split: train
+      args: en-US
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.3520671834625323
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,14 +32,9 @@ 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:
-- eval_loss: 0.6233
-- eval_wer_ortho: 0.3499
-- eval_wer: 0.3463
-- eval_runtime: 28.4463
-- eval_samples_per_second: 3.972
-- eval_steps_per_second: 0.281
-- epoch: 2.0
-- step: 56
+- Loss: 0.6490
+- Wer Ortho: 0.3567
+- Wer: 0.3521
 
 ## Model description
 
@@ -50,7 +60,17 @@ 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: 100
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    | Wer Ortho |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|
+| 0.022         | 1.0   | 28   | 0.5935          | 0.3605 | 0.3661    |
+| 0.0158        | 2.0   | 56   | 0.6233          | 0.3463 | 0.3499    |
+| 0.0067        | 3.0   | 84   | 0.6469          | 0.3546 | 0.3521    |
+| 0.0066        | 3.57  | 100  | 0.6490          | 0.3567 | 0.3521    |
+
 
 ### Framework versions
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97080dc756111c2d08b8daa12981ccce0d99da0653477d5907407d23e4e1e9a0
+oid sha256:0aa3200647226a68815929d88238801c40e7a5b1f7c67e4c0be7e9e8d9e72cd8
 size 151099049