End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.40703517587939697
+      value: 0.001256281407035176
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +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:
-- Loss: 0.9685
-- Wer Ortho: 40.1048
-- Wer: 0.4070
+- Loss: 0.0001
+- Wer Ortho: 0.0013
+- Wer: 0.0013
 
 ## Model description
 
@@ -60,14 +60,13 @@ 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: 1000
+- training_steps: 100
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
-| 0.0006        | 31.25 | 500  | 0.8965          | 38.4010   | 0.3932 |
-| 0.0002        | 62.5  | 1000 | 0.9685          | 40.1048   | 0.4070 |
+| 0.0           | 6.25  | 100  | 0.0001          | 0.0013    | 0.0013 |
 
 
 ### Framework versions

generation_config.json

@@ -1,30 +1,4 @@
 {
-  "alignment_heads": [
-    [
-      2,
-      2
-    ],
-    [
-      3,
-      0
-    ],
-    [
-      3,
-      2
-    ],
-    [
-      3,
-      3
-    ],
-    [
-      3,
-      4
-    ],
-    [
-      3,
-      5
-    ]
-  ],
   "begin_suppress_tokens": [
     220,
     50257