update model card README.md

README.md

@@ -1,39 +1,38 @@
 ---
 license: apache-2.0
 tags:
-- whisper-event
 - generated_from_trainer
 datasets:
-- NbAiLab/NCC_S
+- ncc_s
 metrics:
 - wer
 model-index:
-- name: Whisper Base Norwegian
+- name: pere/whisper-small-nob-clr
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: NbAiLab/NCC_S
-      type: NbAiLab/NCC_S
+      name: ncc_s
+      type: ncc_s
       config: 'no'
       split: validation
       args: 'no'
     metrics:
     - name: Wer
       type: wer
-      value: 16.017052375152254
+      value: 15.012180267965894
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Whisper Base Norwegian
+# pere/whisper-small-nob-clr
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the NbAiLab/NCC_S dataset.
+This model is a fine-tuned version of [pere/whisper-small-nob-clr](https://huggingface.co/pere/whisper-small-nob-clr) on the ncc_s dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3290
-- Wer: 16.0171
+- Loss: 0.3284
+- Wer: 15.0122
 
 ## Model description
 
@@ -60,19 +59,16 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
-- lr_scheduler_warmup_steps: 500
-- training_steps: 5000
+- training_steps: 3000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.8528        | 0.2   | 1000 | 0.4402          | 22.5639 |
-| 0.7558        | 0.4   | 2000 | 0.3861          | 19.7016 |
-| 0.721         | 0.6   | 3000 | 0.3545          | 17.8441 |
-| 0.6803        | 0.8   | 4000 | 0.3364          | 16.5652 |
-| 0.6557        | 1.0   | 5000 | 0.3290          | 16.0171 |
+| 0.5975        | 0.33  | 1000 | 0.3354          | 15.7734 |
+| 0.5783        | 0.67  | 2000 | 0.3327          | 16.3520 |
+| 0.5788        | 1.0   | 3000 | 0.3284          | 15.0122 |
 
 
 ### Framework versions