update model card README.md

README.md

@@ -1,44 +1,38 @@
 ---
-language:
-- it
 license: apache-2.0
 tags:
-- whisper-event
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_11_0
+- common_voice_11_0
+metrics:
+- wer
 model-index:
-- name: Whisper Small It - Edoardo Abati
+- name: openai/whisper-small
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: mozilla-foundation/common_voice_11_0 it
-      type: mozilla-foundation/common_voice_11_0
+      name: common_voice_11_0
+      type: common_voice_11_0
       config: it
       split: test
       args: it
     metrics:
     - name: Wer
       type: wer
-      value: 10.1352
+      value: 9.26934935147778
 ---
 
 <!-- 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 Small It - Edoardo Abati
+# openai/whisper-small
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_11_0 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.2111
-- eval_wer: 10.1352
-- eval_runtime: 4736.3912
-- eval_samples_per_second: 3.168
-- eval_steps_per_second: 0.396
-- epoch: 0.4
-- step: 2000
+- Loss: 0.2013
+- Wer: 9.2693
 
 ## Model description
 
@@ -59,14 +53,24 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 64
-- eval_batch_size: 8
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 5000
+- training_steps: 4000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.2851        | 0.25  | 1000 | 0.2604          | 11.9744 |
+| 0.1885        | 0.5   | 2000 | 0.2176          | 10.1358 |
+| 0.1176        | 1.15  | 3000 | 0.2111          | 9.5664  |
+| 0.1256        | 1.4   | 4000 | 0.2013          | 9.2693  |
+
+
 ### Framework versions
 
 - Transformers 4.26.0.dev0