update model card README.md

README.md

@@ -1,41 +1,38 @@
 ---
-language:
-- be
 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 Tiny Belarusian
+- name: whisper-tiny-be-test
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: mozilla-foundation/common_voice_11_0 be
-      type: mozilla-foundation/common_voice_11_0
+      name: common_voice_11_0
+      type: common_voice_11_0
       config: be
       split: validation
       args: be
     metrics:
     - name: Wer
       type: wer
-      value: 52.197802197802204
+      value: 61.72161172161172
 ---
 
 <!-- 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 Tiny Belarusian
+# whisper-tiny-be-test
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the mozilla-foundation/common_voice_11_0 be dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_11_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5074
-- Wer: 52.1978
+- Loss: 0.5790
+- Wer: 61.7216
 
 ## Model description
 
@@ -54,34 +51,30 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 0.0001
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 300
+- lr_scheduler_warmup_steps: 10
+- training_steps: 100
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 2.4473        | 0.5   | 10   | 1.3675          | 95.4212 |
-| 1.256         | 1.0   | 20   | 0.9745          | 75.2747 |
-| 0.9934        | 0.3   | 30   | 0.8114          | 72.1612 |
-| 0.9568        | 0.4   | 40   | 0.7814          | 72.7106 |
-| 0.6856        | 0.5   | 50   | 0.7517          | 76.9231 |
-| 0.7808        | 0.6   | 60   | 0.6514          | 63.5531 |
-| 0.6826        | 0.7   | 70   | 0.6197          | 60.4396 |
-| 0.7832        | 0.8   | 80   | 0.6129          | 65.9341 |
-| 0.6031        | 0.9   | 90   | 0.5877          | 61.3553 |
-| 0.6678        | 1.0   | 100  | 0.5759          | 61.5385 |
-| 0.4611        | 0.07  | 110  | 0.5625          | 57.6923 |
-| 0.4451        | 0.13  | 120  | 0.5636          | 56.5934 |
-| 0.3615        | 0.2   | 130  | 0.5490          | 61.1722 |
-| 0.4055        | 0.27  | 140  | 0.5382          | 55.1282 |
-| 0.2946        | 0.33  | 150  | 0.5387          | 55.6777 |
+| 2.5622        | 0.1   | 10   | 1.5402          | 94.5055 |
+| 1.3719        | 0.2   | 20   | 1.0012          | 75.2747 |
+| 0.9898        | 0.3   | 30   | 0.8217          | 72.7106 |
+| 0.9742        | 0.4   | 40   | 0.7924          | 72.5275 |
+| 0.6951        | 0.5   | 50   | 0.7628          | 76.1905 |
+| 0.7824        | 0.6   | 60   | 0.6738          | 65.3846 |
+| 0.6818        | 0.7   | 70   | 0.6389          | 60.0733 |
+| 0.7823        | 0.8   | 80   | 0.6208          | 65.7509 |
+| 0.5994        | 0.9   | 90   | 0.5901          | 61.9048 |
+| 0.6647        | 1.0   | 100  | 0.5790          | 61.7216 |
 
 
 ### Framework versions

train.log

@@ -151,3 +151,5 @@
 {'loss': 0.5994, 'learning_rate': 1.4444444444444444e-05, 'epoch': 0.9}
 {'eval_loss': 0.5900620818138123, 'eval_wer': 61.904761904761905, 'eval_runtime': 17.489, 'eval_samples_per_second': 3.659, 'eval_steps_per_second': 0.114, 'epoch': 0.9}
 {'loss': 0.6647, 'learning_rate': 3.3333333333333333e-06, 'epoch': 1.0}
+{'eval_loss': 0.5789934992790222, 'eval_wer': 61.72161172161172, 'eval_runtime': 18.4962, 'eval_samples_per_second': 3.46, 'eval_steps_per_second': 0.108, 'epoch': 1.0}
+{'train_runtime': 873.4716, 'train_samples_per_second': 3.664, 'train_steps_per_second': 0.114, 'train_loss': 1.0103698587417602, 'epoch': 1.0}