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 Small 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: 55.12820512820513
+      value: 55.311355311355314
 ---
 
+<!-- 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
 
-Test model repository to debug train & evaluation scrips.
-
-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: 0.5382
-- Wer: 55.1282
+- Loss: 0.5342
+- Wer: 55.3114
 
 ## Model description
 
@@ -54,14 +51,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3.1578947368421056e-06
+- learning_rate: 1e-05
 - 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
-- lr_scheduler_warmup_steps: 5
-- training_steps: 150
+- training_steps: 200
 - mixed_precision_training: Native AMP
 
 ### Training results

train.log

@@ -81,3 +81,5 @@
 {'loss': 0.3533, 'learning_rate': 8.050000000000001e-06, 'epoch': 0.2}
 {'eval_loss': 0.530021071434021, 'eval_wer': 56.59340659340659, 'eval_runtime': 18.1912, 'eval_samples_per_second': 3.518, 'eval_steps_per_second': 0.11, 'epoch': 0.2}
 {'loss': 0.2844, 'learning_rate': 7.5500000000000006e-06, 'epoch': 0.25}
+{'eval_loss': 0.5341857671737671, 'eval_wer': 55.311355311355314, 'eval_runtime': 17.7172, 'eval_samples_per_second': 3.612, 'eval_steps_per_second': 0.113, 'epoch': 0.25}
+{'train_runtime': 406.2172, 'train_samples_per_second': 15.755, 'train_steps_per_second': 0.492, 'train_loss': 0.0719480574131012, 'epoch': 0.25}