12/21/2022 10:10:48 - INFO - __main__ - running evaluation script with following parameters: Namespace(batch_size=16, config='be_by', dataset='google/fleurs', device=0, language='be', max_eval_samples=None, model_id='ales/whisper-small-belarusian', push_to_hub=True, save_predictions=True, split='test', streaming=True, text_column='raw_transcription') 12/21/2022 10:10:48 - INFO - __main__ - using following text normalizer: 12/21/2022 10:10:54 - INFO - __main__ - loading dataset 12/21/2022 10:10:56 - INFO - __main__ - running inference 12/21/2022 10:52:01 - INFO - __main__ - computing metrics 12/21/2022 10:52:01 - INFO - __main__ - metrics computed 12/21/2022 10:52:01 - INFO - __main__ - WER: 45.89674723962996 12/21/2022 10:52:01 - INFO - __main__ - saving predictions to: "preds_google_fleurs_be_by_test_20221221-101048.tsv" 12/21/2022 10:52:01 - INFO - __main__ - updating model card and pushing to HuggingFace Hub /home/ubuntu/python_venvs/hf_env/lib/python3.8/site-packages/transformers/generation/utils.py:1134: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use a generation configuration file (see https://huggingface.co/docs/transformers/main_classes/text_generation) warnings.warn( Traceback (most recent call last): File "src/run_eval_whisper_streaming.py", line 219, in main(args) File "src/run_eval_whisper_streaming.py", line 123, in main evaluate.push_to_hub( File "/home/ubuntu/python_venvs/hf_env/lib/python3.8/site-packages/evaluate/hub.py", line 119, in push_to_hub return metadata_update(repo_id=model_id, metadata=metadata, overwrite=overwrite) File "/home/ubuntu/python_venvs/hf_env/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 124, in _inner_fn return fn(*args, **kwargs) File "/home/ubuntu/python_venvs/hf_env/lib/python3.8/site-packages/huggingface_hub/repocard.py", line 802, in metadata_update raise ValueError( ValueError: You passed a new value for the existing metric 'name: WER, type: wer'. Set `overwrite=True` to overwrite existing metrics.