I'm trying to fine tune the openai/whisper model from huggingface using jupyter notebook and i keep getting this error

### Describe the bug

I'm trying to fine tune the openai/whisper model from huggingface using jupyter notebook and i keep getting this error, i'm following the steps in this blog post

https://huggingface.co/blog/fine-tune-whisper

I tried google collab and it works but because I'm on the free version the training doesn't complete

the error comes in jupyter notebook when i run this line

`common_voice = common_voice.map(prepare_dataset, remove_columns=common_voice.column_names["train"], num_proc=4)`

here is the error message

```
Map (num_proc=4): 0% 0/2506 [00:52 1 common_voice = common_voice.map(prepare_dataset, remove_columns=common_voice.column_names["train"], num_proc=4)

File ~\anaconda\Lib\site-packages\datasets\dataset_dict.py:853, in DatasetDict.map(self, function, with_indices, with_rank, input_columns, batched, batch_size, drop_last_batch, remove_columns, keep_in_memory, load_from_cache_file, cache_file_names, writer_batch_size, features, disable_nullable, fn_kwargs, num_proc, desc) 850 if cache_file_names is None: 851 cache_file_names = {k: None for k in self} 852 return DatasetDict( --> 853 { 854 k: dataset.map( 855 function=function, 856 with_indices=with_indices, 857 with_rank=with_rank, 858 input_columns=input_columns, 859 batched=batched, 860 batch_size=batch_size, 861 drop_last_batch=drop_last_batch, 862 remove_columns=remove_columns, 863 keep_in_memory=keep_in_memory, 864 load_from_cache_file=load_from_cache_file, 865 cache_file_name=cache_file_names[k], 866 writer_batch_size=writer_batch_size, 867 features=features, 868 disable_nullable=disable_nullable, 869 fn_kwargs=fn_kwargs, 870 num_proc=num_proc, 871 desc=desc, 872 ) 873 for k, dataset in self.items() 874 } 875 )

File ~\anaconda\Lib\site-packages\datasets\dataset_dict.py:854, in (.0) 850 if cache_file_names is None: 851 cache_file_names = {k: None for k in self} 852 return DatasetDict( 853 { --> 854 k: dataset.map( 855 function=function, 856 with_indices=with_indices, 857 with_rank=with_rank, 858 input_columns=input_columns, 859 batched=batched, 860 batch_size=batch_size, 861 drop_last_batch=drop_last_batch, 862 remove_columns=remove_columns, 863 keep_in_memory=keep_in_memory, 864 load_from_cache_file=load_from_cache_file, 865 cache_file_name=cache_file_names[k], 866 writer_batch_size=writer_batch_size, 867 features=features, 868 disable_nullable=disable_nullable, 869 fn_kwargs=fn_kwargs, 870 num_proc=num_proc, 871 desc=desc, 872 ) 873 for k, dataset in self.items() 874 } 875 )

File ~\anaconda\Lib\site-packages\datasets\arrow_dataset.py:592, in transmit_tasks..wrapper(*args, **kwargs) 590 self: "Dataset" = kwargs.pop("self") 591 # apply actual function --> 592 out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs) 593 datasets: List["Dataset"] = list(out.values()) if isinstance(out, dict) else [out] 594 for dataset in datasets: 595 # Remove task templates if a column mapping of the template is no longer valid

File ~\anaconda\Lib\site-packages\datasets\arrow_dataset.py:557, in transmit_format..wrapper(*args, **kwargs) 550 self_format = { 551 "type": self._format_type, 552 "format_kwargs": self._format_kwargs, 553 "columns": self._format_columns, 554 "output_all_columns": self._output_all_columns, 555 } 556 # apply actual function --> 557 out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs) 558 datasets: List["Dataset"] = list(out.values()) if isinstance(out, dict) else [out] 559 # re-apply format to the output

File ~\anaconda\Lib\site-packages\datasets\arrow_dataset.py:3189, in Dataset.map(self, function, with_indices, with_rank, input_columns, batched, batch_size, drop_last_batch, remove_columns, keep_in_memory, load_from_cache_file, cache_file_name, writer_batch_size, features, disable_nullable, fn_kwargs, num_proc, suffix_template, new_fingerprint, desc) 3182 logger.info(f"Spawning {num_proc} processes") 3183 with logging.tqdm( 3184 disable=not logging.is_progress_bar_enabled(), 3185 unit=" examples", 3186 total=pbar_total, 3187 desc=(desc or "Map") + f" (num_proc={num_proc})", 3188 ) as pbar: -> 3189 for rank, done, content in iflatmap_unordered( 3190 pool, Dataset._map_single, kwargs_iterable=kwargs_per_job 3191 ): 3192 if done: 3193 shards_done += 1

File ~\anaconda\Lib\site-packages\datasets\utils\py_utils.py:1394, in iflatmap_unordered(pool, func, kwargs_iterable) 1391 finally: 1392 if not pool_changed: 1393 # we get the result in case there's an error to raise -> 1394 [async_result.get(timeout=0.05) for async_result in async_results]

File ~\anaconda\Lib\site-packages\datasets\utils\py_utils.py:1394, in (.0) 1391 finally: 1392 if not pool_changed: 1393 # we get the result in case there's an error to raise -> 1394 [async_result.get(timeout=0.05) for async_result in async_results]

File ~\anaconda\Lib\site-packages\multiprocess\pool.py:774, in ApplyResult.get(self, timeout) 772 return self._value 773 else: --> 774 raise self._value

NameError: name 'feature_extractor' is not defined
```

### Steps to reproduce the bug

1. follow the steps in this blog post
https://huggingface.co/blog/fine-tune-whisper

2. run this line of code
`common_voice = common_voice.map(prepare_dataset, remove_columns=common_voice.column_names["train"], num_proc=4)`

3. I'm using jupyter notebook from anaconda

### Expected behavior

No error message

### Environment info

datasets version: 2.8.0
Python version: 3.11
Windows 10