chunked/nltk_chunking/tasks_asr/chunk_14.txt

Unlike other data collators, this specific data collator needs to apply a different padding method to input_values and labels:

import torch
from dataclasses import dataclass, field
from typing import Any, Dict, List, Optional, Union
@dataclass
 class DataCollatorCTCWithPadding:
     processor: AutoProcessor
     padding: Union[bool, str] = "longest"

     def call(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
         # split inputs and labels since they have to be of different lengths and need
         # different padding methods
         input_features = [{"input_values": feature["input_values"][0]} for feature in features]
         label_features = [{"input_ids": feature["labels"]} for feature in features]
         batch = self.processor.pad(input_features, padding=self.padding, return_tensors="pt")
         labels_batch = self.processor.pad(labels=label_features, padding=self.padding, return_tensors="pt")
         # replace padding with -100 to ignore loss correctly
         labels = labels_batch["input_ids"].masked_fill(labels_batch.attention_mask.ne(1), -100)
         batch["labels"] = labels
         return batch

Now instantiate your DataCollatorForCTCWithPadding:

data_collator = DataCollatorCTCWithPadding(processor=processor, padding="longest")

Evaluate
Including a metric during training is often helpful for evaluating your model's performance.