Add Language Model Decoder

Closes #142 (closed)

Taking over from !222 (closed)

dan/ocr/decoder.py

@@ -516,8 +516,6 @@ class CTCLanguageDecoder:
         Add CTC frames between each characters to avoid duplicate removal
         """
         batch_size, _, n_tokens = batch_features.shape
-        torch.clone(batch_features)
-        # visualize_debug(batch_features.exp()[0, :batch_frames[0], :].numpy(), "probs.jpg", False)
 
         # Create tensor with high probability CTC token
         high_prob = 0.99