duplicated block id: 1
size: 32 cleaned lines of code
in 2 files:
 - fairseq/models/speech_to_text/xm_transformer.py (0:0)
 - fairseq/models/speech_to_text/s2t_transformer.py (0:0)

duplicated block id: 2
size: 24 cleaned lines of code
in 2 files:
 - fairseq/benchmark/dummy_masked_lm.py (0:0)
 - fairseq/benchmark/dummy_lm.py (0:0)

duplicated block id: 3
size: 17 cleaned lines of code
in 2 files:
 - fairseq/tasks/fairseq_task.py (0:0)
 - fairseq/tasks/translation_multi_simple_epoch.py (0:0)

duplicated block id: 4
size: 14 cleaned lines of code
in 2 files:
 - fairseq/models/lightconv.py (0:0)
 - fairseq/model_parallel/models/pipeline_parallel_transformer/layers.py (0:0)

duplicated block id: 5
size: 15 cleaned lines of code
in 2 files:
 - fairseq/criterions/speech_to_speech_criterion.py (0:0)
 - fairseq/criterions/speech_to_speech_criterion.py (0:0)

duplicated block id: 6
size: 13 cleaned lines of code
in 3 files:
 - fairseq/models/speech_to_text/convtransformer.py (0:0)
 - fairseq/models/speech_to_text/xm_transformer.py (0:0)
 - fairseq/models/speech_to_text/s2t_transformer.py (0:0)

duplicated block id: 7
size: 12 cleaned lines of code
in 2 files:
 - fairseq/models/transformer/transformer_decoder.py (0:0)
 - fairseq/models/text_to_speech/tts_transformer.py (0:0)

duplicated block id: 8
size: 11 cleaned lines of code
in 2 files:
 - fairseq/models/wav2vec/wav2vec2_asr.py (0:0)
 - fairseq/model_parallel/models/pipeline_parallel_transformer/model.py (0:0)

duplicated block id: 9
size: 12 cleaned lines of code
in 2 files:
 - fairseq/tasks/language_modeling.py (0:0)
 - fairseq/tasks/multilingual_language_modeling.py (0:0)

duplicated block id: 10
size: 10 cleaned lines of code
in 2 files:
 - fairseq/models/speech_to_speech/s2s_transformer.py (0:0)
 - fairseq/models/transformer/transformer_decoder.py (0:0)

duplicated block id: 11
size: 10 cleaned lines of code
in 2 files:
 - fairseq/data/audio/speech_to_text_dataset.py (0:0)
 - fairseq/data/audio/text_to_speech_dataset.py (0:0)

duplicated block id: 12
size: 8 cleaned lines of code
in 2 files:
 - fairseq/models/speech_to_text/modules/emformer.py (0:0)
 - fairseq/models/speech_to_text/modules/emformer.py (0:0)

duplicated block id: 13
size: 8 cleaned lines of code
in 2 files:
 - fairseq/models/text_to_speech/fastspeech2.py (0:0)
 - fairseq/models/text_to_speech/tts_transformer.py (0:0)

duplicated block id: 14
size: 8 cleaned lines of code
in 2 files:
 - fairseq/models/lightconv.py (0:0)
 - fairseq/models/lightconv.py (0:0)

duplicated block id: 15
size: 7 cleaned lines of code
in 2 files:
 - fairseq/models/speech_to_text/convtransformer.py (0:0)
 - fairseq/models/transformer/transformer_decoder.py (0:0)

duplicated block id: 16
size: 7 cleaned lines of code
in 2 files:
 - fairseq/models/roberta/model.py (0:0)
 - fairseq/model_parallel/models/roberta/model.py (0:0)

duplicated block id: 17
size: 12 cleaned lines of code
in 2 files:
 - fairseq/model_parallel/models/pipeline_parallel_transformer/layers.py (0:0)
 - fairseq/modules/transformer_layer.py (0:0)

duplicated block id: 18
size: 7 cleaned lines of code
in 2 files:
 - fairseq/checkpoint_utils.py (0:0)
 - fairseq/checkpoint_utils.py (0:0)

duplicated block id: 19
size: 7 cleaned lines of code
in 2 files:
 - fairseq/modules/downsampled_multihead_attention.py (0:0)
 - fairseq/modules/downsampled_multihead_attention.py (0:0)

duplicated block id: 20
size: 7 cleaned lines of code
in 2 files:
 - fairseq/criterions/tacotron2_loss.py (0:0)
 - fairseq/criterions/speech_to_speech_criterion.py (0:0)

duplicated block id: 21
size: 6 cleaned lines of code
in 2 files:
 - fairseq/tasks/language_modeling.py (0:0)
 - fairseq/tasks/multilingual_language_modeling.py (0:0)

duplicated block id: 22
size: 6 cleaned lines of code
in 2 files:
 - fairseq/ngram_repeat_block.py (0:0)
 - fairseq/ngram_repeat_block.py (0:0)

duplicated block id: 23
size: 6 cleaned lines of code
in 2 files:
 - fairseq/models/speech_to_speech/s2s_transformer.py (0:0)
 - fairseq/models/transformer/transformer_decoder.py (0:0)

duplicated block id: 24
size: 6 cleaned lines of code
in 2 files:
 - fairseq/models/speech_to_text/xm_transformer.py (0:0)
 - fairseq/models/speech_to_text/s2t_transformer.py (0:0)

duplicated block id: 25
size: 6 cleaned lines of code
in 2 files:
 - fairseq/models/roberta/model_xlmr.py (0:0)
 - fairseq/models/roberta/model_camembert.py (0:0)

duplicated block id: 26
size: 6 cleaned lines of code
in 2 files:
 - fairseq/model_parallel/megatron_trainer.py (0:0)
 - fairseq/trainer.py (0:0)

duplicated block id: 27
size: 6 cleaned lines of code
in 2 files:
 - fairseq/search.py (0:0)
 - fairseq/search.py (0:0)

duplicated block id: 28
size: 6 cleaned lines of code
in 2 files:
 - fairseq/file_io.py (0:0)
 - fairseq/file_io.py (0:0)

duplicated block id: 29
size: 8 cleaned lines of code
in 2 files:
 - fairseq/data/subsample_dataset.py (0:0)
 - fairseq/data/monolingual_dataset.py (0:0)

duplicated block id: 30
size: 6 cleaned lines of code
in 2 files:
 - fairseq/data/prepend_token_dataset.py (0:0)
 - fairseq/data/append_token_dataset.py (0:0)

duplicated block id: 31
size: 6 cleaned lines of code
in 2 files:
 - fairseq/criterions/label_smoothed_cross_entropy.py (0:0)
 - fairseq/criterions/speech_to_speech_criterion.py (0:0)

duplicated block id: 32
size: 8 cleaned lines of code
in 3 files:
 - fairseq/tasks/multilingual_denoising.py (0:0)
 - fairseq/tasks/multilingual_language_modeling.py (0:0)
 - fairseq/tasks/multilingual_masked_lm.py (0:0)

duplicated block id: 33
size: 7 cleaned lines of code
in 2 files:
 - fairseq/tasks/sentence_prediction.py (0:0)
 - fairseq/tasks/sentence_ranking.py (0:0)

duplicated block id: 34
size: 6 cleaned lines of code
in 12 files:
 - fairseq/model_parallel/criterions/vocab_parallel_cross_entropy.py (0:0)
 - fairseq/criterions/cross_entropy.py (0:0)
 - fairseq/criterions/ctc.py (0:0)
 - fairseq/criterions/adaptive_loss.py (0:0)
 - fairseq/criterions/model_criterion.py (0:0)
 - fairseq/criterions/legacy_masked_lm.py (0:0)
 - fairseq/criterions/nat_loss.py (0:0)
 - fairseq/criterions/label_smoothed_cross_entropy.py (0:0)
 - fairseq/criterions/sentence_prediction.py (0:0)
 - fairseq/criterions/label_smoothed_cross_entropy_with_alignment.py (0:0)
 - fairseq/criterions/masked_lm.py (0:0)
 - fairseq/criterions/sentence_ranking.py (0:0)

duplicated block id: 35
size: 6 cleaned lines of code
in 3 files:
 - fairseq/criterions/fairseq_criterion.py (0:0)
 - fairseq/criterions/hubert_criterion.py (0:0)
 - fairseq/criterions/speech_to_speech_criterion.py (0:0)