AlexanderMaz/LanguageModel_Fusion

1---2license: apache-2.03datasets:4- librispeech_asr5language:6- en7metrics:8- wer9pipeline_tag: automatic-speech-recognition10tags:11- asr12- rescoring13- rnn-t14- gpt215- nemo16- lstm17- kenlm18---19 20The data is used in project https://github.com/Alexander92-cpu/LanguageModel_Fusion21 22Data desciption:23 24- 'asr/stt_en_conformer_transducer_small.nemo' - NeMo ASR pre-trained RNN-T model (https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_en_conformer_transducer_small);25 26- 'gpt2' - fine-tuned GPT-2 LM model for rescoring (https://huggingface.co/docs/transformers/model_doc/gpt2#transformers.GPT2LMHeadModel);27 28- 'kenlm/4_ngram_output.bin' - 4-gram language model;29 30- 'lstm' - trained from scratch word-level LSTM LM model and the corresponding tokenizer;31 32- 'text' - contains text data used for training, validation, and testing.33 34- 'optimize' - data and results of optimization experiments35