kaldi-tuda-de
Scripts for training general-purpose large vocabulary German acoustic models for ASR with Kaldi.
파일 탐색기
최종 버전 다운로드 (.zip)- fbank.conf
- mfcc.conf
- mfcc_hires.conf
- online_cmvn.conf
- online_pitch.conf
- decode.config
- decode_dnn.config
- fbank.conf
- mfcc.conf
- mfcc_hires.conf
- no_k20.conf
- online_cmvn.conf
- online_pitch.conf
- pitch.conf
- run_nnet2_common.sh
- run_nnet2_ensemble.sh
- run_nnet2_ms.sh
- run_nnet2_ms_disc.sh
- run_nnet2_ms_perturbed.sh
- build_big_lexicon.py
- build_lm.sh
- build_sampa.py
- common_utils.py
- data_prepare.py
- export_lexicon.py
- format_data.sh
- maryclient.py
- maryfy_corpus.py
- prepare_dir_structure.py
- RemoteException.py
- run_am.sh
- run_dnn.sh
- score.sh
- build_nnet2_dist.sh
- cmd.sh
- decode.sh
- path.sh
- README.md
- RESULTS.me.2015-11-24-11-44-47
- run.sh
- fbank.conf
- mfcc.conf
- mfcc_hires.conf
- online_cmvn.conf
- online_pitch.conf
- decode.config
- decode_dnn.config
- fbank.conf
- mfcc.conf
- mfcc_hires.conf
- no_k20.conf
- online_cmvn.conf
- online_pitch.conf
- pitch.conf
- mary_de.txt
- problematic_wavs.txt
- run_nnet2_common.sh
- run_nnet2_ensemble.sh
- run_nnet2_ms.sh
- run_nnet2_ms_disc.sh
- run_nnet2_ms_perturbed.sh
- build_big_lexicon.py
- build_lm.sh
- build_sampa.py
- common_utils.py
- data_prepare.py
- de_extra_lexicon.txt
- decode_sep_mic_dirs.sh
- export_lexicon.py
- extra_words.txt
- filtered_300k_vocab_de_wiki.txt
- find_oov.py
- format_data.sh
- german_asr_lm_tools
- get_reco2dur.sh
- get_utt2dur.sh
- make_feats.sh
- make_feats_sep_mic_dirs.sh
- make_feats_vm.sh
- make_hires_feats_train.sh
- maryclient.py
- maryfy_corpus.py
- move_files_to_skip.py
- output_normalizer.py
- prepare_commonvoice_data.py
- prepare_dir_structure.py
- prepare_m-ailabs_data.py
- prepare_swc_german_wavscp.py
- prune_fst.sh
- RemoteException.py
- renormalize_datadir_text.py
- run_am.sh
- run_cleanup_segmentation.sh
- run_dnn.sh
- run_ivector_common.sh
- run_tdnn_1f.sh
- run_tdnn_7o.sh
- score.sh
- stopwords.de.txt
- train_rnnlm.sh
- train_rnnlm2.sh
- tuda_files_to_skip.txt
- view_data_length.py
- vm1_createwordlist.py
- vm1_prepare_limited_lang_dir.sh
- vm1_read_corpus.py
- voc_600k.txt
- voc_800k.txt
- wer_hyp_filter
- wer_ref_filter
- build_model_dist_nnet3chain.sh
- build_nnet2_dist.sh
- cleanup.sh
- cmd.sh
- decode.sh
- decode_custom.sh
- decode_train.sh
- path.sh
- redecode.sh
- RESULTS
- RESULTS_tuda_only
- run.sh
- show_results.sh
- .gitignore
- .gitmodules
- LICENSE
- README.md
// repository documentation
Was this content helpful?
(0 ratings)