tensorflow_end2end_speech_recognition
End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)
File Explorer
Download Latest Version (.zip)- en_blstm_de_lstm_kanji_subset_dot_product.yml
- blstm_ctc_kana_fullset.yml
- blstm_ctc_kana_subset.yml
- blstm_ctc_kanji_fullset.yml
- blstm_ctc_kanji_subset.yml
- hierarchical_blstmctc_kanji_char_stack3.yml
- hierarchical_blstmctc_kanji_char_stack3_large.yml
- hierarchical_blstmctc_kanji_phone_stack3.yml
- hierarchical_blstmctc_kanji_phone_stack3_large.yml
- test_load_dataset_attention.py
- test_load_dataset_ctc.py
- test_load_dataset_multitask_ctc.py
- load_dataset_attention.py
- load_dataset_ctc.py
- load_dataset_multitask_ctc.py
- eval_ctc.py
- eval_julius_cer.py
- eval_julius_fmeasure.py
- run_ctc.sh
- finetune_ctc_dialog.py
- run_finetune_ctc_dialog.sh
- kana.txt
- kana2phone.txt
- kana_divide.txt
- kanji_divide_train_fullset.txt
- kanji_divide_train_subset.txt
- kanji_train_fullset.txt
- kanji_train_subset.txt
- __init__.py
- attention.py
- ctc.py
- run_attention.sh
- run_ctc.sh
- run_multitask_ctc.sh
- train_attention.py
- train_ctc.py
- train_multitask_ctc.py
- ctc.py
- decode_ctc.py
- plot_ctc_posterior.py
- en_blstm_de_lstm_insert_both_dot_product.yml
- en_blstm_de_lstm_insert_left_dot_product.yml
- en_blstm_de_lstm_insert_right_dot_product.yml
- en_blstm_de_lstm_remove_dot_product.yml
- blstm_ctc_insert_both.yml
- blstm_ctc_insert_left.yml
- blstm_ctc_insert_right.yml
- blstm_ctc_remove.yml
- test_load_dataset_attention.py
- test_load_dataset_ctc.py
- load_dataset_attention.py
- load_dataset_ctc.py
- eval_attention.py
- eval_ctc.py
- eval_julius.py
- kana_insert_both.txt
- kana_insert_left.txt
- kana_insert_right.txt
- kana_remove.txt
- attention.py
- ctc.py
- run_attention.sh
- run_ctc.sh
- train_attention.py
- train_ctc.py
- decode_attention.py
- decode_ctc.py
- plot_ctc_posterior.py
- blstm_ctc_100h_char.yml
- blstm_ctc_100h_char_faster.yml
- blstm_ctc_460h_char.yml
- blstm_ctc_460h_char_faster.yml
- blstm_ctc_960h_char.yml
- blstm_ctc_960h_char_faster.yml
- blstm_ctc_100h_char_capital.yml
- blstm_ctc_100h_char_capital_faster.yml
- blstm_ctc_460h_char_capital.yml
- blstm_ctc_460h_char_capital_faster.yml
- blstm_ctc_960h_char_capital.yml
- blstm_ctc_960h_char_capital_faster.yml
- blstm_ctc_100h_word_faster.yml
- blstm_ctc_460h_word_faster.yml
- blstm_ctc_960h_word_faster.yml
- hierarchical_blstm_ctc_train100h_word_char_faster.yml
- hierarchical_blstm_ctc_train960h_word_char_faster.yml
- student_cnn_compact_xe_100h_char.yml
- test_load_dataset_ctc.py
- test_load_dataset_multitask_ctc.py
- test_load_dataset_xe.py
- load_dataset_ctc.py
- load_dataset_multitask_ctc.py
- load_dataset_xe.py
- eval_ctc.py
- eval_ctc_temp.py
- eval_ensemble2_ctc.py
- eval_ensemble4_ctc.py
- eval_ensemble8_ctc.py
- eval_multitask_ctc.py
- eval_student.py
- run_ctc.sh
- run_ctc_temp.sh
- run_ensemble2_blstmctc.sh
- run_ensemble4_blstmctc.sh
- run_ensemble8_blstmctc.sh
- run_multitask_ctc.sh
- run_save.sh
- run_student.sh
- save_ctc_prob.py
- character.txt
- character_capital_divide_train100h.txt
- character_capital_divide_train460h.txt
- character_capital_divide_train960h.txt
- word_freq10_train100h.txt
- word_freq10_train460h.txt
- word_freq10_train960h.txt
- ctc.py
- run_ctc.sh
- run_ctc_temp.sh
- run_multitask_ctc.sh
- run_student_cnn_xe.sh
- train_ctc.py
- train_ctc_temp.py
- train_multitask_ctc.py
- train_student_cnn_xe.py
- __init__.py
- ctc.py
- __init__.py
- decode_ctc.py
- decode_multitask_ctc.py
- plot_ctc_prob.py
- en_blstm_de_lstm_phone43_dot_product.yml
- blstm_ctc_phone3.yml
- blstm_ctc_phone4.yml
- blstm_ctc_phone43.yml
- test_load_dataset_attention.py
- test_load_dataset_ctc.py
- __init__.py
- load_dataset_attention.py
- load_dataset_ctc.py
- __init__.py
- ctc.sh
- restore_ctc.py
- restore_ff.py
- visualize_ctc.py
- __init__.py
- eval_framewise.py
- metric.py
- phone3.txt
- phone4.txt
- phone43.txt
- attention.py
- ctc.py
- run_attention.sh
- run_ctc.sh
- train_attention.py
- train_ctc.py
- __init__.py
- decode_ctc.py
- probs.py
- att_blstm_content.yml
- att_blstm_dot.yml
- att_cnn_location.yml
- att_dense_residual_blstm_location.yml
- att_residual_blstm_location.yml
- att_vgg_blstm_location.yml
- att_blstm_location_logits_temp.yml
- att_blstm_location_ls.yml
- att_blstm_location_sharping.yml
- att_blstm_location_weight_noise.yml
- att_lstm_location_sigmoid_smoothing.yml
- att_baseline.yml
- cnn_ctc.yml
- dense_residual_blstm_ctc.yml
- residual_blstm_ctc.yml
- vgg_blstm_ctc.yml
- blstm_ctc_ls.yml
- blstm_ctc_subsample.yml
- blstm_ctc_weight_noise.yml
- blstm_ctc_baseline.yml
- __init__.py
- test_load_dataset_attention.py
- test_load_dataset_ctc.py
- test_load_dataset_joint_ctc_attention.py
- test_load_dataset_multitask_ctc.py
- __init__.py
- load_dataset_attention.py
- load_dataset_ctc.py
- load_dataset_joint_ctc_attention.py
- load_dataset_multitask_ctc.py
- __init__.py
- eval_attention.py
- eval_ctc.py
- eval_multitask_ctc.py
- character.txt
- character_capital_divide.txt
- phone2phone.txt
- phone39.txt
- phone48.txt
- phone61.txt
- __init__.py
- attention.py
- ctc.py
- mapping.py
- run_attention.sh
- run_ctc.sh
- train_attention.py
- train_ctc.py
- train_joint_ctc_attention.py
- train_multitask_ctc.py
- __init__.py
- __init__.py
- decode_attention.py
- decode_ctc.py
- decode_multitask_ctc.py
- plot_attention_weights.py
- plot_ctc_prob.py
- plot_multitask_ctc_prob.py
- __init__.py
- README.md
- save_ctc_prob.py
- plot_ctc_prob.py
- beam_search_decoder.py
- namedtuple.py
- util.py
- __init__.py
- attention_decoder.py
- attention_layer.py
- beam_search_decoder_from_tensorflow.py
- decoder_util.py
- dynamic_decoder.py
- __init__.py
- attention_seq2seq.py
- bridge.py
- joint_ctc_attention.py
- ListenAttendandSpell.py
- __init__.py
- beam_search_decoder.py
- charlm_beam_search_decoder.py
- greedy_decoder.py
- __init__.py
- bn_blstm_ctc.py
- ctc.py
- multitask_ctc.py
- student_ctc.py
- __init__.py
- blstm.py
- cldnn_wang.py
- cnn_util.py
- cnn_zhang.py
- gru.py
- lstm.py
- multitask_blstm.py
- multitask_lstm.py
- pyramidal_blstm.py
- rnn_util.py
- student_cnn_compact_ctc.py
- student_cnn_compact_xe.py
- student_cnn_ctc.py
- student_cnn_xe.py
- vgg_blstm.py
- vgg_lstm.py
- vgg_wang.py
- __init__.py
- load_encoder.py
- __init__.py
- base.py
- char_rnnlm.py
- word_rnnlm.py
- __init__.py
- basic_lstm.py
- batch_normalization.py
- bn_basic_lstm.py
- bn_lstm.py
- lstm.py
- qrnn.py
- test_tf_qrnn_forward.py
- test_tf_qrnn_work.py
- __init__.py
- initializer.py
- LDC93S1.phn
- LDC93S1.txt
- LDC93S1.wrd
- __init__.py
- data.py
- install_sample.sh
- phone61.txt
- run_attention.sh
- run_ctc.sh
- run_joint_ctc_attention.sh
- run_multitask_ctc.sh
- test_attention.py
- test_ctc.py
- test_ctc_decoder.py
- test_encoder.py
- test_joint_ctc_attention.py
- test_multitask_ctc.py
- __init__.py
- model_base.py
- README.md
- __init__.py
- attention.py
- base.py
- ctc.py
- joint_ctc_attention.py
- multitask_ctc.py
- xe.py
- __init__.py
- edit_distance.py
- __init__.py
- feature_extraction.py
- frame_stacking.py
- splicing.py
- __init__.py
- character.py
- phone.py
- sparsetensor.py
- word.py
- __init__.py
- __init__.py
- learning_rate_controller.py
- multi_gpu.py
- plot.py
- __init__.py
- directory.py
- measure_time_func.py
- parallel.py
- parameter.py
- progressbar.py
- .gitignore
- LICENSE
- README.md
- requirements.txt
// repository documentation
Was this content helpful?
(0 ratings)