文件名称：multi_speaker_tts:多扬声器TTS的实现
文件大小：58KB
文件格式：ZIP
更新时间：2024-06-19 13:42:23
Python
多扬声器 TTS 此代码是论文 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis' 的实现，除了 'WAVENET' 。 该算法基于以下论文： Wang, Y., Skerry-Ryan, R. J., Stanton, D., Wu, Y., Weiss, R. J., Jaitly, N., ... & Le, Q. (2017). Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135. Wan, L., Wang, Q., Papir, A., & Moreno, I. L. (2017). Generalized end-to-end loss for
【文件预览】：
multi_speaker_tts-master
----Pattern_Generate.py(17KB)
----Instruction.txt(2KB)
----Inference_Sentence_in_Train.txt(448B)
----requirements.txt(37B)
----Speaker_Embedding()
--------Pattern_Generate.py(7KB)
--------Speaker_Embedding.py(9KB)
--------Feeder.py(8KB)
--------Modules.py(7KB)
----WaveGlow_Inference_File_Path_in_Train.txt(263B)
----Mel_to_Spect_Inference_in_Train.txt(94B)
----Hyper_Parameters.py(8KB)
----Feeder.py(12KB)
----Taco1_Mel_to_Spect()
--------Pattern_Generate.py(5KB)
--------Taco1_Mel_to_Spect.py(8KB)
--------Feeder.py(7KB)
--------Modules.py(5KB)
----ZoneoutLSTMCell.py(12KB)
----README.md(7KB)
----Token_Index_Dict.json(586B)
----Speaker_Embedding_Inference_in_Train.txt(47KB)
----Location_Sensitive_Attention.py(4KB)
----MSTTS_SV.py(24KB)
----Modules.py(17KB)
----Audio.py(5KB)
----WaveGlow()
--------WaveGlow.py(9KB)
--------Feeder.py(8KB)
--------Modules.py(15KB)
--------Inv1x1.py(2KB)