Python-在5秒内克隆语音以实时生成任意语音

[{"title":"（ 73 个子文件 123KB ） Python-在5秒内克隆语音以实时生成任意语音","children":[{"title":"Real-Time-Voice-Cloning-master","children":[{"title":"encoder","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"inference.py <span style='color:#111;'> 7.67KB </span>","children":null,"spread":false},{"title":"config.py <span style='color:#111;'> 1.11KB </span>","children":null,"spread":false},{"title":"params_data.py <span style='color:#111;'> 901B </span>","children":null,"spread":false},{"title":"data_objects","children":[{"title":"utterance.py <span style='color:#111;'> 855B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 181B </span>","children":null,"spread":false},{"title":"random_cycler.py <span style='color:#111;'> 1.35KB </span>","children":null,"spread":false},{"title":"speaker_verification_dataset.py <span style='color:#111;'> 2.10KB </span>","children":null,"spread":false},{"title":"speaker.py <span style='color:#111;'> 1.79KB </span>","children":null,"spread":false},{"title":"speaker_batch.py <span style='color:#111;'> 616B </span>","children":null,"spread":false}],"spread":true},{"title":"visualizations.py <span style='color:#111;'> 6.50KB </span>","children":null,"spread":false},{"title":"preprocess.py <span style='color:#111;'> 7.48KB </span>","children":null,"spread":false},{"title":"params_model.py <span style='color:#111;'> 196B </span>","children":null,"spread":false},{"title":"audio.py <span style='color:#111;'> 4.31KB </span>","children":null,"spread":false},{"title":"model.py <span style='color:#111;'> 6.14KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 4.98KB </span>","children":null,"spread":false}],"spread":false},{"title":".gitignore <span style='color:#111;'> 206B </span>","children":null,"spread":false},{"title":"demo_cli.py <span style='color:#111;'> 8.85KB </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 180B </span>","children":null,"spread":false},{"title":"synthesizer_preprocess_audio.py <span style='color:#111;'> 1.81KB </span>","children":null,"spread":false},{"title":"vocoder","children":[{"title":"models","children":[{"title":"fatchord_version.py <span style='color:#111;'> 14.06KB </span>","children":null,"spread":false},{"title":"deepmind_version.py <span style='color:#111;'> 6.85KB </span>","children":null,"spread":false}],"spread":true},{"title":"hparams.py <span style='color:#111;'> 1.78KB </span>","children":null,"spread":false},{"title":"inference.py <span style='color:#111;'> 1.59KB </span>","children":null,"spread":false},{"title":"distribution.py <span style='color:#111;'> 4.69KB </span>","children":null,"spread":false},{"title":"LICENSE.txt <span style='color:#111;'> 1.16KB </span>","children":null,"spread":false},{"title":"audio.py <span style='color:#111;'> 2.15KB </span>","children":null,"spread":false},{"title":"display.py <span style='color:#111;'> 2.65KB </span>","children":null,"spread":false},{"title":"gen_wavernn.py <span style='color:#111;'> 985B </span>","children":null,"spread":false},{"title":"vocoder_dataset.py <span style='color:#111;'> 3.04KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 4.34KB </span>","children":null,"spread":false}],"spread":true},{"title":"demo_toolbox.py <span style='color:#111;'> 1.60KB </span>","children":null,"spread":false},{"title":"LICENSE.txt <span style='color:#111;'> 1.32KB </span>","children":null,"spread":false},{"title":"demo_toolbox_collab.ipynb <span style='color:#111;'> 3.93KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"profiler.py <span style='color:#111;'> 1.44KB </span>","children":null,"spread":false},{"title":"logmmse.py <span style='color:#111;'> 8.97KB </span>","children":null,"spread":false},{"title":"argutils.py <span style='color:#111;'> 1.14KB </span>","children":null,"spread":false}],"spread":true},{"title":"synthesizer_train.py <span style='color:#111;'> 2.86KB </span>","children":null,"spread":false},{"title":"encoder_train.py <span style='color:#111;'> 2.29KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 4.43KB </span>","children":null,"spread":false},{"title":"vocoder_train.py <span style='color:#111;'> 2.83KB </span>","children":null,"spread":false},{"title":"synthesizer_preprocess_embeds.py <span style='color:#111;'> 1.17KB </span>","children":null,"spread":false},{"title":"encoder_preprocess.py <span style='color:#111;'> 2.74KB </span>","children":null,"spread":false},{"title":"synthesizer","children":[{"title":"__init__.py <span style='color:#111;'> 1B </span>","children":null,"spread":false},{"title":"models","children":[{"title":"architecture_wrappers.py <span style='color:#111;'> 8.17KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 174B </span>","children":null,"spread":false},{"title":"tacotron.py <span style='color:#111;'> 28.67KB </span>","children":null,"spread":false},{"title":"custom_decoder.py <span style='color:#111;'> 4.71KB </span>","children":null,"spread":false},{"title":"attention.py <span style='color:#111;'> 8.86KB </span>","children":null,"spread":false},{"title":"modules.py <span style='color:#111;'> 21.81KB </span>","children":null,"spread":false},{"title":"helpers.py <span style='color:#111;'> 5.85KB </span>","children":null,"spread":false}],"spread":false},{"title":"hparams.py <span style='color:#111;'> 19.54KB </span>","children":null,"spread":false},{"title":"inference.py <span style='color:#111;'> 5.72KB </span>","children":null,"spread":false},{"title":"synthesize.py <span style='color:#111;'> 3.55KB </span>","children":null,"spread":false},{"title":"LICENSE.txt <span style='color:#111;'> 1.17KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"plot.py <span style='color:#111;'> 2.15KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 444B </span>","children":null,"spread":false},{"title":"symbols.py <span style='color:#111;'> 633B </span>","children":null,"spread":false},{"title":"cleaners.py <span style='color:#111;'> 2.36KB </span>","children":null,"spread":false},{"title":"_cmudict.py <span style='color:#111;'> 1.88KB </span>","children":null,"spread":false},{"title":"numbers.py <span style='color:#111;'> 2.07KB </span>","children":null,"spread":false},{"title":"text.py <span style='color:#111;'> 2.11KB </span>","children":null,"spread":false}],"spread":false},{"title":"tacotron2.py <span style='color:#111;'> 11.64KB </span>","children":null,"spread":false},{"title":"preprocess.py <span style='color:#111;'> 10.28KB </span>","children":null,"spread":false},{"title":"audio.py <span style='color:#111;'> 7.60KB </span>","children":null,"spread":false},{"title":"infolog.py <span style='color:#111;'> 1.23KB </span>","children":null,"spread":false},{"title":"feeder.py <span style='color:#111;'> 11.30KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 20.41KB </span>","children":null,"spread":false}],"spread":false},{"title":"toolbox","children":[{"title":"utterance.py <span style='color:#111;'> 222B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 10.23KB </span>","children":null,"spread":false},{"title":"ui.py <span style='color:#111;'> 19.57KB </span>","children":null,"spread":false}],"spread":false},{"title":"vocoder_preprocess.py <span style='color:#111;'> 1.93KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]