style-token_tacotron2

style-token_tacotron2 copied to clipboard

Bumps [scipy](https://github.com/scipy/scipy) from 1.0.0 to 1.10.0. Release notes Sourced from scipy's releases. SciPy 1.10.0 Release Notes SciPy 1.10.0 is the culmination of 6 months of hard work. It contains many...

dependabot[bot]

Bumps [numpy](https://github.com/numpy/numpy) from 1.14.0 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

作者您好！ 您用THCHS-30数据集的全部说话人训练的Tacotron模型吗？ 我之前只用过标贝单人数据集训练Tacotron，想请教一下多说话人需要什么设置？在hpamars里也没看到您关于speakers的设置。 感谢！～

yannier912

无法生成正确的音频

1

你好，我运行了你的代码，将tacotron_batch_size改成了48，outputs_per_step改为3，但是输出在80000代时仍未对齐； 同时，我在训练仍未结束时测试synthesize，得到的确是1:14时常的wav，里面几乎全是杂音，这是错误提示 > Loading checkpoint: logs-Tacotron-2/taco_pretrained/tacotron_model.ckpt-80000 WARNING:tensorflow:From /home/lyj/code/style-token-chinese/tacotron/synthesizer.py:63: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead. 2020-10-07 17:29:27.822125: W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar...

EmptyMoon-hub

the trained model generates different wavs with the same text and reference audio

15

When doing tests, I found each time I ran the synthesize.py(with the same text and reference audio), I got different results(namely different syntheized wavs). After looking up the code, I...

MorganCZY

中文数据处理

8

您好，我想问一下，按照您代码里默认的数据处理方法，得到的thchs30的文本是中文汉子，是否应该在train之前手动改成拼音序列呢？拼音序列的话是取wav.trn的第二行还是第三行比较好呢？ 例如 C20_717.wav.trn 内容如下： 她 还 去 看 整容 医生 把 鼻子 也 改变 了 结果 却 认为 自己 比 整容 以前 更 丑 所以 很 懊丧 ta1 hai2 qu4...

CathyW77

i just working on tts lately,especially on chinese corpus , and I found [begeekmyfriend] (https://github.com/begeekmyfriend/Tacotron-2/tree/mandarin-griffin-lim) done the great job.Btw,how to use you utils to preprocess the biaobei corpus

alenweiru