tacotron
tacotron copied to clipboard
keithito
A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
Hi all. _This project is very interesting, and I'd like to create a french voice for ubuntu (ubuntu is very poor in french male TTS_) - how many wav sentences...
i run this train.py in tensorflow 1.12.0 ,but this have an error : 2019-07-24 11:12:20.997008: E tensorflow/stream_executor/cuda/cuda_dnn.cc:363] Loaded runtime CuDNN library: 7.0.3 but source was compiled with: 7.1.4. CuDNN library...
As I understand ljspeech dataset is originally an audiobook, how it was prepared? i.e. what tools were used to cut it to single sentences? Is it possible to use this...
Here are two examples of a 500000 training step model, one good and one bad (whistling and echo): https://www.dropbox.com/sh/olasdvxvjgbgi4m/AADFt3R5Gi9EJg4Qy3WJrHP1a?dl=0 How to achieve more consistent synthesis, what am I doing wrong?...
I was wondering why this pipeline didn't have an evaluation function to get validation loss to check for overfitting. Or is it there and did i miss it?
Hi @keithito ! In the multispeaker branch, I wonder why the speaker_ids embedding size is set to 377 ? Is this the result of a particular tuning or is it...
(tensorflow) wtx@wtx-Vostro-230:~/tacotron$ python preprocess_zh.py --dataset ljspeech 0%| | 0/13100 [00:00
Hello!! I have been testing a model with my voice. The voice is very clear and has the same properties as the example voice in spanish that works The problem...
I have added a data set generated for urdu language and made changes to the preprocess.py, added a file urdu.py in datasets and changed the symbols.py. When I run preprocess.py...
1.python3的版本号有确定是3.x ? 2.我用conda 工具从tensorflow-gpu1.3.0 尝试到tensorflow-gpu1.12.0 都有问题 3.能不能给下你的版本信息 我checkout的是https://github.com/begeekmyfriend/tacotron 的mandarin 分支 @[email protected]
