Zhao

Update patch error

2

Error when updating the patch error: Failed to patch: src/cudamatrix/cu-matrix.h:693 Error: src/cudamatrix/cu-matrix.h: Patch not applied What are the reasons for this?thanks

Hi, thanks to the implement. How to add PQMF module in Generator(istftnet) to realize inference speedup? thx!

用文章上提到的预训练模型，.pth 文件和一个Tacotron 生成的 .npy 文件。 执行命令 ：python synthesis.py ./checkpoint_biaobei-36Khz/checkpoint_biaobei-36Khz.pth ./out --conditional=mel-prediction-step-100000.npy Traceback (most recent call last): File "synthesis.py", line 212, in args = docopt(__doc__) File "/home/xxx/lib/python3.6/site-packages/docopt-0.6.2-py3.6.egg/docopt.py", line 558, in docopt...

如题所示，如何优化内存占用，从哪方面下手

Thank you for sharing, the results I got in the experiment using data（Chinese Standard Mandarin Speech Copus） is poor, is it the align problem? mfa train corpus ./mono.dict ./textgrid corpus...

convert onnnx model

1

Thank you for your excellent work， How to export Pytorch model in ONNX format？thx

性能

3

使用chrono时间库 root@d255e0717767:/tmp_workspace/SummerTTS-main/build# ./tts_test ../test.txt ../models/single_speaker_big.bin out.wav ttsLoadModel cost time = 110ms new Synthesizer cost time = 68ms infer synthesizer cost time = 42259ms root@d255e0717767:/tmp_workspace/SummerTTS-main/build# ./tts_test ../test.txt ../models/single_speaker_medium.bin out.wav ttsLoadModel cost...