Xin Xin

update to py3.5 and tf 1.9.0

4

Update the original version of code to py3.5.3 and tensorflow_gpu 1.9.0

For song vc what should I do

9

Hello and thank you sharing your great work, but I have some questions. 1. For song vc with Madarian, I tried train a new starganv2vc model with pretrained ASR and...

Librispeech and Buckeye train infer with bad case

1

Hello, and thank you for your sharing. This time I use Librispeech and Buckeye for training and 20 dataset from ljspeech for inference but i find that the time align...

您好， 感谢您的工作和分享，但是README中频道码现在不能用了，请问怎么能够下载预训练模型吗？谢谢，期待您的回复。

Hello, sir. Thank you for you sharing your great works. And after training my TTS model, I find a weird voice during inference . I use chinese dataset for training,...

May has a bug in save_to_wav_file

1

Hello, I'm using azure tts servuce with python. When I finish one inference with speechsdk, and then I want to save to file, I get the following error.  stream...

ECAPA-TDNN voice clone 问题

2

您好感谢你们公开的工作，不过有个问题想请教下。我在尝试examples/aishell3/vc2 TCAPA-TDNN的voice clone时，我直接跑了run.sh中voice_clone这部。我使用的测试src是我自己的原声（男声），但是tts出来的结果竟然是女声。我使用的都是预训练模型。请问这是不是spk_embedding有问题也就是tcapa-tdnn提取的有问题。

请问vad在多进程会卡主要怎么解决呢？ ```python def post_process(vad_model, refWavPath: str, svcWav: str): """_summary_ Args: ref_wave_path (str): Path of ref audio. svc_wave_path (str): Path of svc audio. Returns: _type_: _description_ """ ref_wave, _ = librosa.load(refWavPath,...