ysujiang

anyone can provid tensorboard of finetune taco2?

推理时模型维度报错

3

File "torch_to_onnx.py", line 190, in conver_bert_torch_to_onnx() File "torch_to_onnx.py", line 104, in conver_bert_torch_to_onnx sess = onnxruntime.InferenceSession(MODEL_ONNX_PATH) File "/opt/conda/lib/python3.7/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 335, in __init__ self._create_inference_session(providers, provider_options, disabled_optimizers) File "/opt/conda/lib/python3.7/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 379, in _create_inference_session...

Training multi-speaker

1

Have you trained multi-speaker fre-gan? What is the better config on multi-speaker dataset?

前端预处理问题

8

您好，读了您的文章有两个问题想要请教一下，方便告知吗 1. 请问您得分词工具和词性标注工具用的是什么呢？ 2.您得数据集是自己标注的还是公开的数据集呀？如果是公开数据集可否给出公开数据集的下载网址？

我听生成的样例中，有语速忽快的现象，请问后期有做改进吗

thanks for your work. I tried https://github.com/carlfm01/Tacotron-2/tree/spanish(105k)+https://github.com/MlWoo/LPCNet(10epochs) . No parameters changed ，but the generated samples sound not good .here are my samples and trained steps. for LPCnet, 1. used concat.sh...

合成语音噪声

1

作者您好，非常感谢您在此方面做出的贡献，关于解决合成语音含有噪声的问题，不知您这边是否能给一些的建议？非常期待您的回复。谢谢。

不同的语境下，对应的label不同 例如： 挂牌起始价为七十亿元，n 为_p m,"['NA', 'wei2', 'NA']" 全力为二零一六赛季做好准备 n 为_p m,"['NA', 'wei4', 'NA']" 这种情况是否有做其他的处理

hello, the result of adaspeech is better than fastspeech2?