提交 d592f252 编写于 作者: 小湉湉's avatar 小湉湉

add onnx inference for fastspeech2 + hifigan/mb_melgan, test=tts

上级 7aecb2c4
train_output_path=$1
stage=1
stop_stage=1
stage=0
stop_stage=0
# only support default_fastspeech2 + hifigan now!
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册