Fork of https://github.com/alokprasad/fastspeech_squeezewave to also fix denoising in squeezewave
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
651 B
651 B
fastspeech_squeezewave
Integration of Fastspeech Text to Mel generation and fast Vocoder Squeezewave ( CPU only)
Code from
https://github.com/xcmyz/FastSpeech
https://github.com/tianrengao/SqueezeWave
Put Model in Squeezewave from
https://drive.google.com/file/d/1RyVMLY2l8JJGq_dCEAAd8rIRIn_k13UB/view?usp=sharing
and rename it Squeezewave.pt ( select based on quality and size tradeoff)
-rwxrwxrwx 1 root root 312M Jan 17 05:02 L128_large_pretrain
-rwxrwxrwx 1 root root 97M Jan 17 05:02 L128_small_pretrain
-rwxrwxrwx 1 root root 324M Jan 17 05:01 L64_large_pretrain
-rwxrwxrwx 1 root root 106M Jan 17 05:03 L64_small_pretrain