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.

22 lines
651 B

4 years ago
4 years ago
4 years ago
4 years ago
4 years ago
4 years ago
4 years ago
4 years ago
4 years ago
4 years ago
  1. # fastspeech_squeezewave
  2. Integration of Fastspeech Text to Mel generation and fast Vocoder Squeezewave ( CPU only)
  3. Code from
  4. https://github.com/xcmyz/FastSpeech
  5. https://github.com/tianrengao/SqueezeWave
  6. Put Model in Squeezewave from
  7. https://drive.google.com/file/d/1RyVMLY2l8JJGq_dCEAAd8rIRIn_k13UB/view?usp=sharing
  8. and rename it Squeezewave.pt ( select based on quality and size tradeoff)
  9. ```
  10. -rwxrwxrwx 1 root root 312M Jan 17 05:02 L128_large_pretrain
  11. -rwxrwxrwx 1 root root 97M Jan 17 05:02 L128_small_pretrain
  12. -rwxrwxrwx 1 root root 324M Jan 17 05:01 L64_large_pretrain
  13. -rwxrwxrwx 1 root root 106M Jan 17 05:03 L64_small_pretrain
  14. ```