dan
/
fastspeech_squeezewave
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
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.
11 Commits
1 Branch
3.9 MiB
Tree: e9a595cf98
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'e9a595cf98'
${ noResults }
fastspeech_squeezewave/README.md

13 lines
636 B
Raw Normal View History

Create README.md
4 years ago
Update README.md
4 years ago
Create README.md
4 years ago
​
​
​
​
squeezewave model path
4 years ago
​
​
​
​
​
 
  1. # fastspeech_squeezewave

  2. Integration of Fastspeech Text to Mel generation and fast Vocoder Squeezewave ( CPU only)
  3. 

  4. Code from 
  5. https://github.com/xcmyz/FastSpeech
  6. https://github.com/tianrengao/SqueezeWave
  7. 

  8. Put Model in Squeezewave from https://drive.google.com/file/d/1RyVMLY2l8JJGq_dCEAAd8rIRIn_k13UB/view?usp=sharing 
  9. and rename it Squeezewave.pt ( select based on quality and size tradeoff)
  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