Added: - new documentation - demo in the documentation - extra API endpoints (yet to be documented) - voice notification on change of model or setting - DeepSpeed update to v11.x and re-documented - improved vocab bringing the XTTSv2 model closer to sounding like the sample, with improved pronunciation and intonation.
18 lines
642 B
Plaintext
18 lines
642 B
Plaintext
These are the modified files you would need for a MANUAL build of DeepSpeed 11.1 or 11.2.
|
|
|
|
They were created by a mix of instructions from erew123 and S95Sedan.
|
|
|
|
|
|
- You still have to download the DeepSpeed v11.1 or v11.2 installation files from Microsoft to use these files.
|
|
|
|
https://github.com/microsoft/DeepSpeed/releases/tag/v0.11.2
|
|
|
|
|
|
- These files were provided by S95Sedan here:
|
|
|
|
https://github.com/S95Sedan/Deepspeed-Windows
|
|
|
|
|
|
- They are related to the manual build of DeepSpeed for AllTalk, which is linked here:
|
|
|
|
https://github.com/erew123/alltalk_tts/tree/main?tab=readme-ov-file#-option-2---a-bit-more-complicated |