Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Xtts v2 truss #65

Merged
merged 12 commits into from
Dec 4, 2023
+162 −0
Merged

Xtts v2 truss #65

Changes from 3 commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
0f6f82d
WIP
Nov 10, 2023
cdafa02
testing things
htrivedi99 Nov 17, 2023
f58766a
Update README.md
htrivedi99 Nov 17, 2023
794059d
Update README.md
htrivedi99 Nov 17, 2023
b82129f
removing unnecessary audio file
htrivedi99 Nov 17, 2023
e8095ba
Merge branch 'xtts-v2-truss' of github.com:htrivedi99/truss-examples …
htrivedi99 Nov 17, 2023
729aedd
Merge branch 'basetenlabs:main' into xtts-v2-truss
htrivedi99 Nov 17, 2023
6a6e004
Merge branch 'xtts-v2-truss' of github.com:htrivedi99/truss-examples …
htrivedi99 Nov 17, 2023
e4a43b8
Delete xtts-v2-truss/samuel_jackson_voice.mp4
htrivedi99 Nov 17, 2023
24aaf91
Merge branch 'xtts-v2-truss' of github.com:htrivedi99/truss-examples …
htrivedi99 Nov 17, 2023
9088e0d
cleaning up truss
htrivedi99 Dec 4, 2023
fa055e7
Removing the custom base image, as its no longer needed
htrivedi99 Dec 4, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion xtts-v2-truss/README.md
View file
Original file line number Diff line number Diff line change
@@ -65,4 +65,9 @@ output = base64_to_wav(res.get('output'), "test_output.wav")
The output of the model is a base64 string as well, so you can convert it to a wav file using the `base64_to_wav` function.

Here is the input file for Samuel Jackson's voice:
![speaker voice](samuel_jackson_voice.mp4)
![speaker voice](https://github.com/htrivedi99/truss-examples/assets/15642666/6ae79c53-f63a-4e0a-b6fc-d397fee6162e)

Here is the output file for the text to speech:
![output](https://github.com/htrivedi99/truss-examples/assets/15642666/2a2f9a80-860d-4ef1-a530-7892a8bd874e)

In this README, the audio files are in the MP4 format because github does not allow the WAV format. However, for the truss itself using the WAV format is recommended.