Skip to content

Overriding the new default of 'sdpa' #108

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

Open
ParthaEth wants to merge 25 commits into
base: main
Choose a base branch
from
Open

Overriding the new default of 'sdpa' #108

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
25 commits
Select commit Hold shift + click to select a range
34446ab
Overriding the newdefault of 'sdpa'
VRWarg Jul 23, 2025
61ed007
Building CLI interface so it can be triggered from hubspot
Jan 19, 2026
705e428
real number of steps
Jan 20, 2026
915ccbc
So the checkpoint is not picked from the deve version
Jan 22, 2026
d018b00
minor
Jan 27, 2026
331c6a5
more informative error
Feb 5, 2026
00e31ea
error correction in func name
Feb 5, 2026
bed9919
Creation speed param for ETA reporting
Feb 6, 2026
9b2542f
Building a little buffer
Feb 6, 2026
dd58810
Handling too short and verly long videos
Feb 6, 2026
9a0a0ea
calibrating the vid gen time
Feb 7, 2026
093ae1f
calibrating better
Feb 7, 2026
88be606
CLI now takes the avatar image and specified voice
Feb 18, 2026
d742dd3
Add attention_blackwell module with fallback mechanisms for flash att…
Feb 18, 2026
72c96bb
Keeping max frames rather high so things get included
Feb 18, 2026
6736154
Enhance avatar asset selection and input payload construction in CLI
Feb 19, 2026
07c9153
Update .gitignore to include .vscode directory
Feb 19, 2026
17017e7
Add base TTS template and enhance avatar handling in CLI
Feb 19, 2026
78e0170
Update input payload documentation to clarify avatar name usage
Feb 19, 2026
20a7804
Add mini.sh script for generating multitalk with configurable flash a…
Feb 23, 2026
1b09ac4
Add custom.sh script for generating multitalk with specified configur…
Feb 26, 2026
2a03256
Add new audio files and update JSON configuration for avatar processi…
Feb 26, 2026
a71cecd
Update mini.sh to include SCRIPT_TEXT in JSON output and modify input…
Mar 9, 2026
8a6e3bf
Refactor JSON formatting in base_tts_template.json and ensure consist…
Mar 11, 2026
04b5210
Add mini-audio.sh script for generating audio JSON configuration and …
Mar 16, 2026
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
5 changes: 5 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
__pycache__/
weights/
local_data/
save_audio/
.vscode/
Binary file added backend_runs/69a0754e42141599e5301cff/audio/avatar/1.pt
View file
Open in desktop
Binary file not shown.
Binary file added backend_runs/69a0754e42141599e5301cff/audio/avatar/s1.wav
View file
Open in desktop
Binary file not shown.
1 change: 1 addition & 0 deletions backend_runs/69a0754e42141599e5301cff/f799126dcf204820adca9bfdf0a35b79.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"prompt": "A professional speaks confidently directly to the camera.", "cond_image": "/mnt/c/Users/anwan/OneDrive/Khan/maity/vidLink/output/videos/69a0754e42141599e5301cff/avatar.png", "tts_audio": {"text": "We are ready for liftoff... finally!", "human1_voice": "/mnt/c/Users/anwan/OneDrive/Khan/maity/vidLink/video_generators/multitalk/weights/Kokoro-82M/voices/af_heart.pt"}, "cond_audio": {}}
10 changes: 10 additions & 0 deletions base_tts_template.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
{
"prompt": "A confident representative speaks directly to the camera.",
"cond_image": "Input_outputs/input_files/sales_executive/executive.png",
"tts_audio": {
"text": "example",
"human1_voice": "weights/Kokoro-82M/voices/af_heart.pt"
},
"cond_audio": {}
}

Loading