Skip to content

Conversation

@Gldkslfmsd
Copy link
Member

translate server works.
But documentation is not good and žžžendofranslatežžž as well. Json would be better.

📄 Contributor License Agreement Consent

The authors of SimulStreaming wish to enhance ways to collect and use feedback from users of SimulStreaming in future research and development while not limiting community contributions and non-commercial use. Therefore, this project is dual-licenced; the commercial use requires registration before obtaining a commercial licence.

Before we merge this pull request, we kindly ask you to consider granting the permissions below. If you have questions or prefer a different arrangement, feel free to leave a comment or contact the author. Thank you!

By checking the boxes below, you confirm the following:

  • I confirm that I have the legal right to grant a license for the contributions in this pull request to the maintainers of the SimulStreaming project.
    (For example, you are the only author, of legal age, not restricted by employment or institutional agreements.)

  • I grant the maintainers of SimulStreaming permission to re-license my contribution under any license, including commercial ones.

Gldkslfmsd and others added 23 commits July 24, 2025 12:20
although the code is messy :(
Apparently kernel.src cannot be directly assigned in v3, so store src
in a local copy and modify that one before applying the updates.

Tested on simulated streaming audio locally.

see openai/whisper#2597
The previous commit added Triton 3.x support but broke backward
compatibility with Triton 2.x by requiring triton>=3.0.0.

This commit restores compatibility with both versions by following
the upstream OpenAI Whisper approach:
- Use hasattr() to detect which API is available
- Call _unsafe_update_src() + hash reset for Triton 3.0-3.1
- Fall back to kernel.src for Triton 2.x
- Restore triton>=2.0.0 requirement (supports both 2.x and 3.x)

This matches the implementation in openai/whisper and addresses
the maintainer feedback to follow upstream more closely.

Builds on: #22
See: openai/whisper#2597
- bugfixes, catch-up, hovercraft
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants