8000 Comparing 0.8.8.1...0.8.9 · uezo/ChatdollKit · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: uezo/ChatdollKit
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: 0.8.8.1
Choose a base ref
...
head repository: uezo/ChatdollKit
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: 0.8.9
Choose a head ref
  • 11 commits
  • 10 files changed
  • 1 contributor

Commits on Dec 12, 2024

  1. Add Voice Prefetch Mode functionality 

    - Introduced Voice Prefetch Modes: Parallel, Sequential, and Disabled.
- Implemented Sequential mode to handle requests in a FIFO queue.
- Replaced the previous `bool UsePrefetch` setting with the new `Voice Prefetch Mode` system.
  - `UsePrefetch = true` corresponds to the new `Parallel` mode (default).
  - `UsePrefetch = false` corresponds to the new `Disabled` mode.
    @uezo
    uezo committed Dec 12, 2024
    Configuration menu
    Copy the full SHA
    ba720ab View commit details
    Browse the repository at this point in the history

  2. Merge pull request #408 from uezo/voice-prefetch-mode 

    Add Voice Prefetch Mode functionality
    @uezo
    uezo authored Dec 12, 2024
    Configuration menu
    Copy the full SHA
    50be0d0 View commit details
    Browse the repository at this point in the history

  3. Add support for NijiVoice as a speech synthesizer 

    - Added support for NijiVoice as a speech synthesis service.
- To use NijiVoice, add the `NijiVoiceSpeechSynthesizer` component to the AIAvatar object and configure the following in the inspector:
  - Set the API key and Voice Actor Id.
  - Enable the `IsEnabled` option.
- When using NijiVoice, set the `Voice Prefetch Mode` to `Sequential`. This can be configured in the ModelController inspector.
    @uezo
    uezo committed Dec 12, 2024
    Configuration menu
    Copy the full SHA
    6c68894 View commit details
    Browse the repository at this point in the history

  4. Merge pull request #409 from uezo/support-nijivoice-speech-synthesizer 

    Add support for NijiVoice as a speech synthesizer
    @uezo
    uezo authored Dec 12, 2024
    Configuration menu
    Copy the full SHA
    d7854ac View commit details
    Browse the repository at this point in the history

Commits on Dec 13, 2024

  1. Make it possible to start another GenAI stream while dialog 

    - Add `overwrite` argument: If set false, start new dialog (LLM stream) without stopping ongoing dialog.
- Add OnBeforeProcessContentStreamAsync: Execute before processing content stream.

By combining these features, you can improve the performance of successive speech by AITuber.
    @uezo
    uezo committed Dec 13, 2024
    Configuration menu
    Copy the full SHA
    66c9e5d View commit details
    Browse the repository at this point in the history

  2. Use buffered request regardless of the priority

    @uezo
    uezo committed Dec 13, 2024
    Configuration menu
    Copy the full SHA
    65ddef1 View commit details
    Browse the repository at this point in the history

  3. Merge pull request #410 from uezo/improve-dialog-processing-20241214 

    Improve dialog processing
    @uezo
    uezo authored Dec 13, 2024
    Configuration menu
    Copy the full SHA
    a091d8a View commit details
    Browse the repository at this point in the history

  4. Fix bug where DialogProcessor fails on before processing LLM stream 

    🙏
    @uezo
    uezo committed Dec 13, 2024
    Configuration menu
    Copy the full SHA
    16a5b92 View commit details
    Browse the repository at this point in the history

  5. Merge pull request #411 from uezo/fix-bug-error-before-processing-con… 

    …tent

Fix bug where DialogProcessor fails on before processing LLM stream
    @uezo
    uezo authored Dec 13, 2024
    Configuration menu
    Copy the full SHA
    4b82119 8000 View commit details
    Browse the repository at this point in the history

  6. Update for v0.8.9 

    README, version, demo and small change.
    @uezo
    uezo committed Dec 13, 2024
    Configuration menu
    Copy the full SHA
    3911225 View commit details
    Browse the repository at this point in the history

  7. Merge pull request #412 from uezo/update-for-089 

    Update for v0.8.9
    @uezo
    uezo authored Dec 13, 2024
    Configuration menu
    Copy the full SHA
    31b34ab View commit details
    Browse the repository at this point in the history
Loading
0