Init kimi into utterance_metrics#43
Open
Stanwang1210 wants to merge 2 commits intowavlab-speech:mainfrom
Open
Conversation
Contributor
|
Many thanks! One minor suggestion is to use the existing prompts so that we can simplify the scripts a lot. I will have a further detailed check soon. Appreciate! |
Author
|
I’ve incorporated existing prompts so the scripts are now simpler. Please take a look at the current version. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR integrates the Kimi-Audio model into the evaluation pipeline.
The overall implementation structure follows the pattern established in qwen2_audio.py, ensuring consistency with existing audio model integrations. Key components include:
• Preprocessing and tokenization of audio inputs using Kimi-Audio’s API
• Compatibility with the existing evaluation framework
Let me know if any adjustments are needed, especially regarding tokenizer behavior or input formatting. I’m happy to iterate!