Init GLM-4-Voice into utterance_metrics #46
Open
Stanwang1210 wants to merge 2 commits intowavlab-speech:mainfrom
Open
Init GLM-4-Voice into utterance_metrics #46Stanwang1210 wants to merge 2 commits intowavlab-speech:mainfrom
Stanwang1210 wants to merge 2 commits intowavlab-speech:mainfrom
Conversation
Stanwang1210
force-pushed
the
glm_4_voice
branch
from
a7bb4b8 to
e12bb6a
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 GLM-4-Voice into the evaluation pipeline
The implementation follows the structure used in qwen2_audio.py, ensuring consistency with other audio model integrations.
✅ Key Features
• Preprocessing and tokenization of audio and text inputs using GLM-4-Voice’s tokenizer
• Maintains compatibility with the existing evaluation framework
• Tokenization Pipeline: The current audio tokenization step may need further verification for correctness and completeness.
• Unexpected Output: The model is currently generating outputs like:
“I’m sorry, I can’t listen to or analyze audio. However, if you can transcribe the audio for me, I can help you count the number of distinct speakers. Let me know if you need assistance with that!”
It’s unclear whether this is caused by:
• A bug in the integration (e.g., incorrect formatting or tokenization)
• Or a limitation of the model’s current capabilities