Open Issues Need Help
View All on GitHub To boost the inference speed about 2 months ago
AI Summary: Optimize the inference speed of Whisper-large-v3-turbo model when using n-gram and large language models (LLMs) for improved performance. This likely involves investigating techniques such as model quantization, pruning, or using more efficient inference hardware/software.
Complexity:
4/5
help wanted question
Add n-gram and large language model (LLM) support to Whisper models.
Jupyter Notebook
#large-language-models#llm#n-gram-language-models#speech-recognition#speech-to-text#whisper