wenet-e2e / wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit
https://wenet-e2e.github.io/wenet/
Apache License 2.0
3.87k stars 1.03k forks source link

[Audio LLM]support audiollm for asr, based on whisper and llama3 #2532

Open Zth9730 opened 1 month ago

Zth9730 commented 1 month ago

conduct experiment on librispeech dataset for severl steps:

image
thsxbw commented 1 month ago

Can you provide config.yaml or experimental results?

Zth9730 commented 1 month ago

Can you provide config.yaml or experimental results?

Yes, there will be new commits later.