Promote Sign in Sign up

Multimodal model

Mega ASR

Mega-ASR is an open-source robust automatic speech recognition model built for difficult real-world audio with noise, far-field speech, obstruction, echo, distortion, and transmission dropout.

Shanghai AI Laboratory Multimodal Closed apache-2.0
Open model card ↗
Type
Multimodal
Weights
Closed
Likes
101
Pipeline
automatic speech recognition
License
apache-2.0

Model hub

zhifeixie/Mega-ASR

Repo
zhifeixie/Mega-ASR
Access
Public
Technical tags and languages
en zh safetensors automatic-speech-recognition speech-recognition audio robust-asr qwen3-asr base_model:Qwen/Qwen3-ASR-1.7B base_model:finetune:Qwen/Qwen3-ASR-1.7B
Open on Hugging Face

Papers

1

More from Shanghai AI Laboratory

5

About Shanghai AI Laboratory

1

Shanghai AI Laboratory (Shanghai AI Lab) is a research organization advancing next-generation AI and open innovation. Through initiatives like InternAI, it builds and open-sources models and tools, supports researchers and developers worldwide, and pushes practical AI forward from research to real-world applications.