Qwen-Audio-Chat

Parameters

8.5B

Published

Nov 14, 2023

Qwen-Audio-Chat is an AI model developed by Alibaba (China), first published in November 2023. It works in the language, speech and audio domain, on tasks such as audio question answering, chat, speech recognition (asr) and 8 more.

Epoch AI has no training-compute estimate for this model. The model has 8,460,000,000 parameters.

Access: Open weights (restricted use). Its weights are openly available. The reference paper has 743 citations. Epoch AI rates the confidence of this record as likely.

Full record

Organization: Alibaba
Country of organization: China
Domain: Language, Speech, Audio
Task: Audio question answering, Chat, Speech recognition (ASR), Translation, Transcription, Text classification, Question answering, Audio classification, Voice identification, Part-of-speech tagging, Speech-to-speech
Parameters: 8,460,000,000
Numerical format: BF16
Model accessibility: Open weights (restricted use)
Open weights: Yes
Citations: 743
Epoch confidence: Likely