[GH-ISSUE #6367] Please add support for Audio models such as Qwen2-Audio #29758

Closed
opened 2026-04-22 08:57:31 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @carlosforster on GitHub (Aug 15, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6367

Please add support to audio files / streams...
so we can use models such as
https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct

Originally created by @carlosforster on GitHub (Aug 15, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6367 Please add support to audio files / streams... so we can use models such as https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct
GiteaMirror added the feature request label 2026-04-22 08:57:31 -05:00
Author
Owner

@goetzc commented on GitHub (Aug 17, 2024):

Having audio models support in Ollama would be great, not many nice tools support this, AFAIK only LocalAI currently does.

I would like to see OpenAI's Whisper, which is open source.

<!-- gh-comment-id:2294499335 --> @goetzc commented on GitHub (Aug 17, 2024): Having audio models support in Ollama would be great, not many nice tools support this, AFAIK only [LocalAI](https://localai.io) currently does. I would like to see OpenAI's [Whisper](https://github.com/openai/whisper), which is open source.
Author
Owner

@pdevine commented on GitHub (Sep 2, 2024):

Dupe of #3471

<!-- gh-comment-id:2323712761 --> @pdevine commented on GitHub (Sep 2, 2024): Dupe of #3471
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#29758