ollama icon indicating copy to clipboard operation
ollama copied to clipboard

Please add Qwen-audio

Open zimuoo opened this issue 1 year ago • 4 comments

What model would you like?

No response

zimuoo avatar Apr 03 '24 06:04 zimuoo

Please add Qwen-VL: https://huggingface.co/Qwen/Qwen-VL

tikeoewoew avatar Apr 03 '24 10:04 tikeoewoew

I think you meant https://huggingface.co/Qwen/Qwen-Audio and That's a really neat idea!

iplayfast avatar Apr 03 '24 16:04 iplayfast

Yes,thanks!发自我的 iPhone在 2024年4月4日,00:01,Chris Bruner @.***> 写道: I think you meant https://huggingface.co/Qwen/Qwen-Audio and That's a really neat idea!

—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you authored the thread.Message ID: @.***>

zimuoo avatar Apr 04 '24 05:04 zimuoo

hello, thank you for your amazing working! and I wonder how it's going? the newest qwen2-audio model was here: https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct

testmana2 avatar Aug 15 '24 03:08 testmana2

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

Additionally to Qwen2-Audio, I would like to see support for OpenAI's Whisper, which is also open source.

goetzc avatar Sep 02 '24 03:09 goetzc

The new NVIDIA Parakeet and related models are very good.

philipag avatar May 08 '25 08:05 philipag

Unfortunately this project doesn't seem to have any interest in those amazing new local models 😞

NVIDIA's New Open-Source Tool to Revolutionize Multilingual Speech-to-Text Experience https://www.communeify.com/en/blog/parakeet-tdt-0-6b-v3-nvidia-opensource-multilingual-stt/ https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3

reneleonhardt avatar Sep 15 '25 09:09 reneleonhardt