Please add support to audio files / streams...
so we can use models such as
https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct
Please add support to audio files / streams...
so we can use models such as
https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct
1条答案
按热度按时间0md85ypi1#
在Ollama中支持音频模型将会非常棒,目前很少有好的工具支持这个功能,据我所知,只有LocalAI目前支持。
我希望看到OpenAI的Whisper,它是开源的。