[Feature Request]: Can ragflow add a speech-to-text model such as faster whisper? Can only fish audio be added to the text-to-speech model

[ZxnSnowy]

Is there an existing issue for the same feature request?

• [X] I have checked the existing issues.

Is your feature request related to a problem?

No response

Describe the feature you'd like

I wish I could add speech-to-text models like whisper. There are also text-to-speech models, such as cosyvoice

Describe implementation you've considered

No response

Documentation, adoption, use case

No response

Additional information

No response

[KevinHuSh]

Do you mean this?

[ZxnSnowy]

你是这个意思吗？

Yes, how did you add it? Can I add a local model？

[KevinHuSh]

Add a validated openAI api key.

[ZxnSnowy]

Add a validated openAI api key.

Thank you for your reply. I was wondering if I could add the local model I downloaded? Examples include faster-whisper and GPT-SoVITS.

[KevinHuSh]

What about using Xinference to deploy your LLM model？

[zzc-ccccc]

What about using Xinference to deploy your LLM model？

@KevinHuSh Good idea. I have already used Xinference to deploy CosyVoice2-0.5B. My question is, how can we use this model? Do we need to develop the audio workflow and get the text data back from the Xinderence service?