Tanjiro
Tanjiro
Can you detail the steps to test on audio
We can load safetensors medusa Lm heads
Hi Team, I am trying to replicate this text-completion behaviour with OpenAI Whisper Model, how can I send audio inputs to the basaran so that it can generate streaming output
### Motivation As model is higher, to quantize we require higher gpu to load model whole in gpu, but after quantization it can be fitted in low gram as well,...
### Checklist - [X] 1. I have searched related issues but cannot get the expected help. - [X] 2. The bug has not been fixed in the latest version. -...
This is an integration PR of [Simplismart](https://simplismart.ai)'s open source stt, tts and LLM models