Skip to main content

Feature Requests

Submit, discuss, and vote on feature requests for Groq API

  • 3 Topics
  • 0 Replies
3 Topics
yawnxyz
yawnxyzCommunity Manager
posted in Feature Requests
Model Request: Parakeet v2 0.6b Model

(Posted by peacock on the Groq Discord: https://discord.com/channels/1207099205563457597/1370606104966594680) Parakeet v2 0.6b can transcribe 1hr of audio in just 1 second https://huggingface.co/spaces/nvidia/parakeet-tdt-0.6b-v2https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2Only English SupportedIs this on roadmap? 

50
yawnxyz
yawnxyz
yawnxyzCommunity Manager
posted in Feature Requests
Add speech-to-speech model support

(Posted by Aly on the Groq Discord: https://discord.com/channels/1207099205563457597/1376241264101425273)Hi Groq Team,I'd like to request the addition of support for speech-to-speech (or voice-to-voice) models like ultravox on the Groq inference engine.Thanks!

10
yawnxyz
yawnxyz
yawnxyzCommunity Manager
posted in Feature Requests
Add support for logprobs in model API response

(Posted by Verdi on the Groq Discord: https://discord.com/channels/1207099205563457597/1377607663004811294) Looking to use Groq for writing our eval set. We are intending to use a design which is LLM-as-judge in our CD/CI pipeline. However, one of the issues as highlighted in this research (https://arxiv.org/pdf/2303.16634) is when asked a model will bias its "score" answer to be almost-always 3 and a better technique to get more high-quality test is to use the probability distribution instead. This is available when using OpenAI's API directly, but not for models on Groq. I would prefer to use Groq if possible since it's much faster!

30
yawnxyz
Terms & ConditionsCookie settings