GitHub - gauravgola96/gemini-llm-asr-go: A Golang-based implementation of an Automatic Speech Recognition (ASR) system leveraging Gemini LLM's multimodal capabilities. This repository demonstrates how to process speech input and generate accurate text transcriptions using Gemini LLM.

Installation

Macos onnxruntime - brew install onnxruntime

export LIBRARY_PATH=/opt/homebrew/Cellar/onnxruntime/1.20.1/lib

export C_INCLUDE_PATH=/opt/homebrew/Cellar/onnxruntime/1.20.1/include/onnxruntime

  go mod tidy
  go run main.go

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
gemini-asr		gemini-asr
model		model
vad		vad
README.md		README.md
go.mod		go.mod
main.go		main.go