scpedicini

# This script will transcribe an audio file (mp3, wav, etc.) to text and then clean the text using a local LLM model via Ollama. Technically, this script will work with any LLM that supports the standard OpenAI bindings with minor adjustments. 

# GETTING STARTED:
# 1. Install required python packages (pip install openai python-dotenv)
# 2. Git clone a copy of ggerganov/whisper (https://github.com/ggerganov/whisper.cpp)
# 3. Build the whisper binary (see the whisper.cpp README for instructions)
# 4. Download one of the whisper models (largev2 is the most accurate for all languages, though the base model works reasonably well for English).
# 5. Install ffmpeg (brew install ffmpeg on macOS, apt-get install ffmpeg)
# 6. Install ollama (https://ollama.com/download)
# 7. Download an LLM model (https://ollama.com/library)

vrslev

import os

import arel
from fastapi import FastAPI, Request
from fastapi.templating import Jinja2Templates

app = FastAPI()
templates = Jinja2Templates("templates")

if _debug := os.getenv("DEBUG"):