Add transcribe

This commit is contained in:
suraj.shenoy.b@gmail.com
2025-01-25 09:50:53 -06:00
parent e3437fefc9
commit 43b66a6e0f
9 changed files with 184 additions and 0 deletions

View File

@@ -25,8 +25,10 @@
"hoyahax-2025": "file:",
"lucide-react": "^0.474.0",
"mongoose": "^8.9.5",
"multer": "^1.4.5-lts.1",
"next": "15.1.6",
"next-themes": "^0.4.4",
"openai-whisper": "^1.0.2",
"react": "^19.0.0",
"react-dom": "^19.0.0",
"svix": "^1.45.1",
@@ -35,6 +37,7 @@
},
"devDependencies": {
"@eslint/eslintrc": "^3.2.0",
"@types/multer": "^1.4.12",
"@types/node": "^20.17.16",
"@types/react": "^19.0.8",
"@types/react-dom": "^19.0.3",

Binary file not shown.

View File

@@ -0,0 +1,34 @@
from fastapi import FastAPI, File, UploadFile
from fastapi.middleware.cors import CORSMiddleware
import whisper
import os
import tempfile
app = FastAPI()
model = whisper.load_model("base") # Load the model once for efficiency
app.add_middleware(
CORSMiddleware,
allow_origins=["http://localhost:3000"], # Frontend origin (adjust as needed)
allow_credentials=True,
allow_methods=["*"], # Allow all HTTP methods (GET, POST, etc.)
allow_headers=["*"], # Allow all headers (Authorization, Content-Type, etc.)
)
@app.post("/transcribe")
async def transcribe_audio(file: UploadFile = File(...)):
# Save the uploaded file to a temporary location
with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_file:
temp_file.write(await file.read())
temp_path = temp_file.name
try:
# Transcribe the audio
result = model.transcribe("inputs/test.mp3")
transcription = result["text"]
print(transcription)
finally:
# Clean up temporary file
os.remove(temp_path)
return {"transcription": transcription}

Binary file not shown.

View File

@@ -0,0 +1,55 @@
import { NextRequest, NextResponse } from "next/server";
import multer from "multer";
import fs from "fs/promises";
import whisper from "openai-whisper";
const upload = multer({ dest: "uploads/" });
export const config = {
api: {
bodyParser: false, // Disable Next.js's body parsing for file uploads
},
};
// Whisper model (initialize once for efficiency)
const model = whisper.load_model("base");
// Utility to transcribe audio
async function transcribeAudio(filePath: string): Promise<string> {
const transcription = await model.transcribe(filePath);
return transcription.text;
}
async function parseMultipartForm(req: NextRequest): Promise<File> {
return new Promise((resolve, reject) => {
const multerMiddleware = upload.single("audio");
multerMiddleware(req as any, {} as any, (error: any) => {
if (error) return reject(error);
resolve(req.file);
});
});
}
export async function POST(req: NextRequest) {
try {
// Parse the incoming multipart form data
const file = await parseMultipartForm(req);
if (!file) {
return NextResponse.json({ error: "No audio file provided" }, { status: 400 });
}
const filePath = file.path;
// Transcribe the audio
const transcription = await transcribeAudio(filePath);
// Clean up the uploaded file
await fs.unlink(filePath);
return NextResponse.json({ transcription });
} catch (error) {
console.error("Error during transcription:", error);
return NextResponse.json({ error: "Transcription failed" }, { status: 500 });
}
}

17
src/app/page.tsx Normal file
View File

@@ -0,0 +1,17 @@
import RootLayout from './layout'
import SignupPage from './signup/page'
import Link from "next/link";
export default function Home() {
return (
<RootLayout>
<div style={{ display: 'flex', flexDirection: 'column', alignItems: 'center', justifyContent: 'center', height: '100vh' }}>
<h1 style={{ fontSize: 64, marginBottom: 20 }}>Welcome to Hoya</h1>
<SignupPage />
<Link href="/transcribe">
<button>Go to Transcribe Page</button>
</Link>
</div>
</RootLayout>
)
}

View File

@@ -0,0 +1,16 @@
export const metadata = {
title: 'Next.js',
description: 'Generated by Next.js',
}
export default function RootLayout({
children,
}: {
children: React.ReactNode
}) {
return (
<html lang="en">
<body>{children}</body>
</html>
)
}

View File

@@ -0,0 +1,56 @@
"use client";
import React, { useState } from "react";
import axios from "axios";
const AudioTranscriber: React.FC = () => {
const [file, setFile] = useState<File | null>(null);
const [transcription, setTranscription] = useState<string | null>(null);
const [loading, setLoading] = useState(false);
const handleFileChange = (event: React.ChangeEvent<HTMLInputElement>) => {
if (event.target.files && event.target.files.length > 0) {
setFile(event.target.files[0]);
}
};
const handleTranscription = async () => {
if (!file) return alert("Please select an audio file to transcribe!");
const formData = new FormData();
formData.append("file", file);
setLoading(true);
try {
const response = await axios.post("http://localhost:8000/transcribe", formData, {
headers: {
"Content-Type": "multipart/form-data",
},
});
setTranscription(response.data.transcription);
} catch (error) {
console.error("Error transcribing audio:", error);
alert("Failed to transcribe audio. Please try again.");
} finally {
setLoading(false);
}
};
return (
<div>
<h1>Audio Transcription</h1>
<input type="file" accept="audio/*" onChange={handleFileChange} />
<button onClick={handleTranscription} disabled={loading}>
{loading ? "Transcribing..." : "Transcribe"}
</button>
{transcription && (
<div>
<h2>Transcription:</h2>
<p>{transcription}</p>
</div>
)}
</div>
);
};
export default AudioTranscriber;

View File

@@ -28,6 +28,9 @@ export function Navbar() {
<Link href="/products" className="transition-colors hover:text-foreground/80 text-foreground/60">
Map
</Link>
<Link href="/transcribe" className="transition-colors hover:text-foreground/80 text-foreground/60">
Transcribe
</Link>
</nav>
</div>
<div className="flex flex-1 items-center justify-between space-x-2 md:justify-end">