Spaces:
Running
Running
File size: 3,918 Bytes
88b6846 b3e360f 88b6846 b3e360f 88b6846 b3e360f 88b6846 b3e360f 88b6846 b3e360f 88b6846 b3e360f 88b6846 b3e360f 88b6846 b3e360f 88b6846 b3e360f 88b6846 b3e360f 88b6846 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
import { NextResponse } from 'next/server';
import { promises as fs } from 'fs';
import path from 'path';
import archiver from 'archiver';
import { getDataDir, getAudioPath, getTranscriptionsPath, getMetadataPath } from '@/lib/dataPath';
export async function GET(request: Request) {
const { searchParams } = new URL(request.url);
const speakerId = searchParams.get('speaker_id');
// Get the base data directory
const dataDir = getDataDir();
try {
await fs.access(dataDir);
} catch {
return NextResponse.json({ error: 'Data directory not found' }, { status: 404 });
}
const archive = archiver('zip', {
zlib: { level: 9 }
});
const stream = new ReadableStream({
async start(controller) {
archive.on('data', (chunk) => {
controller.enqueue(chunk);
});
archive.on('end', () => {
controller.close();
});
archive.on('error', (err) => {
console.error('Archive error:', err);
controller.error(err);
});
try {
// Generate metadata.csv for LJSpeech compatibility
const metadataPath = path.join(getMetadataPath(), 'dataset_info.json');
try {
const metadataContent = await fs.readFile(metadataPath, 'utf-8');
const metadata = JSON.parse(metadataContent);
if (metadata.recordings && Array.isArray(metadata.recordings)) {
const csvContent = metadata.recordings.map((r: { filename?: string; text?: string }) =>
`${r.filename || ''}|${r.text || ''}`
).join('\n');
archive.append(csvContent, { name: 'metadata.csv' });
}
} catch {
console.warn('Could not generate metadata.csv');
}
// If speaker_id is provided, only export that speaker's data
if (speakerId) {
const audioDir = getAudioPath(speakerId);
const textDir = getTranscriptionsPath(speakerId);
try {
await fs.access(audioDir);
archive.directory(audioDir, `audio/${speakerId}`);
} catch {
// No audio for this speaker
}
try {
await fs.access(textDir);
archive.directory(textDir, `transcriptions/${speakerId}`);
} catch {
// No transcriptions for this speaker
}
} else {
// Export all data
const audioDir = getAudioPath();
const textDir = getTranscriptionsPath();
try {
await fs.access(audioDir);
archive.directory(audioDir, 'audio');
} catch {
// No audio folder
}
try {
await fs.access(textDir);
archive.directory(textDir, 'transcriptions');
} catch {
// No transcriptions folder
}
}
archive.finalize();
} catch (error) {
console.error('Error creating archive:', error);
controller.error(error);
}
}
});
const filename = speakerId ? `dataset_${speakerId}.zip` : 'dataset_full.zip';
return new NextResponse(stream, {
headers: {
'Content-Type': 'application/zip',
'Content-Disposition': `attachment; filename="${filename}"`
}
});
}
|