{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiez3ukqx6xd2tf2zqf5ps5vunubp2o5urmezee2n4txcozl5nldlu",
"uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mfp7cngiqar2"
},
"path": "/t/looking-for-asr-whisper-engineer-for-success-based-partnership/173434#post_3",
"publishedAt": "2026-02-25T17:11:58.000Z",
"site": "https://discuss.huggingface.co",
"textContent": "Thanks for your response\n\nYour goal of a production-ready ASR system that can handle both short clips and long recordings really resonates with me.\n\nI’ve built similar systems end-to-end—fine-tuning models like wav2vec 2.0 and Whisper, integrating LLM workflows for post-processing, and deploying everything as scalable microservices using FastAPI, Docker, and Kubernetes.\n\nBecause this is a results-focused project, I’d suggest structuring our work around clear milestones and measurable outcomes so we can ensure the system meets your transcription accuracy and latency requirements.\n\nI can put together a plan with timelines and deliverables if that works for you.\n\nLooking forward to hearing your thoughts and discussing next steps.\n\nBest,\nRobert",
"title": "Looking for ASR / Whisper engineer for success-based partnership"
}