NVIDIA livestream: fine-tuning Nemotron ASR and LLMs for vertical voice agents
NVIDIA Developer · youtube · 2026-10-09
A NVIDIA Developer livestream on customizing speech and language models to build voice agents for real-world domains:
- When and why to fine-tune an ASR model, with lessons from NVIDIA Nemotron ASR;
- Data, training, and evaluation considerations for speech adaptation, plus techniques for specialized vocabularies and languages;
- How LLM post-training improves task-specific performance and how ASR/LLM customization combine in voice-agent workflows;
- Lessons learned from real-world deployments.
Aimed at developers building customer-service assistants, industry copilots, or multilingual voice apps.
More from coding & agent
- PartyKit shuts down free hosted platform 2.5 years after Cloudflare acquisition — threepointone · 2026-10-09
- Run a Brand X Account With 3 AI Bots: Community Manager, Content Strategist, Analyst — FinanceYF5 · 2026-10-09
- Google's A2A protocol moves to neutral foundation alongside MCP under AAIF — SnooDingos9560 · 2026-10-09
- Who owns the job after the agent disconnects? A Kubernetes MCP architecture — stevenacreman · 2026-10-09
- LangChain Founder: Evals Work for Narrow Tasks but Break Down for Autonomous Agents — hwchase17 · 2026-10-09
- Deepkit author: Bun is rediscovering our decade-old ideas, agents could revive it — MarcJSchmidt · 2026-10-09