Customizing Vertical Voice Agents with ASR and LLM Fine-Tuning

Voice AI experiences are only as good as the models behind them. In this livestream, NVIDIA and our partner expert will walk through how to customize speech and language models to build voice agents for real-world domains and use cases.
We'll share practical lessons learned from fine-tuning NVIDIA Nemotron ASR models, including data requirements, training considerations, and techniques for improving recognition accuracy on specialized vocabularies and languages. We'll also explore how post-training and customization can be applied to large language models, and how these approaches can be combined to create domain-specific voice agents.
Through real examples and live discussion, attendees will learn:

• When and why to fine-tune an ASR model
• Data, training, and evaluation considerations for speech adaptation
• How LLM post-training can improve task-specific performance
• How ASR and LLM customization work together in voice-agent workflows
• Lessons learned from real-world deployments and experimentation

Whether you're building customer service assistants, industry-specific copilots, or multilingual voice applications, this session will provide practical guidance for adapting foundation models to your own use cases.