Entity · model

FastConformer-Large

modelactivefastconformer-large-6b450640·1 events·first seen Jun 3, 2026

Aliases: FastConformer-Large

Co-occurring entities

Efficient ASR Training with Conversations that Never Happened BEA-Dialogue

More like this (12)

Conformal Prediction MemCon Biconvex Optimization PosConf Mondrian Conformal Prediction Whisper large-v3 ConvMemory v2 ClinFusion ClinFusion emotion2vec_plus_large Conformal Decision Theory Confluent

Recent events (1)

5arXiv · cs.CL·Jun 3, 2026·source ↗

Synthetic LLM-generated conversations improve ASR training for low-resource languages

Researchers propose a pipeline that uses LLMs to generate scenario-level dialogues and TTS to synthesize multi-speaker audio, creating simulated conversational training data for ASR systems. Evaluated on the Hungarian BEA-Dialogue benchmark, a model trained on 67 hours of real plus 636 hours of synthetic data outperforms a zero-shot model trained on 2,700 hours of real Hungarian speech. The study tests five LLM families under multiple budget and mixing configurations using a FastConformer-Large backbone, finding that generator choice and data composition significantly affect gains.

Evaluation and Benchmarking FastConformer-Large Efficient ASR Training with Conversations that Never Happened BEA-Dialogue