Soul-AILab / SoulX-Transcriber

What it does

• State of the art performance. SoulX-Transcriber achieves superior performance on the AISHELL-4 and AliMeeting benchmarks via a unified diarization and recognition framework, which directly produces structured outputs consisting of timestamp
• Speaker-aware multi-stage training. Speaker-aware multi-task Continues Pre-Training plus Supervised Fine-tuned strengthens speaker representation and robustness to conversations, mitigating same-gender confusion, overlap, and boundary error
• A more natural and authentic approach to dialogue generation. We propose a speaker characteristics-driven audio matching pipeline that automatically selects the most suitable reference audio for each utterance, producing more natural, conte