FormalASR fine-tunes small Qwen3-ASR models on new spoken-to-formal Chinese datasets to achieve direct transcription with up to 37.4% relative CER reduction over verbatim baselines.
HyPoradise: An open baseline for generative speech recognition with large language models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FormalASR: End-to-End Spoken Chinese to Formal Text
FormalASR fine-tunes small Qwen3-ASR models on new spoken-to-formal Chinese datasets to achieve direct transcription with up to 37.4% relative CER reduction over verbatim baselines.