TEVR: Improving Speech Recognition by Token Entropy Variance Reduction

Abstract: This paper presents TEVR, a speech recognition model designed to minimize the variation in token entropy w.r.t. to the LLM. This takes advantage of the fact that if the LLM will reliably and accurately predict a token anyway, then the acoustic model doesn't need to be accurate in recognizing it. We train German ASR models with 900 million parameters and show that on CommonVoice German, TEVR scores a very competitive 3.64% word error rate, which outperforms the best reported results by a relative 16.89% reduction in word error rate. We hope that releasing our fully trained speech recognition pipeline to the community will lead to privacy-preserving offline virtual assistants in the future.