# WhisperRT -- Turning Whisper into a Causal Streaming Model

arXiv: https://arxiv.org/abs/2508.12301 · HTML: https://mlsanity.com/paper/2508.12301/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 17 Aug 2025.

## Builds on (most cited first, 18 of 18)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Streaming automatic speech recognition with the transformer model](https://mlsanity.com/paper/2001.02674/) (2020)
- [Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection](https://mlsanity.com/paper/2005.11185/) (2020)
- [LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models](https://mlsanity.com/paper/2310.02943/) (2023)
- [Turning Whisper into Real-Time Transcription System](https://mlsanity.com/paper/2307.14743/) (2023)
- [Low Latency End-to-End Streaming Speech Recognition with a Scout Network](https://mlsanity.com/paper/2003.10369/) (2020)
- [Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition](https://mlsanity.com/paper/2107.01269/) (2021)
- [Knowledge Distillation for Small-footprint Highway Networks](https://mlsanity.com/paper/1608.00892/) (2016)
- [Decoder-only Architecture for Streaming End-to-end Speech Recognition](https://mlsanity.com/paper/2406.16107/) (2024)
- [Efficient Streaming LLM for Speech Recognition](https://mlsanity.com/paper/2410.03752/) (2024)
- [Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection](https://mlsanity.com/paper/2406.10052/) (2024)
- [Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study](https://mlsanity.com/paper/2406.18862/) (2024)
- [On-device Streaming Discrete Speech Units](https://mlsanity.com/paper/2506.01845/) (2025)

## Abstract (arXiv)

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming (online or real-time) transcription, due to limitations in their architecture and training methodology. We propose a method to turn the transformer encoder-decoder model into a low-latency streaming model. The encoder is made causal to process audio incrementally, while the decoder conditions on partial encoder states to generate tokens aligned with the available temporal context. This requires explicit synchronization between encoded input frames and token emissions. Since tokens are produced only after sufficient acoustic evidence is observed, an inherent latency arises, necessitating fine-tuning of the encoder-decoder alignment mechanism. We propose an updated inference mechanism that utilizes the fine-tuned causal encoder and decoder to yield greedy and beam-search decoding, and is shown to be locally optimal. Experiments on low-latency chunk sizes (less than 300 msec) show that our fine-tuned model outperforms existing non-fine-tuned streaming approaches in most cases, while using a lower complexity. We release our training and inference code, along with the fine-tuned models, to support further research and development in streaming ASR.