Exploring RWKV for Memory Efficient and Low Latency Streaming ASR
원문 초록
Recently, self-attention-based transformers and conformers have been introduced as alternatives to RNNs for ASR acoustic modeling. Nevertheless, the full-sequence attention mechanism is non-streamable and computationally expensive, thus requiring modifications, such as chunking and caching, for efficient streaming ASR. In this paper, we propose to apply RWKV, a variant of linear attention transformer, to streaming ASR. RWKV combines the superior performance of transformers and the inference efficiency of RNNs, which is well-suited for streaming ASR scenarios where the budget for latency and memory is restricted. Experiments on varying scales (100h - 10000h) demonstrate that RWKV-Transducer and RWKV-Boundary-Aware-Transducer achieve comparable to or even better accuracy compared with chunk conformer transducer, with minimal latency and inference memory cost.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree
TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning
Real-Time Execution of Action Chunking Flow Policies
Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models
Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings
Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis
토론
이 논문과 연결된 포럼 글이 아직 없습니다.