{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unifying-streaming-and-non-streaming","title":"Unifying Streaming and Non-streaming Zipformer-based ASR","arxiv_id":"2506.14434","date":"2025-06-17","proceeding":null,"authors":["Bidisha Sharma","Karthik Pandia Durai","Shankar Venkatesan","Jeena J Prakash","Shashi Kumar","Malolan Chetlur","Andreas Stolcke"],"abstract":"There has been increasing interest in unifying streaming and non-streaming automatic speech recognition (ASR) models to reduce development, training, and deployment costs. We present a unified framework that trains a single end-to-end ASR model for both streaming and non-streaming applications, leveraging future context information. We propose to use dynamic right-context through the chunked attention masking in the training of zipformer-based ASR models. We demonstrate that using right-context is more effective in zipformer models compared to other conformer models due to its multi-scale nature. We analyze the effect of varying the number of right-context frames on accuracy and latency of the streaming ASR models. We use Librispeech and large in-house conversational datasets to train different versions of streaming and non-streaming models and evaluate them in a production grade server-client setup across diverse testsets of different domains. The proposed strategy reduces word error by relative 7.9\\% with a small degradation in user-perceived latency. By adding more right-context frames, we are able to achieve streaming performance close to that of non-streaming models. Our approach also allows flexible control of the latency-accuracy tradeoff according to customers requirements.","url_abs":"https://arxiv.org/abs/2506.14434v1","url_pdf":"https://arxiv.org/pdf/2506.14434v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2506.14434","atlas_url":"https://app.syntology.ai/?focus=2506.14434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.14434"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/k2-fsa/icefall","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/k2-fsa/sherpa","reach":null}],"summary":{"ran":1,"ran_fixture":1,"unverified":11},"by_repo_kind":{"found_in_text":{"samples":13,"ran":2,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"913ef6ad7c628305","entry":"FrameReducer","repo":"k2-fsa/sherpa","repo_kind":"found_in_text","path":"triton/zipformer/model_repo_offline_bs/frame_reducer/1/model.py","file_url":"https://github.com/k2-fsa/sherpa/blob/HEAD/triton/zipformer/model_repo_offline_bs/frame_reducer/1/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"913ef6ad7c628305"}},{"code_sha256_prefix":"3b57039980b0928c","entry":"make_pad_mask","repo":"k2-fsa/sherpa","repo_kind":"found_in_text","path":"triton/zipformer/model_repo_offline_bs/frame_reducer/1/model.py","file_url":"https://github.com/k2-fsa/sherpa/blob/HEAD/triton/zipformer/model_repo_offline_bs/frame_reducer/1/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3b57039980b0928c"}},{"code_sha256_prefix":"4890d0a6d7925ab3","entry":"attach_diagnostics","repo":"k2-fsa/icefall","repo_kind":"found_in_text","path":"icefall/diagnostics.py","file_url":"https://github.com/k2-fsa/icefall/blob/HEAD/icefall/diagnostics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4890d0a6d7925ab3"}},{"code_sha256_prefix":"c90ec0af48b591a2","entry":"average_checkpoints","repo":"k2-fsa/icefall","repo_kind":"found_in_text","path":"icefall/checkpoint.py","file_url":"https://github.com/k2-fsa/icefall/blob/HEAD/icefall/checkpoint.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c90ec0af48b591a2"}},{"code_sha256_prefix":"59d410aa19bdef96","entry":"byte_decode","repo":"k2-fsa/icefall","repo_kind":"found_in_text","path":"icefall/byte_utils.py","file_url":"https://github.com/k2-fsa/icefall/blob/HEAD/icefall/byte_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59d410aa19bdef96"}},{"code_sha256_prefix":"004eb0067bd43754","entry":"byte_encode","repo":"k2-fsa/icefall","repo_kind":"found_in_text","path":"icefall/byte_utils.py","file_url":"https://github.com/k2-fsa/icefall/blob/HEAD/icefall/byte_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"004eb0067bd43754"}},{"code_sha256_prefix":"8a64b592c82c0d10","entry":"convert_alignments_to_tensor","repo":"k2-fsa/icefall","repo_kind":"found_in_text","path":"icefall/ali.py","file_url":"https://github.com/k2-fsa/icefall/blob/HEAD/icefall/ali.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8a64b592c82c0d10"}},{"code_sha256_prefix":"c75cf10a124dca6a","entry":"find_checkpoints","repo":"k2-fsa/icefall","repo_kind":"found_in_text","path":"icefall/checkpoint.py","file_url":"https://github.com/k2-fsa/icefall/blob/HEAD/icefall/checkpoint.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c75cf10a124dca6a"}},{"code_sha256_prefix":"b865558252e1566a","entry":"get_class_name","repo":"k2-fsa/icefall","repo_kind":"found_in_text","path":"icefall/diagnostics.py","file_url":"https://github.com/k2-fsa/icefall/blob/HEAD/icefall/diagnostics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b865558252e1566a"}},{"code_sha256_prefix":"d6c6ed911b29d8a6","entry":"get_tensor_stats","repo":"k2-fsa/icefall","repo_kind":"found_in_text","path":"icefall/diagnostics.py","file_url":"https://github.com/k2-fsa/icefall/blob/HEAD/icefall/diagnostics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d6c6ed911b29d8a6"}},{"code_sha256_prefix":"24af924ede3ca20e","entry":"load_alignments","repo":"k2-fsa/icefall","repo_kind":"found_in_text","path":"icefall/ali.py","file_url":"https://github.com/k2-fsa/icefall/blob/HEAD/icefall/ali.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"24af924ede3ca20e"}},{"code_sha256_prefix":"a1f5678203ff47e8","entry":"lookup_alignments","repo":"k2-fsa/icefall","repo_kind":"found_in_text","path":"icefall/ali.py","file_url":"https://github.com/k2-fsa/icefall/blob/HEAD/icefall/ali.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a1f5678203ff47e8"}},{"code_sha256_prefix":"226350299950338b","entry":"smart_byte_decode","repo":"k2-fsa/icefall","repo_kind":"found_in_text","path":"icefall/byte_utils.py","file_url":"https://github.com/k2-fsa/icefall/blob/HEAD/icefall/byte_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"226350299950338b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}