{"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/fastadasp-multitask-adapted-efficient","title":"FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model","arxiv_id":"2410.03007","date":"2024-10-03","proceeding":null,"authors":["Yichen Lu","Jiaqi Song","Chao-Han Huck Yang","Shinji Watanabe"],"abstract":"In this study, we aim to explore Multitask Speech Language Model (SpeechLM) efficient inference via token reduction. Unlike other modalities such as vision or text, speech has unique temporal dependencies, making previous efficient inference works on other modalities not directly applicable. Furthermore, methods for efficient SpeechLM inference on long sequence and sparse signals remain largely unexplored. Then we propose FastAdaSP, a weighted token merging framework specifically designed for various speech-related tasks to improve the trade-off between efficiency and performance. Experimental results on WavLLM and Qwen-Audio show that our method achieves the state-of-the-art (SOTA) efficiency-performance trade-off compared with other baseline methods. Specifically, FastAdaSP achieved 7x memory efficiency and 1.83x decoding throughput without any degradation on tasks like Emotion Recognition (ER) and Spoken Question Answering (SQA). The code will be available at https://github.com/yichen14/FastAdaSP","url_abs":"https://arxiv.org/abs/2410.03007v1","url_pdf":"https://arxiv.org/pdf/2410.03007v1.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":[{"paper_slug":"fastadasp-multitask-adapted-efficient","repo_url":"https://github.com/yichen14/fastadasp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"token-reduction","task_name":"Token Reduction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.03007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03007"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/yichen14/FastAdaSP","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"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":"d9db9f86b30f9ac0","entry":"dequantize_cache_torch","repo":"yichen14/FastAdaSP","repo_kind":"official","path":"Qwen-Audio/modeling_qwen.py","file_url":"https://github.com/yichen14/FastAdaSP/blob/HEAD/Qwen-Audio/modeling_qwen.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9db9f86b30f9ac0"}},{"code_sha256_prefix":"1fec7a76f0d171a6","entry":"quantize_cache_v","repo":"yichen14/FastAdaSP","repo_kind":"official","path":"Qwen-Audio/modeling_qwen.py","file_url":"https://github.com/yichen14/FastAdaSP/blob/HEAD/Qwen-Audio/modeling_qwen.py","link_basis":"plan_row","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":"1fec7a76f0d171a6"}},{"code_sha256_prefix":"fbda921818ec02df","entry":"apply_rotary_pos_emb","repo":"yichen14/FastAdaSP","repo_kind":"official","path":"Qwen-Audio/modeling_qwen.py","file_url":"https://github.com/yichen14/FastAdaSP/blob/HEAD/Qwen-Audio/modeling_qwen.py","link_basis":"plan_row","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":"fbda921818ec02df"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}