{"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/llama-omni2-llm-based-real-time-spoken","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","arxiv_id":"2505.02625","date":"2025-05-05","proceeding":null,"authors":["Qingkai Fang","Yan Zhou","Shoutao Guo","Shaolei Zhang","Yang Feng"],"abstract":"Real-time, intelligent, and natural speech interaction is an essential part of the next-generation human-computer interaction. Recent advancements have showcased the potential of building intelligent spoken chatbots based on large language models (LLMs). In this paper, we introduce LLaMA-Omni 2, a series of speech language models (SpeechLMs) ranging from 0.5B to 14B parameters, capable of achieving high-quality real-time speech interaction. LLaMA-Omni 2 is built upon the Qwen2.5 series models, integrating a speech encoder and an autoregressive streaming speech decoder. Despite being trained on only 200K multi-turn speech dialogue samples, LLaMA-Omni 2 demonstrates strong performance on several spoken question answering and speech instruction following benchmarks, surpassing previous state-of-the-art SpeechLMs like GLM-4-Voice, which was trained on millions of hours of speech data.","url_abs":"https://arxiv.org/abs/2505.02625v1","url_pdf":"https://arxiv.org/pdf/2505.02625v1.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":"llama-omni2-llm-based-real-time-spoken","repo_url":"https://github.com/ictnlp/llama-omni2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"llama-omni2-llm-based-real-time-spoken","repo_url":"https://github.com/rainbowluocs/openomni","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"chatbot","task_name":"Chatbot"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.02625","atlas_url":"https://app.syntology.ai/?focus=2505.02625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02625"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rainbowluocs/openomni","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ictnlp/llama-omni2","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/openai/whisper","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/tarepan/SpeechMOS","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":2,"ran_fixture":3,"unverified":2},"by_repo_kind":{"listed":{"samples":10,"ran":8,"repositories":1},"found_in_text":{"samples":1,"ran":1,"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":10,"samples":[{"code_sha256_prefix":"d5a46d215b2b4700","entry":"CrossAttention","repo":"rainbowluocs/openomni","repo_kind":"listed","path":"openomni/model/speech_generator_ar/speech_generator.py","file_url":"https://github.com/rainbowluocs/openomni/blob/HEAD/openomni/model/speech_generator_ar/speech_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d5a46d215b2b4700"}},{"code_sha256_prefix":"5105747c2711b1cb","entry":"FeedForward","repo":"rainbowluocs/openomni","repo_kind":"listed","path":"openomni/model/speech_generator_ar/speech_generator.py","file_url":"https://github.com/rainbowluocs/openomni/blob/HEAD/openomni/model/speech_generator_ar/speech_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5105747c2711b1cb"}},{"code_sha256_prefix":"b21fcef2adef76c6","entry":"LabelSmoothingLoss","repo":"rainbowluocs/openomni","repo_kind":"listed","path":"openomni/model/speech_generator_ar/speech_generator.py","file_url":"https://github.com/rainbowluocs/openomni/blob/HEAD/openomni/model/speech_generator_ar/speech_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b21fcef2adef76c6"}},{"code_sha256_prefix":"755890df462a8e30","entry":"RLSIAT","repo":"rainbowluocs/openomni","repo_kind":"listed","path":"openomni/model/speech_generator_ar/speech_generator.py","file_url":"https://github.com/rainbowluocs/openomni/blob/HEAD/openomni/model/speech_generator_ar/speech_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"755890df462a8e30"}},{"code_sha256_prefix":"74f6d53ff93d8db0","entry":"lengths_to_padding_mask","repo":"rainbowluocs/openomni","repo_kind":"listed","path":"openomni/model/speech_generator_ar/speech_generator.py","file_url":"https://github.com/rainbowluocs/openomni/blob/HEAD/openomni/model/speech_generator_ar/speech_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"74f6d53ff93d8db0"}},{"code_sha256_prefix":"553c8e5537c2683d","entry":"nucleus_sampling","repo":"rainbowluocs/openomni","repo_kind":"listed","path":"openomni/model/speech_generator_ar/speech_generator.py","file_url":"https://github.com/rainbowluocs/openomni/blob/HEAD/openomni/model/speech_generator_ar/speech_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"553c8e5537c2683d"}},{"code_sha256_prefix":"49d0b5ded7a1be92","entry":"pad_to_multiple","repo":"tarepan/SpeechMOS","repo_kind":"found_in_text","path":"speechmos/utmos22/fairseq_alt.py","file_url":"https://github.com/tarepan/SpeechMOS/blob/HEAD/speechmos/utmos22/fairseq_alt.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49d0b5ded7a1be92"}},{"code_sha256_prefix":"989f0fc8f2162c7c","entry":"random_sampling","repo":"rainbowluocs/openomni","repo_kind":"listed","path":"openomni/model/speech_generator_ar/speech_generator.py","file_url":"https://github.com/rainbowluocs/openomni/blob/HEAD/openomni/model/speech_generator_ar/speech_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"989f0fc8f2162c7c"}},{"code_sha256_prefix":"326c74cdba3f656f","entry":"ras_sampling","repo":"rainbowluocs/openomni","repo_kind":"listed","path":"openomni/model/speech_generator_ar/speech_generator.py","file_url":"https://github.com/rainbowluocs/openomni/blob/HEAD/openomni/model/speech_generator_ar/speech_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"326c74cdba3f656f"}},{"code_sha256_prefix":"cc7c97831fcaf37b","entry":"Qwen2Encoder","repo":"rainbowluocs/openomni","repo_kind":"listed","path":"openomni/model/speech_generator_ar/speech_generator.py","file_url":"https://github.com/rainbowluocs/openomni/blob/HEAD/openomni/model/speech_generator_ar/speech_generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cc7c97831fcaf37b"}},{"code_sha256_prefix":"e5647dbb7cf2ccc9","entry":"SpeechGeneratorCTC","repo":"rainbowluocs/openomni","repo_kind":"listed","path":"openomni/model/speech_generator_ar/speech_generator.py","file_url":"https://github.com/rainbowluocs/openomni/blob/HEAD/openomni/model/speech_generator_ar/speech_generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e5647dbb7cf2ccc9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}