{"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/mini-omni2-towards-open-source-gpt-4o-model","title":"Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities","arxiv_id":"2410.11190","date":"2024-10-15","proceeding":null,"authors":["Zhifei Xie","Changqiao Wu"],"abstract":"GPT-4o, an all-encompassing model, represents a milestone in the development of large multi-modal language models. It can understand visual, auditory, and textual modalities, directly output audio, and support flexible duplex interaction. Models from the open-source community often achieve some functionalities of GPT-4o, such as visual understanding and voice chat. Nevertheless, training a unified model that incorporates all modalities is challenging due to the complexities of multi-modal data, intricate model architectures, and training processes. In this paper, we introduce Mini-Omni2, a visual-audio assistant capable of providing real-time, end-to-end voice responses to visoin and audio queries. By integrating pretrained visual and auditory encoders, Mini-Omni2 maintains performance in individual modalities. We propose a three-stage training process to align modalities, allowing the language model to handle multi-modal inputs and outputs after training on a limited dataset. For interaction, we introduce a command-based interruption mechanism, enabling more flexible interaction with users. To the best of our knowledge, Mini-Omni2 is one of the closest reproductions of GPT-4o, which have similar form of functionality, and we hope it can offer valuable insights for subsequent research.","url_abs":"https://arxiv.org/abs/2410.11190v3","url_pdf":"https://arxiv.org/pdf/2410.11190v3.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":"mini-omni2-towards-open-source-gpt-4o-model","repo_url":"https://github.com/gpt-omni/mini-omni2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.11190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11190"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gpt-omni/mini-omni2","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":2,"ran":9,"unverified":3},"by_repo_kind":{"official":{"samples":14,"ran":11,"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":"aa32c6faaa562b69","entry":"apply_rope","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"litgpt/model.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/litgpt/model.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa32c6faaa562b69"}},{"code_sha256_prefix":"7ee1c3ba71156110","entry":"build_mask_cache","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"litgpt/model.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/litgpt/model.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7ee1c3ba71156110"}},{"code_sha256_prefix":"847a58dff80851e5","entry":"collect_chunks","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"utils/vad.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/utils/vad.py","link_basis":"first_harvest_node","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":"847a58dff80851e5"}},{"code_sha256_prefix":"f5d9c92914e0ccfa","entry":"find_multiple","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"litgpt/utils.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/litgpt/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f5d9c92914e0ccfa"}},{"code_sha256_prefix":"9b5c939537b0e38c","entry":"find_resume_path","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"litgpt/utils.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/litgpt/utils.py","link_basis":"first_harvest_node","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":"9b5c939537b0e38c"}},{"code_sha256_prefix":"641d60a367fa3083","entry":"get_snac","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"utils/snac_utils.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/utils/snac_utils.py","link_basis":"first_harvest_node","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":"641d60a367fa3083"}},{"code_sha256_prefix":"615c2d6183fce709","entry":"init_out_dir","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"litgpt/utils.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/litgpt/utils.py","link_basis":"first_harvest_node","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":"615c2d6183fce709"}},{"code_sha256_prefix":"eba9e8fbcfaae4be","entry":"layershift","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"utils/snac_utils.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/utils/snac_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eba9e8fbcfaae4be"}},{"code_sha256_prefix":"17e4446536a73126","entry":"multinomial_num_samples_1","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"litgpt/generate/base.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/litgpt/generate/base.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"17e4446536a73126"}},{"code_sha256_prefix":"62b68fa657c0d6eb","entry":"sample","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"litgpt/generate/base.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/litgpt/generate/base.py","link_basis":"first_harvest_node","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":"62b68fa657c0d6eb"}},{"code_sha256_prefix":"a2d9cc3c4221f547","entry":"sample_top_p","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"litgpt/generate/base.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/litgpt/generate/base.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2d9cc3c4221f547"}},{"code_sha256_prefix":"c0cabd60c81402a5","entry":"build_rope_cache","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"litgpt/model.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/litgpt/model.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0cabd60c81402a5"}},{"code_sha256_prefix":"1d7eb4c029d371bd","entry":"generate_audio_data","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"utils/snac_utils.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/utils/snac_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d7eb4c029d371bd"}},{"code_sha256_prefix":"f8e3df53ca30326f","entry":"get_speech_timestamps","repo":"gpt-omni/mini-omni2","repo_kind":"official","path":"utils/vad.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/utils/vad.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f8e3df53ca30326f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}