{"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/moonshine-speech-recognition-for-live","title":"Moonshine: Speech Recognition for Live Transcription and Voice Commands","arxiv_id":"2410.15608","date":"2024-10-21","proceeding":null,"authors":["Nat Jeffries","Evan King","Manjunath Kudlur","Guy Nicholson","James Wang","Pete Warden"],"abstract":"This paper introduces Moonshine, a family of speech recognition models optimized for live transcription and voice command processing. Moonshine is based on an encoder-decoder transformer architecture and employs Rotary Position Embedding (RoPE) instead of traditional absolute position embeddings. The model is trained on speech segments of various lengths, but without using zero-padding, leading to greater efficiency for the encoder during inference time. When benchmarked against OpenAI's Whisper tiny-en, Moonshine Tiny demonstrates a 5x reduction in compute requirements for transcribing a 10-second speech segment while incurring no increase in word error rates across standard evaluation datasets. These results highlight Moonshine's potential for real-time and resource-constrained applications.","url_abs":"https://arxiv.org/abs/2410.15608v2","url_pdf":"https://arxiv.org/pdf/2410.15608v2.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":"moonshine-speech-recognition-for-live","repo_url":"https://github.com/usefulsensors/moonshine","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":null,"task_name":"Position"},{"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/2410.15608","atlas_url":"https://app.syntology.ai/?focus=2410.15608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15608"}},"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/usefulsensors/moonshine","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"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":8,"samples":[{"code_sha256_prefix":"fab9f7d50af01a81","entry":"crc32c_file","repo":"usefulsensors/moonshine","repo_kind":"official","path":"language-bindings/python/src/moonshine_voice/download_file.py","file_url":"https://github.com/usefulsensors/moonshine/blob/HEAD/language-bindings/python/src/moonshine_voice/download_file.py","link_basis":"plan_row","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":"fab9f7d50af01a81"}},{"code_sha256_prefix":"d216fc2ce888c4e8","entry":"get_cache_dir","repo":"usefulsensors/moonshine","repo_kind":"official","path":"language-bindings/python/src/moonshine_voice/download_file.py","file_url":"https://github.com/usefulsensors/moonshine/blob/HEAD/language-bindings/python/src/moonshine_voice/download_file.py","link_basis":"plan_row","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":"d216fc2ce888c4e8"}},{"code_sha256_prefix":"4dd63075dea3762c","entry":"hash_file","repo":"usefulsensors/moonshine","repo_kind":"official","path":"language-bindings/python/src/moonshine_voice/download_file.py","file_url":"https://github.com/usefulsensors/moonshine/blob/HEAD/language-bindings/python/src/moonshine_voice/download_file.py","link_basis":"plan_row","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":"4dd63075dea3762c"}},{"code_sha256_prefix":"c0b8d2436a8e0deb","entry":"model_arch_to_string","repo":"usefulsensors/moonshine","repo_kind":"official","path":"language-bindings/python/src/moonshine_voice/moonshine_api.py","file_url":"https://github.com/usefulsensors/moonshine/blob/HEAD/language-bindings/python/src/moonshine_voice/moonshine_api.py","link_basis":"plan_row","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":"c0b8d2436a8e0deb"}},{"code_sha256_prefix":"9a27c4a8b45fda56","entry":"moonshine_options_array","repo":"usefulsensors/moonshine","repo_kind":"official","path":"language-bindings/python/src/moonshine_voice/moonshine_api.py","file_url":"https://github.com/usefulsensors/moonshine/blob/HEAD/language-bindings/python/src/moonshine_voice/moonshine_api.py","link_basis":"plan_row","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":"9a27c4a8b45fda56"}},{"code_sha256_prefix":"c1f6d9a28c7f13f2","entry":"spoken_form","repo":"usefulsensors/moonshine","repo_kind":"official","path":"language-bindings/python/src/moonshine_voice/alphanumeric_listener.py","file_url":"https://github.com/usefulsensors/moonshine/blob/HEAD/language-bindings/python/src/moonshine_voice/alphanumeric_listener.py","link_basis":"plan_row","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":"c1f6d9a28c7f13f2"}},{"code_sha256_prefix":"efd406f04b8eba8f","entry":"string_to_model_arch","repo":"usefulsensors/moonshine","repo_kind":"official","path":"language-bindings/python/src/moonshine_voice/moonshine_api.py","file_url":"https://github.com/usefulsensors/moonshine/blob/HEAD/language-bindings/python/src/moonshine_voice/moonshine_api.py","link_basis":"plan_row","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":"efd406f04b8eba8f"}},{"code_sha256_prefix":"0d4210a3940c2807","entry":"write_cached_embeddings_tsv","repo":"usefulsensors/moonshine","repo_kind":"official","path":"language-bindings/python/src/moonshine_voice/cached_embeddings.py","file_url":"https://github.com/usefulsensors/moonshine/blob/HEAD/language-bindings/python/src/moonshine_voice/cached_embeddings.py","link_basis":"plan_row","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":"0d4210a3940c2807"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}