{"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/robust-speech-recognition-via-large-scale-1","title":"Robust Speech Recognition via Large-Scale Weak Supervision","arxiv_id":"2212.04356","date":"2022-12-06","proceeding":"Preprint 2022 9","authors":["Alec Radford","Jong Wook Kim","Tao Xu","Greg Brockman","Christine McLeavey","Ilya Sutskever"],"abstract":"We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zero-shot transfer setting without the need for any fine-tuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.","url_abs":"https://arxiv.org/abs/2212.04356v1","url_pdf":"https://arxiv.org/pdf/2212.04356v1.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":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/openai/whisper","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/audioshake/alt-eval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/briansidp/whisperbiasing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/collabora/whisperlive","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/collabora/whisperspeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/k2-fsa/icefall","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/kadirnar/whisper-plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/open-creator/icefall","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/robflynnyh/long-context-asr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/sanchit-gandhi/whisper-jax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/whisperspeech/whisperspeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/ggerganov/whisper.cpp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/m-bain/whisperx","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"robust-speech-recognition-via-large-scale-1","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/1/whisper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"robust-speech-recognition","task_name":"Robust Speech Recognition"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-to-speech-translation","task_name":"Speech-to-Speech Translation"},{"task_slug":"zero-shot-audio-retrieval","task_name":"Zero-Shot Audio Retrieval"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-common-voice-english","task":"Speech Recognition","dataset":"Common Voice English","model":"Whisper (Large v2)","rank_in_archive_order":2,"of":2,"metrics":{"Word Error Rate (WER)":"9.4%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-french","task":"Speech Recognition","dataset":"Common Voice French","model":"Whisper (Large v2)","rank_in_archive_order":8,"of":8,"metrics":{"Test WER":"13.9%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-german","task":"Speech Recognition","dataset":"Common Voice German","model":"Whisper (Large v2)","rank_in_archive_order":7,"of":14,"metrics":{"Test WER":"6.4%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-italian","task":"Speech Recognition","dataset":"Common Voice Italian","model":"Whisper (Large v2)","rank_in_archive_order":1,"of":2,"metrics":{"Test WER":"7.1%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-japanese","task":"Speech Recognition","dataset":"Common Voice Japanese","model":"Whisper (Large v2)","rank_in_archive_order":1,"of":1,"metrics":{"Test WER":"9.1%"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-common-voice-russian","task":"Speech Recognition","dataset":"Common Voice Russian","model":"Whisper (Large v2)","rank_in_archive_order":1,"of":1,"metrics":{"Test WER":"7.1%"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-common-voice-spanish","task":"Speech Recognition","dataset":"Common Voice Spanish","model":"Whisper (Large v2)","rank_in_archive_order":2,"of":8,"metrics":{"Test WER":"5.6%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-to-speech-translation-on-fleurs-x-eng","task":"Speech-to-Speech Translation","dataset":"FLEURS X-eng","model":"WhisperV2","rank_in_archive_order":6,"of":7,"metrics":{"ASR-BLEU":"23.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.04356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04356"}},"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/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/k2-fsa/icefall","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/whisperspeech/whisperspeech","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sanchit-gandhi/whisper-jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/briansidp/whisperbiasing","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/audioshake/alt-eval","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ggerganov/whisper.cpp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/collabora/whisperlive","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/1/whisper","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-creator/icefall","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/robflynnyh/long-context-asr","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kadirnar/whisper-plus","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/m-bain/whisperx","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/collabora/whisperspeech","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openai/whisper","reach":null}],"summary":{"ran":1,"ran_honours":2,"ran_fixture":1,"ran_draft_wrong":1,"unverified":54},"by_repo_kind":{"listed":{"samples":58,"ran":4,"repositories":9}},"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":18,"samples":[{"code_sha256_prefix":"2000f34f95c683d6","entry":"dot_product_attention","repo":"sanchit-gandhi/whisper-jax","repo_kind":"listed","path":"whisper_jax/layers.py","file_url":"https://github.com/sanchit-gandhi/whisper-jax/blob/HEAD/whisper_jax/layers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2000f34f95c683d6"}},{"code_sha256_prefix":"6e0808fc4828513a","entry":"exact_div","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"whisper/utils.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"6e0808fc4828513a"}},{"code_sha256_prefix":"8a8edc42e5e25cea","entry":"logits_to_probs","repo":"whisperspeech/whisperspeech","repo_kind":"listed","path":"whisperspeech/inference.py","file_url":"https://github.com/whisperspeech/whisperspeech/blob/HEAD/whisperspeech/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a8edc42e5e25cea"}},{"code_sha256_prefix":"0b5f90e8856ad7af","entry":"multinomial_sample_one_no_sync","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"0b5f90e8856ad7af"}},{"code_sha256_prefix":"e529c9641c178fe0","entry":"sinusoids","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"whisper/model.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/model.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e529c9641c178fe0"}},{"code_sha256_prefix":"6ecbcf4f3d00f7ed","entry":"LinearActivation","repo":"robflynnyh/long-context-asr","repo_kind":"listed","path":"lcasr/components/long_conv.py","file_url":"https://github.com/robflynnyh/long-context-asr/blob/HEAD/lcasr/components/long_conv.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":"6ecbcf4f3d00f7ed"}},{"code_sha256_prefix":"5969d689c8a84ef2","entry":"attach_diagnostics","repo":"open-creator/icefall","repo_kind":"listed","path":"icefall/diagnostics.py","file_url":"https://github.com/open-creator/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":"5969d689c8a84ef2"}},{"code_sha256_prefix":"69124b03f4b749bd","entry":"average_checkpoints","repo":"open-creator/icefall","repo_kind":"listed","path":"icefall/checkpoint.py","file_url":"https://github.com/open-creator/icefall/blob/HEAD/icefall/checkpoint.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":"69124b03f4b749bd"}},{"code_sha256_prefix":"41c654294ba9ec56","entry":"backtrace","repo":"kadirnar/whisper-plus","repo_kind":"listed","path":"whisperplus/pipelines/lightning_whisper_mlx/timing.py","file_url":"https://github.com/kadirnar/whisper-plus/blob/HEAD/whisperplus/pipelines/lightning_whisper_mlx/timing.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":"41c654294ba9ec56"}},{"code_sha256_prefix":"3787ac531561b6c6","entry":"blank_p","repo":"robflynnyh/long-context-asr","repo_kind":"listed","path":"exp/train_utterance_meta_loss_pred.py","file_url":"https://github.com/robflynnyh/long-context-asr/blob/HEAD/exp/train_utterance_meta_loss_pred.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":"3787ac531561b6c6"}},{"code_sha256_prefix":"9f16788e5da13dfa","entry":"blank_p","repo":"robflynnyh/long-context-asr","repo_kind":"listed","path":"exp/train_utterance_meta_loss_pred_ce.py","file_url":"https://github.com/robflynnyh/long-context-asr/blob/HEAD/exp/train_utterance_meta_loss_pred_ce.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":"9f16788e5da13dfa"}},{"code_sha256_prefix":"acb6a55d43c7f465","entry":"build_tokenizer","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"whisper/tokenizer.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/tokenizer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"acb6a55d43c7f465"}},{"code_sha256_prefix":"59d410aa19bdef96","entry":"byte_decode","repo":"open-creator/icefall","repo_kind":"listed","path":"icefall/byte_utils.py","file_url":"https://github.com/open-creator/icefall/blob/HEAD/icefall/byte_utils.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":"59d410aa19bdef96"}},{"code_sha256_prefix":"004eb0067bd43754","entry":"byte_encode","repo":"open-creator/icefall","repo_kind":"listed","path":"icefall/byte_utils.py","file_url":"https://github.com/open-creator/icefall/blob/HEAD/icefall/byte_utils.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":"004eb0067bd43754"}},{"code_sha256_prefix":"9140147b0fd2c440","entry":"check_if_already_evaluated","repo":"robflynnyh/long-context-asr","repo_kind":"listed","path":"eval/eval_manager.py","file_url":"https://github.com/robflynnyh/long-context-asr/blob/HEAD/eval/eval_manager.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":"9140147b0fd2c440"}},{"code_sha256_prefix":"fa47326ca5e0886b","entry":"check_in_utt","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"dataloader.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/dataloader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"fa47326ca5e0886b"}},{"code_sha256_prefix":"c4c3b54ad53b1fce","entry":"collate_wrapper","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"dataloader.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/dataloader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"c4c3b54ad53b1fce"}},{"code_sha256_prefix":"5632d6609129dfa3","entry":"compression_ratio","repo":"kadirnar/whisper-plus","repo_kind":"listed","path":"whisperplus/pipelines/lightning_whisper_mlx/decoding.py","file_url":"https://github.com/kadirnar/whisper-plus/blob/HEAD/whisperplus/pipelines/lightning_whisper_mlx/decoding.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":"5632d6609129dfa3"}},{"code_sha256_prefix":"8a64b592c82c0d10","entry":"convert_alignments_to_tensor","repo":"open-creator/icefall","repo_kind":"listed","path":"icefall/ali.py","file_url":"https://github.com/open-creator/icefall/blob/HEAD/icefall/ali.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":"8a64b592c82c0d10"}},{"code_sha256_prefix":"b41e987fee8a92ff","entry":"correct_for_bias_scale_order_inversion","repo":"ggerganov/whisper.cpp","repo_kind":"listed","path":"models/convert-whisper-to-coreml.py","file_url":"https://github.com/ggerganov/whisper.cpp/blob/HEAD/models/convert-whisper-to-coreml.py","link_basis":"harvester_set","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":"b41e987fee8a92ff"}},{"code_sha256_prefix":"76330ed965e60af5","entry":"dtw_cpu","repo":"kadirnar/whisper-plus","repo_kind":"listed","path":"whisperplus/pipelines/lightning_whisper_mlx/timing.py","file_url":"https://github.com/kadirnar/whisper-plus/blob/HEAD/whisperplus/pipelines/lightning_whisper_mlx/timing.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":"76330ed965e60af5"}},{"code_sha256_prefix":"87c9b24deaf27799","entry":"find_checkpoints","repo":"open-creator/icefall","repo_kind":"listed","path":"icefall/checkpoint.py","file_url":"https://github.com/open-creator/icefall/blob/HEAD/icefall/checkpoint.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":"87c9b24deaf27799"}},{"code_sha256_prefix":"9649e15864c56627","entry":"format_time","repo":"collabora/whisperlive","repo_kind":"listed","path":"whisper_live/utils.py","file_url":"https://github.com/collabora/whisperlive/blob/HEAD/whisper_live/utils.py","link_basis":"harvester_set","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":"9649e15864c56627"}},{"code_sha256_prefix":"fef7828e835c938d","entry":"generate","repo":"ggerganov/whisper.cpp","repo_kind":"listed","path":"models/generate-parakeet-test-model.py","file_url":"https://github.com/ggerganov/whisper.cpp/blob/HEAD/models/generate-parakeet-test-model.py","link_basis":"harvester_set","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":"fef7828e835c938d"}},{"code_sha256_prefix":"63302892207b7f5b","entry":"get_args","repo":"robflynnyh/long-context-asr","repo_kind":"listed","path":"eval/eval_manager.py","file_url":"https://github.com/robflynnyh/long-context-asr/blob/HEAD/eval/eval_manager.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":"63302892207b7f5b"}},{"code_sha256_prefix":"b865558252e1566a","entry":"get_class_name","repo":"open-creator/icefall","repo_kind":"listed","path":"icefall/diagnostics.py","file_url":"https://github.com/open-creator/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":"ae28fa768d63729b","entry":"get_data_to_save","repo":"robflynnyh/long-context-asr","repo_kind":"listed","path":"eval/eval_manager.py","file_url":"https://github.com/robflynnyh/long-context-asr/blob/HEAD/eval/eval_manager.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":"ae28fa768d63729b"}},{"code_sha256_prefix":"ad63708b6da385d5","entry":"get_dtype","repo":"robflynnyh/long-context-asr","repo_kind":"listed","path":"exp/train_utterance_meta_loss_pred.py","file_url":"https://github.com/robflynnyh/long-context-asr/blob/HEAD/exp/train_utterance_meta_loss_pred.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":"ad63708b6da385d5"}},{"code_sha256_prefix":"b3916c1b2edcf996","entry":"get_encoding","repo":"kadirnar/whisper-plus","repo_kind":"listed","path":"whisperplus/pipelines/lightning_whisper_mlx/tokenizer.py","file_url":"https://github.com/kadirnar/whisper-plus/blob/HEAD/whisperplus/pipelines/lightning_whisper_mlx/tokenizer.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":"b3916c1b2edcf996"}},{"code_sha256_prefix":"ee3c8d2a605ac8bc","entry":"get_initializer","repo":"robflynnyh/long-context-asr","repo_kind":"listed","path":"lcasr/components/long_conv.py","file_url":"https://github.com/robflynnyh/long-context-asr/blob/HEAD/lcasr/components/long_conv.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":"ee3c8d2a605ac8bc"}},{"code_sha256_prefix":"a5b8c22a3ac7b238","entry":"get_short_name","repo":"ggerganov/whisper.cpp","repo_kind":"listed","path":"ggml/src/ggml-cuda/template-instances/generate_cu_files.py","file_url":"https://github.com/ggerganov/whisper.cpp/blob/HEAD/ggml/src/ggml-cuda/template-instances/generate_cu_files.py","link_basis":"harvester_set","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":"a5b8c22a3ac7b238"}},{"code_sha256_prefix":"d1162925e2d53784","entry":"get_tensor_stats","repo":"open-creator/icefall","repo_kind":"listed","path":"icefall/diagnostics.py","file_url":"https://github.com/open-creator/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":"d1162925e2d53784"}},{"code_sha256_prefix":"f2f52f6a90834243","entry":"get_tokenizer","repo":"kadirnar/whisper-plus","repo_kind":"listed","path":"whisperplus/pipelines/lightning_whisper_mlx/tokenizer.py","file_url":"https://github.com/kadirnar/whisper-plus/blob/HEAD/whisperplus/pipelines/lightning_whisper_mlx/tokenizer.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":"f2f52f6a90834243"}},{"code_sha256_prefix":"9720e570a35f6d55","entry":"hz_to_mel","repo":"ggerganov/whisper.cpp","repo_kind":"listed","path":"models/convert-parakeet-to-ggml.py","file_url":"https://github.com/ggerganov/whisper.cpp/blob/HEAD/models/convert-parakeet-to-ggml.py","link_basis":"harvester_set","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":"9720e570a35f6d55"}},{"code_sha256_prefix":"a799a46446fafd99","entry":"laplace","repo":"robflynnyh/long-context-asr","repo_kind":"listed","path":"lcasr/components/long_conv.py","file_url":"https://github.com/robflynnyh/long-context-asr/blob/HEAD/lcasr/components/long_conv.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":"a799a46446fafd99"}},{"code_sha256_prefix":"a972a5df2771f7a5","entry":"load_alignments","repo":"open-creator/icefall","repo_kind":"listed","path":"icefall/ali.py","file_url":"https://github.com/open-creator/icefall/blob/HEAD/icefall/ali.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":"a972a5df2771f7a5"}},{"code_sha256_prefix":"34dd5baae0e5830e","entry":"load_audio","repo":"collabora/whisperlive","repo_kind":"listed","path":"whisper_live/diarization.py","file_url":"https://github.com/collabora/whisperlive/blob/HEAD/whisper_live/diarization.py","link_basis":"harvester_set","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":"34dd5baae0e5830e"}},{"code_sha256_prefix":"ba1be9f251ecd80a","entry":"load_model_config","repo":"ggerganov/whisper.cpp","repo_kind":"listed","path":"models/convert-parakeet-to-ggml.py","file_url":"https://github.com/ggerganov/whisper.cpp/blob/HEAD/models/convert-parakeet-to-ggml.py","link_basis":"harvester_set","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":"ba1be9f251ecd80a"}},{"code_sha256_prefix":"a1f5678203ff47e8","entry":"lookup_alignments","repo":"open-creator/icefall","repo_kind":"listed","path":"icefall/ali.py","file_url":"https://github.com/open-creator/icefall/blob/HEAD/icefall/ali.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":"a1f5678203ff47e8"}},{"code_sha256_prefix":"c45f3b632ec36534","entry":"make_lexical_tree","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"dataloader.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/dataloader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"c45f3b632ec36534"}},{"code_sha256_prefix":"6f669ba80cbbf823","entry":"median_filter","repo":"kadirnar/whisper-plus","repo_kind":"listed","path":"whisperplus/pipelines/lightning_whisper_mlx/timing.py","file_url":"https://github.com/kadirnar/whisper-plus/blob/HEAD/whisperplus/pipelines/lightning_whisper_mlx/timing.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":"6f669ba80cbbf823"}},{"code_sha256_prefix":"edf924293b4b2375","entry":"mel_filters","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"whisper/audio.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"edf924293b4b2375"}},{"code_sha256_prefix":"40e421c01b760f1c","entry":"mel_to_hz","repo":"ggerganov/whisper.cpp","repo_kind":"listed","path":"models/convert-parakeet-to-ggml.py","file_url":"https://github.com/ggerganov/whisper.cpp/blob/HEAD/models/convert-parakeet-to-ggml.py","link_basis":"harvester_set","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":"40e421c01b760f1c"}},{"code_sha256_prefix":"c4ee356de1bd8c77","entry":"normalize_lyrics","repo":"audioshake/alt-eval","repo_kind":"listed","path":"src/alt_eval/normalization.py","file_url":"https://github.com/audioshake/alt-eval/blob/HEAD/src/alt_eval/normalization.py","link_basis":"harvester_set","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":"c4ee356de1bd8c77"}},{"code_sha256_prefix":"e56996b20b9c19cb","entry":"optional_int","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"whisper/utils.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e56996b20b9c19cb"}},{"code_sha256_prefix":"9f13de1c23e4003d","entry":"pad_or_trim","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"whisper/audio.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"9f13de1c23e4003d"}},{"code_sha256_prefix":"87bdf3970749dc11","entry":"pjit","repo":"sanchit-gandhi/whisper-jax","repo_kind":"listed","path":"whisper_jax/partitioner.py","file_url":"https://github.com/sanchit-gandhi/whisper-jax/blob/HEAD/whisper_jax/partitioner.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":false,"mcp_get_code":{"code_sha256":"87bdf3970749dc11"}},{"code_sha256_prefix":"d35e5ea9b14ce05e","entry":"pjit_with_cpu_fallback","repo":"sanchit-gandhi/whisper-jax","repo_kind":"listed","path":"whisper_jax/partitioner.py","file_url":"https://github.com/sanchit-gandhi/whisper-jax/blob/HEAD/whisper_jax/partitioner.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":false,"mcp_get_code":{"code_sha256":"d35e5ea9b14ce05e"}},{"code_sha256_prefix":"2206d84b6900ab3e","entry":"remove_symbols","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"whisper/normalizers/basic.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/normalizers/basic.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"2206d84b6900ab3e"}},{"code_sha256_prefix":"cef27f679a755971","entry":"remove_symbols_and_diacritics","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"whisper/normalizers/basic.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/normalizers/basic.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"cef27f679a755971"}},{"code_sha256_prefix":"e65744d3337badd5","entry":"rename_keys","repo":"ggerganov/whisper.cpp","repo_kind":"listed","path":"models/convert-h5-to-coreml.py","file_url":"https://github.com/ggerganov/whisper.cpp/blob/HEAD/models/convert-h5-to-coreml.py","link_basis":"harvester_set","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":"e65744d3337badd5"}},{"code_sha256_prefix":"bdbf18d0ee9006f7","entry":"rgetattr","repo":"robflynnyh/long-context-asr","repo_kind":"listed","path":"exp/run_launcher.py","file_url":"https://github.com/robflynnyh/long-context-asr/blob/HEAD/exp/run_launcher.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":"bdbf18d0ee9006f7"}},{"code_sha256_prefix":"407b4297398ff29d","entry":"sinusoids","repo":"kadirnar/whisper-plus","repo_kind":"listed","path":"whisperplus/pipelines/lightning_whisper_mlx/torch_whisper.py","file_url":"https://github.com/kadirnar/whisper-plus/blob/HEAD/whisperplus/pipelines/lightning_whisper_mlx/torch_whisper.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":"407b4297398ff29d"}},{"code_sha256_prefix":"226350299950338b","entry":"smart_byte_decode","repo":"open-creator/icefall","repo_kind":"listed","path":"icefall/byte_utils.py","file_url":"https://github.com/open-creator/icefall/blob/HEAD/icefall/byte_utils.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":"226350299950338b"}},{"code_sha256_prefix":"176b6ba6c2c2940c","entry":"str2bool","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"whisper/utils.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"176b6ba6c2c2940c"}},{"code_sha256_prefix":"2ef9c9c7ee284aaf","entry":"to_rich_tokens","repo":"audioshake/alt-eval","repo_kind":"listed","path":"src/alt_eval/tokenizer.py","file_url":"https://github.com/audioshake/alt-eval/blob/HEAD/src/alt_eval/tokenizer.py","link_basis":"harvester_set","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":"2ef9c9c7ee284aaf"}},{"code_sha256_prefix":"3d1de040cc006f6a","entry":"tokens_as_words","repo":"audioshake/alt-eval","repo_kind":"listed","path":"src/alt_eval/tokenizer.py","file_url":"https://github.com/audioshake/alt-eval/blob/HEAD/src/alt_eval/tokenizer.py","link_basis":"harvester_set","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":"3d1de040cc006f6a"}},{"code_sha256_prefix":"738c6e74fd16381d","entry":"transcribe","repo":"briansidp/whisperbiasing","repo_kind":"listed","path":"whisper/transcribe.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/transcribe.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"738c6e74fd16381d"}},{"code_sha256_prefix":"e5a9a9806511efb5","entry":"with_sharding_constraint","repo":"sanchit-gandhi/whisper-jax","repo_kind":"listed","path":"whisper_jax/partitioner.py","file_url":"https://github.com/sanchit-gandhi/whisper-jax/blob/HEAD/whisper_jax/partitioner.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":false,"mcp_get_code":{"code_sha256":"e5a9a9806511efb5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}