{"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/torchaudio-2-1-advancing-speech-recognition","title":"TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch","arxiv_id":"2310.17864","date":"2023-10-27","proceeding":null,"authors":["Jeff Hwang","Moto Hira","Caroline Chen","Xiaohui Zhang","Zhaoheng Ni","Guangzhi Sun","Pingchuan Ma","Ruizhe Huang","Vineel Pratap","Yuekai Zhang","Anurag Kumar","Chin-Yun Yu","Chuang Zhu","Chunxi Liu","Jacob Kahn","Mirco Ravanelli","Peng Sun","Shinji Watanabe","Yangyang Shi","Yumeng Tao","Robin Scheibler","Samuele Cornell","Sean Kim","Stavros Petridis"],"abstract":"TorchAudio is an open-source audio and speech processing library built for PyTorch. It aims to accelerate the research and development of audio and speech technologies by providing well-designed, easy-to-use, and performant PyTorch components. Its contributors routinely engage with users to understand their needs and fulfill them by developing impactful features. Here, we survey TorchAudio's development principles and contents and highlight key features we include in its latest version (2.1): self-supervised learning pre-trained pipelines and training recipes, high-performance CTC decoders, speech recognition models and training recipes, advanced media I/O capabilities, and tools for performing forced alignment, multi-channel speech enhancement, and reference-less speech assessment. For a selection of these features, through empirical studies, we demonstrate their efficacy and show that they achieve competitive or state-of-the-art performance.","url_abs":"https://arxiv.org/abs/2310.17864v1","url_pdf":"https://arxiv.org/pdf/2310.17864v1.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":"torchaudio-2-1-advancing-speech-recognition","repo_url":"https://github.com/pytorch/audio","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":null,"method_name":"Library"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.17864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17864"}},"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/pytorch/audio","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"ran":5,"unverified":5},"by_repo_kind":{"official":{"samples":10,"ran":5,"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":"25d33eba42f595af","entry":"eval_env","repo":"pytorch/audio","repo_kind":"official","path":"src/torchaudio/_internal/module_utils.py","file_url":"https://github.com/pytorch/audio/blob/HEAD/src/torchaudio/_internal/module_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"25d33eba42f595af"}},{"code_sha256_prefix":"a62536e09f055a5f","entry":"fail_with_message","repo":"pytorch/audio","repo_kind":"official","path":"src/torchaudio/_internal/module_utils.py","file_url":"https://github.com/pytorch/audio/blob/HEAD/src/torchaudio/_internal/module_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a62536e09f055a5f"}},{"code_sha256_prefix":"0f943f916295a5a2","entry":"inverse_mel_scale_scalar","repo":"pytorch/audio","repo_kind":"official","path":"src/torchaudio/compliance/kaldi.py","file_url":"https://github.com/pytorch/audio/blob/HEAD/src/torchaudio/compliance/kaldi.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0f943f916295a5a2"}},{"code_sha256_prefix":"cfa503d2d20f62b7","entry":"no_op","repo":"pytorch/audio","repo_kind":"official","path":"src/torchaudio/_internal/module_utils.py","file_url":"https://github.com/pytorch/audio/blob/HEAD/src/torchaudio/_internal/module_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cfa503d2d20f62b7"}},{"code_sha256_prefix":"4aab9a5564103eaf","entry":"spectrogram","repo":"pytorch/audio","repo_kind":"official","path":"src/torchaudio/compliance/kaldi.py","file_url":"https://github.com/pytorch/audio/blob/HEAD/src/torchaudio/compliance/kaldi.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4aab9a5564103eaf"}},{"code_sha256_prefix":"57cb0e041c9b422c","entry":"get_labels","repo":"pytorch/audio","repo_kind":"official","path":".github/process_commit.py","file_url":"https://github.com/pytorch/audio/blob/HEAD/.github/process_commit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"57cb0e041c9b422c"}},{"code_sha256_prefix":"9eaef367a8dc3018","entry":"get_pr_merger_and_number","repo":"pytorch/audio","repo_kind":"official","path":".github/process_commit.py","file_url":"https://github.com/pytorch/audio/blob/HEAD/.github/process_commit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9eaef367a8dc3018"}},{"code_sha256_prefix":"cd99ee7d35201131","entry":"inverse_mel_scale","repo":"pytorch/audio","repo_kind":"official","path":"src/torchaudio/compliance/kaldi.py","file_url":"https://github.com/pytorch/audio/blob/HEAD/src/torchaudio/compliance/kaldi.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cd99ee7d35201131"}},{"code_sha256_prefix":"48b991de09c22d05","entry":"load_with_torchcodec","repo":"pytorch/audio","repo_kind":"official","path":"src/torchaudio/_torchcodec.py","file_url":"https://github.com/pytorch/audio/blob/HEAD/src/torchaudio/_torchcodec.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"48b991de09c22d05"}},{"code_sha256_prefix":"087f9d0ce1b3f939","entry":"query_torchaudio","repo":"pytorch/audio","repo_kind":"official","path":".github/process_commit.py","file_url":"https://github.com/pytorch/audio/blob/HEAD/.github/process_commit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"087f9d0ce1b3f939"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}