{"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/on-the-comparison-of-popular-end-to-end","title":"On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition","arxiv_id":"2005.14327","date":"2020-05-28","proceeding":null,"authors":["Jinyu Li","Yu Wu","Yashesh Gaur","Chengyi Wang","Rui Zhao","Shujie Liu"],"abstract":"Recently, there has been a strong push to transition from hybrid models to end-to-end (E2E) models for automatic speech recognition. Currently, there are three promising E2E methods: recurrent neural network transducer (RNN-T), RNN attention-based encoder-decoder (AED), and Transformer-AED. In this study, we conduct an empirical comparison of RNN-T, RNN-AED, and Transformer-AED models, in both non-streaming and streaming modes. We use 65 thousand hours of Microsoft anonymized training data to train these models. As E2E models are more data hungry, it is better to compare their effectiveness with large amount of training data. To the best of our knowledge, no such comprehensive study has been conducted yet. We show that although AED models are stronger than RNN-T in the non-streaming mode, RNN-T is very competitive in streaming mode if its encoder can be properly initialized. Among all three E2E models, transformer-AED achieved the best accuracy in both streaming and non-streaming mode. We show that both streaming RNN-T and transformer-AED models can obtain better accuracy than a highly-optimized hybrid model.","url_abs":"https://arxiv.org/abs/2005.14327v2","url_pdf":"https://arxiv.org/pdf/2005.14327v2.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":"on-the-comparison-of-popular-end-to-end","repo_url":"https://github.com/cywang97/StreamingTransformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"decoder","task_name":"Decoder"},{"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/2005.14327","atlas_url":"https://app.syntology.ai/?focus=2005.14327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14327"}},"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/cywang97/StreamingTransformer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"a935500cfe7d7229","entry":"end_detect","repo":"cywang97/StreamingTransformer","repo_kind":"official","path":"espnet/nets/e2e_asr_common.py","file_url":"https://github.com/cywang97/StreamingTransformer/blob/HEAD/espnet/nets/e2e_asr_common.py","link_basis":"first_harvest_node","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":"a935500cfe7d7229"}},{"code_sha256_prefix":"ad850df5b5596972","entry":"freq_mask","repo":"cywang97/StreamingTransformer","repo_kind":"official","path":"espnet/transform/spec_augment.py","file_url":"https://github.com/cywang97/StreamingTransformer/blob/HEAD/espnet/transform/spec_augment.py","link_basis":"first_harvest_node","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":"ad850df5b5596972"}},{"code_sha256_prefix":"22b75f86691acd2c","entry":"get_model_conf","repo":"cywang97/StreamingTransformer","repo_kind":"official","path":"espnet/asr/asr_utils.py","file_url":"https://github.com/cywang97/StreamingTransformer/blob/HEAD/espnet/asr/asr_utils.py","link_basis":"first_harvest_node","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":"22b75f86691acd2c"}},{"code_sha256_prefix":"5c4a29377fca62c3","entry":"label_smoothing_dist","repo":"cywang97/StreamingTransformer","repo_kind":"official","path":"espnet/nets/e2e_asr_common.py","file_url":"https://github.com/cywang97/StreamingTransformer/blob/HEAD/espnet/nets/e2e_asr_common.py","link_basis":"first_harvest_node","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":"5c4a29377fca62c3"}},{"code_sha256_prefix":"323a280a734e2419","entry":"time_mask","repo":"cywang97/StreamingTransformer","repo_kind":"official","path":"espnet/transform/spec_augment.py","file_url":"https://github.com/cywang97/StreamingTransformer/blob/HEAD/espnet/transform/spec_augment.py","link_basis":"first_harvest_node","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":"323a280a734e2419"}},{"code_sha256_prefix":"8164158a7a04e80a","entry":"time_warp","repo":"cywang97/StreamingTransformer","repo_kind":"official","path":"espnet/transform/spec_augment.py","file_url":"https://github.com/cywang97/StreamingTransformer/blob/HEAD/espnet/transform/spec_augment.py","link_basis":"first_harvest_node","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":"8164158a7a04e80a"}},{"code_sha256_prefix":"c2b7cd038bc092cb","entry":"viterbi_align","repo":"cywang97/StreamingTransformer","repo_kind":"official","path":"espnet/nets/viterbi_align.py","file_url":"https://github.com/cywang97/StreamingTransformer/blob/HEAD/espnet/nets/viterbi_align.py","link_basis":"first_harvest_node","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":"c2b7cd038bc092cb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}