{"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/ctcmodel-a-keras-model-for-connectionist","title":"CTCModel: a Keras Model for Connectionist Temporal Classification","arxiv_id":"1901.07957","date":"2019-01-23","proceeding":null,"authors":["Yann Soullard","Cyprien Ruffino","Thierry Paquet"],"abstract":"We report an extension of a Keras Model, called CTCModel, to perform the\nConnectionist Temporal Classification (CTC) in a transparent way. Combined with\nRecurrent Neural Networks, the Connectionist Temporal Classification is the\nreference method for dealing with unsegmented input sequences, i.e. with data\nthat are a couple of observation and label sequences where each label is\nrelated to a subset of observation frames. CTCModel makes use of the CTC\nimplementation in the Tensorflow backend for training and predicting sequences\nof labels using Keras. It consists of three branches made of Keras models: one\nfor training, computing the CTC loss function; one for predicting, providing\nsequences of labels; and one for evaluating that returns standard metrics for\nanalyzing sequences of predictions.","url_abs":"http://arxiv.org/abs/1901.07957v1","url_pdf":"http://arxiv.org/pdf/1901.07957v1.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":"ctcmodel-a-keras-model-for-connectionist","repo_url":"https://github.com/bhavitvyamalik/OCR-using-CRNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"ctcmodel-a-keras-model-for-connectionist","repo_url":"https://github.com/cyprienruffino/CTCModel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"ctcmodel-a-keras-model-for-connectionist","repo_url":"https://github.com/ysoullard/CTCModel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"ctcmodel-a-keras-model-for-connectionist","repo_url":"https://github.com/2023-MindSpore-1/ms-code-15/tree/main/ctcmodel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"ctcmodel-a-keras-model-for-connectionist","repo_url":"https://github.com/MindSpore-paper-code-2/code399/tree/main/ctcmodel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"ctc-loss","method_name":"CTC Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}