{ "id": 334254, "title": "স্বাগতম (Welcome) from BUET CSE Fest 2022 and Bengali.AI", "url": "/competitions/dlsprint/discussion/334254", "author_name": "Najibul Haque Sarker", "post_date": "2022-06-30T16:55:52.074000", "votes": 16, "comment_count": 0, "views": 0, "content": "

Welcome to the Bengali Automatic Speech Recognition Competition!!

\n

BUET CSE Fest 2022 is an event full of competitions and festivities organized by the final year undergraduate students from the Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology. Bengali.AI is a non-profit research organization committed to creating Bengali language centric datasets. Together, they are bringing you DL Sprint, an open for all deep learning competition aimed at Bengali language transcription.

\n

The main goal of this competition is to develop the field of Bengali ASR by building solutions through a crowdsourced sentence-level corpus collected on the Mozilla Common Voice platform. By participating in this competition, you can directly contribute to the development of a generalized ASR model for the Bengali language. Furthermore, the competition hosts hope that this event will help grow the Bengali Deep Learning community through participation and collaboration with Kaggle Machine Learning Specialists.

\n

This competition is divided into 3 parts:
\n1) Phase 1 Part 1 (This Kaggle Competition)
\n2) Phase 1 Part 2 (Another competition link will be sent only to the registered users on 25th July)
\n3) Phase 2 (Onsite final evaluation)

\n

Note that, Phase 1 Part 1 score is for benchmarking and validating participants' models and won't count towards final evaluation. The final evaluation will be based on Phase 1 Part 2 and Phase 2 scores. All teams will submit working Kaggle notebooks for Train and Test with appropriate instructions for reproducibility after Phase 1 Part 1. Beware, the Phase 1 Part 2 and Phase 2 test datasets may contain samples with a slight domain shift (vocabulary) to encourage generalized models.

\n

We hope to see you in all these events!! Hope you guys have fun!!

\n

Links

\n

Competition Website: https://buetcsefest2022.com/dlsprint/
\nCompetition Rules and Regulations: https://buetcsefest2022.com/dlsprint/rules/
\nCompetition Registration: https://tiny.cc/dlsprint22
\nBUET CSE Fest 2022 details: https://buetcsefest2022.com/
\nBengali.AI: https://bengali.ai/
\nFacebook Event: https://fb.me/e/1ug0pEaws

", "messages": [ { "id": 1838577, "postDate": "2022-06-30T16:55:52.073Z", "content": "

Welcome to the Bengali Automatic Speech Recognition Competition!!

\n

BUET CSE Fest 2022 is an event full of competitions and festivities organized by the final year undergraduate students from the Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology. Bengali.AI is a non-profit research organization committed to creating Bengali language centric datasets. Together, they are bringing you DL Sprint, an open for all deep learning competition aimed at Bengali language transcription.

\n

The main goal of this competition is to develop the field of Bengali ASR by building solutions through a crowdsourced sentence-level corpus collected on the Mozilla Common Voice platform. By participating in this competition, you can directly contribute to the development of a generalized ASR model for the Bengali language. Furthermore, the competition hosts hope that this event will help grow the Bengali Deep Learning community through participation and collaboration with Kaggle Machine Learning Specialists.

\n

This competition is divided into 3 parts:
\n1) Phase 1 Part 1 (This Kaggle Competition)
\n2) Phase 1 Part 2 (Another competition link will be sent only to the registered users on 25th July)
\n3) Phase 2 (Onsite final evaluation)

\n

Note that, Phase 1 Part 1 score is for benchmarking and validating participants' models and won't count towards final evaluation. The final evaluation will be based on Phase 1 Part 2 and Phase 2 scores. All teams will submit working Kaggle notebooks for Train and Test with appropriate instructions for reproducibility after Phase 1 Part 1. Beware, the Phase 1 Part 2 and Phase 2 test datasets may contain samples with a slight domain shift (vocabulary) to encourage generalized models.

\n

We hope to see you in all these events!! Hope you guys have fun!!

\n

Links

\n

Competition Website: https://buetcsefest2022.com/dlsprint/
\nCompetition Rules and Regulations: https://buetcsefest2022.com/dlsprint/rules/
\nCompetition Registration: https://tiny.cc/dlsprint22
\nBUET CSE Fest 2022 details: https://buetcsefest2022.com/
\nBengali.AI: https://bengali.ai/
\nFacebook Event: https://fb.me/e/1ug0pEaws

", "rawMarkdown": "Welcome to the Bengali Automatic Speech Recognition Competition!!\n\nBUET CSE Fest 2022 is an event full of competitions and festivities organized by the final year undergraduate students from the Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology. Bengali.AI is a non-profit research organization committed to creating Bengali language centric datasets. Together, they are bringing you DL Sprint, an open for all deep learning competition aimed at Bengali language transcription. \n\nThe main goal of this competition is to develop the field of Bengali ASR by building solutions through a crowdsourced sentence-level corpus collected on the Mozilla Common Voice platform. By participating in this competition, you can directly contribute to the development of a generalized ASR model for the Bengali language. Furthermore, the competition hosts hope that this event will help grow the Bengali Deep Learning community through participation and collaboration with Kaggle Machine Learning Specialists.\n\nThis competition is divided into 3 parts:\n1) **Phase 1 Part 1** (This Kaggle Competition)\n2) **Phase 1 Part 2** (Another competition link will be sent only to the registered users on 25th July)\n3) **Phase 2** (Onsite final evaluation)\n\nNote that, **Phase 1 Part 1** score is for benchmarking and validating participants' models and won't count towards final evaluation. The final evaluation will be based on **Phase 1 Part 2** and **Phase 2** scores. **All teams will submit working Kaggle notebooks for Train and Test with appropriate instructions for reproducibility after Phase 1 Part 1**. Beware, the Phase 1 Part 2 and Phase 2 test datasets may contain samples with a slight domain shift (vocabulary) to encourage generalized models. \n\nWe hope to see you in all these events!! Hope you guys have fun!!\n\n####Links\nCompetition Website: [https://buetcsefest2022.com/dlsprint/](https://buetcsefest2022.com/dlsprint/)\nCompetition Rules and Regulations: [https://buetcsefest2022.com/dlsprint/rules/](https://buetcsefest2022.com/dlsprint/rules/)\nCompetition Registration: [https://tiny.cc/dlsprint22](https://tiny.cc/dlsprint22)\nBUET CSE Fest 2022 details: [https://buetcsefest2022.com/](https://buetcsefest2022.com/)\nBengali.AI: [https://bengali.ai/](https://bengali.ai/)\nFacebook Event: [https://fb.me/e/1ug0pEaws](https://fb.me/e/1ug0pEaws)\n\n\n", "votes": 16 } ], "comments": [], "raw_markdown_by_id": { "1838577": "Welcome to the Bengali Automatic Speech Recognition Competition!!\n\nBUET CSE Fest 2022 is an event full of competitions and festivities organized by the final year undergraduate students from the Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology. Bengali.AI is a non-profit research organization committed to creating Bengali language centric datasets. Together, they are bringing you DL Sprint, an open for all deep learning competition aimed at Bengali language transcription. \n\nThe main goal of this competition is to develop the field of Bengali ASR by building solutions through a crowdsourced sentence-level corpus collected on the Mozilla Common Voice platform. By participating in this competition, you can directly contribute to the development of a generalized ASR model for the Bengali language. Furthermore, the competition hosts hope that this event will help grow the Bengali Deep Learning community through participation and collaboration with Kaggle Machine Learning Specialists.\n\nThis competition is divided into 3 parts:\n1) **Phase 1 Part 1** (This Kaggle Competition)\n2) **Phase 1 Part 2** (Another competition link will be sent only to the registered users on 25th July)\n3) **Phase 2** (Onsite final evaluation)\n\nNote that, **Phase 1 Part 1** score is for benchmarking and validating participants' models and won't count towards final evaluation. The final evaluation will be based on **Phase 1 Part 2** and **Phase 2** scores. **All teams will submit working Kaggle notebooks for Train and Test with appropriate instructions for reproducibility after Phase 1 Part 1**. Beware, the Phase 1 Part 2 and Phase 2 test datasets may contain samples with a slight domain shift (vocabulary) to encourage generalized models. \n\nWe hope to see you in all these events!! Hope you guys have fun!!\n\n####Links\nCompetition Website: [https://buetcsefest2022.com/dlsprint/](https://buetcsefest2022.com/dlsprint/)\nCompetition Rules and Regulations: [https://buetcsefest2022.com/dlsprint/rules/](https://buetcsefest2022.com/dlsprint/rules/)\nCompetition Registration: [https://tiny.cc/dlsprint22](https://tiny.cc/dlsprint22)\nBUET CSE Fest 2022 details: [https://buetcsefest2022.com/](https://buetcsefest2022.com/)\nBengali.AI: [https://bengali.ai/](https://bengali.ai/)\nFacebook Event: [https://fb.me/e/1ug0pEaws](https://fb.me/e/1ug0pEaws)\n\n\n" } }