{"id":25525233,"url":"https://github.com/lakshmi-bashyam/neurallm2arpa","last_synced_at":"2026-01-02T08:30:15.894Z","repository":{"id":211131278,"uuid":"418552484","full_name":"Lakshmi-bashyam/NeuralLM2Arpa","owner":"Lakshmi-bashyam","description":"Implementation of conversion system : Neural Language models to backing off n-gram models for decoding in speech recognition systems","archived":false,"fork":false,"pushed_at":"2022-08-04T09:27:06.000Z","size":307,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2023-12-06T17:35:31.234Z","etag":null,"topics":["arpa","lstm","n-grams","nlp","speech-recognition"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Lakshmi-bashyam.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2021-10-18T15:05:33.000Z","updated_at":"2023-12-06T17:35:32.227Z","dependencies_parsed_at":"2023-12-06T17:45:58.585Z","dependency_job_id":null,"html_url":"https://github.com/Lakshmi-bashyam/NeuralLM2Arpa","commit_stats":null,"previous_names":["lakshmi-bashyam/neurallm2arpa"],"tags_count":0,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lakshmi-bashyam%2FNeuralLM2Arpa","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lakshmi-bashyam%2FNeuralLM2Arpa/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lakshmi-bashyam%2FNeuralLM2Arpa/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lakshmi-bashyam%2FNeuralLM2Arpa/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Lakshmi-bashyam","download_url":"https://codeload.github.com/Lakshmi-bashyam/NeuralLM2Arpa/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239727026,"owners_count":19687100,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["arpa","lstm","n-grams","nlp","speech-recognition"],"created_at":"2025-02-19T20:18:43.144Z","updated_at":"2026-01-02T08:30:15.819Z","avatar_url":"https://github.com/Lakshmi-bashyam.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Convert Neural LM to backing off n-gram\n\n## How to Run\n\nTo train RNNLM, add the corpus to data folder\n\n1. Train an n-gram LM using SRILM tool to generate sentences from corpus\n\n   ```   \n   ngram-count -text corpus.txt -order 6 -lm new_lm.arpa -vocab new_vocab \n\n   ngram -lm new_lm.arpa -gen [no_of_sentences] \u003e gen.txt\n   ```\n\n2. To train RNNLM using above generated corpus as training data, run\n\n    ```\n    python train.py\n    ```\n\n    Evaluation result - Test perpexity value is ~52\n    \n3. To extract RNNLM probabilities, run\n   \n   ```\n   python predict.py\n   ```\n\n## References\n\n[1] Singh, Mittul \u0026 Oualil, Youssef \u0026 Klakow, Dietrich. (2017). \\\nApproximated and Domain-Adapted LSTM Language Models for First-Pass Decoding in Speech Recognition. \\\n2720-2724. 10.21437/Interspeech.2017-147. \\\n\n[2]  H. Adel, K. Kirchhoff, N. T. Vu, D. Telaar, and T. Schultz, \\\n“Comparing approaches to convert recurrent neural networks into backoff language models for efficient decoding,” \\\nin INTER-SPEECH 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014, 2014, pp.  51–655.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flakshmi-bashyam%2Fneurallm2arpa","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flakshmi-bashyam%2Fneurallm2arpa","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flakshmi-bashyam%2Fneurallm2arpa/lists"}