{"id":24818443,"url":"https://github.com/aryanxxvii/lark","last_synced_at":"2025-10-13T19:30:33.881Z","repository":{"id":186071907,"uuid":"674202998","full_name":"aryanxxvii/lark","owner":"aryanxxvii","description":"Speech Assessment API in FastAPI with Hugging Face 🤗","archived":false,"fork":false,"pushed_at":"2025-01-17T08:02:42.000Z","size":187,"stargazers_count":10,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-17T09:19:00.180Z","etag":null,"topics":["fastapi","huggingface","llm","machine-learning","phoneme-recognition","pronunciation","speech-recognition","wav2vec2"],"latest_commit_sha":null,"homepage":"https://larkapi.vercel.app/","language":"JavaScript","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/aryanxxvii.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-08-03T11:27:54.000Z","updated_at":"2025-01-17T08:02:44.000Z","dependencies_parsed_at":null,"dependency_job_id":"50a74358-f3c5-4a9e-bf90-1d2f2cffe9bf","html_url":"https://github.com/aryanxxvii/lark","commit_stats":null,"previous_names":["aryanxxvii/lark"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aryanxxvii%2Flark","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aryanxxvii%2Flark/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aryanxxvii%2Flark/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aryanxxvii%2Flark/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aryanxxvii","download_url":"https://codeload.github.com/aryanxxvii/lark/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":236385728,"owners_count":19140690,"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":["fastapi","huggingface","llm","machine-learning","phoneme-recognition","pronunciation","speech-recognition","wav2vec2"],"created_at":"2025-01-30T17:08:23.774Z","updated_at":"2025-10-13T19:30:28.245Z","avatar_url":"https://github.com/aryanxxvii.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Lark API Readme\n\n## What is it?\n\n- Lark API is a speech assessment REST API built using FastAPI in Python.\n- It provides accuracy scores, speech to text transcription, and the projected IELTS pronunciation band.\n- It allows English learning apps and websites to assess and provide real-time feedback on the users’ pronunciation.\n\n## How does it work?\n\n### ML:\n\n\u003cdiv align=\"center\"\u003e\u003cimg src=\"https://i.imgur.com/veWTSgg.png\" width=\"600\" alt=\"ML\"  /\u003e\n\u003c/div\u003e\n\n- Lark utilizes the Wav2Vec2 model from Meta for analyzing the speech sample.\n- It converts the speech to it’s phonetic transcription (S2P) using zero-shot cross-lingual recognition.\n- After recognizing the phonetics of the speech, it compares it with the ideal pronunciation of the transcribed speech using the Jaro-Winkler string similarity algorithm.\n\n### Backend:\n\n- The API is written completely in FastAPI with MongoDB as the database.\n\n### The Frontend part:\n\n- The Frontend is written using ReactJS and TailwindCSS.\n\n### ML Models used\n\n- [facebook/wav2vec2-xlsr-53-espeak-cv-ft](https://huggingface.co/facebook/wav2vec2-xlsr-53-espeak-cv-ft)\n- [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h)\n\n## References\n\n- [[2109.11680] Simple and Effective Zero-shot Cross-lingual Phoneme Recognition (arxiv.org)](https://arxiv.org/abs/2109.11680)\n- [luozhouyang/python-string-similarity (github.com)](https://github.com/luozhouyang/python-string-similarity#python-string-similarity)\n- [Hugging Face JS libraries](https://huggingface.co/docs/huggingface.js/index)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faryanxxvii%2Flark","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faryanxxvii%2Flark","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faryanxxvii%2Flark/lists"}