{"data":{"node":{"slug":"jinjieni-mixeval","name":"MixEval","tagline":"Evaluation suite and dynamic data release for MixEval","github_url":"https://github.com/JinjieNi/MixEval","owner":"JinjieNi","repo":"MixEval","owner_avatar_url":"https://avatars.githubusercontent.com/u/46987361?v=4","primary_language":"Python","stars":254,"forks":40,"topics":["benchmark","benchmark-mixture","benchmarking-framework","benchmarking-suite","evaluation","evaluation-framework","foundation-models","large-language-model","large-language-models","large-multimodal-models","llm-evaluation","llm-evaluation-framework","llm-inference","mixeval"],"archived":false,"github_pushed_at":"2024-11-10T02:23:50+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/jinjieni-mixeval","markdown_url":"https://www.graphcanon.com/tools/jinjieni-mixeval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jinjieni-mixeval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jinjieni-mixeval"},"categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"benchmark","name":"benchmark"},{"slug":"evaluation-framework","name":"evaluation-framework"},{"slug":"foundation-models","name":"foundation-models"},{"slug":"large-language-models","name":"large language models"},{"slug":"large-multimodal-models","name":"large-multimodal-models"},{"slug":"llm-evaluation","name":"llm-evaluation"}],"edges":[],"neighbours":[{"slug":"confident-ai-deepeval","name":"deepeval","tagline":"LLM Evaluation Framework.","github_url":"https://github.com/confident-ai/deepeval","owner":"confident-ai","repo":"deepeval","owner_avatar_url":"https://avatars.githubusercontent.com/u/130858411?v=4","primary_language":"Python","stars":17226,"forks":1736,"topics":["evaluation-framework","evaluation-metrics","llm-evaluation","llm-evaluation-framework","llm-evaluation-metrics","python"],"archived":false,"github_pushed_at":"2026-07-27T11:33:31+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/confident-ai-deepeval","markdown_url":"https://www.graphcanon.com/tools/confident-ai-deepeval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/confident-ai-deepeval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=confident-ai-deepeval","shared_categories":["evaluation-observability"]},{"slug":"espnet-espnet","name":"espnet","tagline":"End-to-End Speech Processing Toolkit","github_url":"https://github.com/espnet/espnet","owner":"espnet","repo":"espnet","owner_avatar_url":"https://avatars.githubusercontent.com/u/34493687?v=4","primary_language":"Python","stars":9903,"forks":2421,"topics":["chainer","deep-learning","end-to-end","kaldi","machine-translation","pytorch","singing-voice-synthesis","speaker-diarization","speech-enhancement","speech-recognition","speech-separation","speech-synthesis","speech-translation","spoken-language-understanding","text-to-speech","voice-conversion"],"archived":false,"github_pushed_at":"2026-07-28T14:36:55+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/espnet-espnet","markdown_url":"https://www.graphcanon.com/tools/espnet-espnet.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/espnet-espnet","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=espnet-espnet","shared_categories":[]},{"slug":"evolvinglmms-lab-lmms-eval","name":"lmms-eval","tagline":"One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks","github_url":"https://github.com/EvolvingLMMs-Lab/lmms-eval","owner":"EvolvingLMMs-Lab","repo":"lmms-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/154951679?v=4","primary_language":"Python","stars":4368,"forks":639,"topics":["agi","audio-evaluation","benchmark","evaluation","large-language-models","llm-evaluation","multimodal","multimodal-evaluation","video-understanding","vision-language-model","vlm"],"archived":false,"github_pushed_at":"2026-08-06T02:22:23+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval","markdown_url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/evolvinglmms-lab-lmms-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=evolvinglmms-lab-lmms-eval","shared_categories":["evaluation-observability"]},{"slug":"metavoiceio-metavoice-src","name":"metavoice-src","tagline":"Foundational model for human-like, expressive TTS","github_url":"https://github.com/metavoiceio/metavoice-src","owner":"metavoiceio","repo":"metavoice-src","owner_avatar_url":"https://avatars.githubusercontent.com/u/107063843?v=4","primary_language":"Python","stars":4203,"forks":693,"topics":["ai","deep-learning","pytorch","speech","speech-synthesis","text-to-speech","tts","voice-clone","zero-shot-tts"],"archived":false,"github_pushed_at":"2024-07-30T22:13:01+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/metavoiceio-metavoice-src","markdown_url":"https://www.graphcanon.com/tools/metavoiceio-metavoice-src.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/metavoiceio-metavoice-src","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=metavoiceio-metavoice-src","shared_categories":[]},{"slug":"stanford-crfm-helm","name":"helm","tagline":"Holistic, reproducible and transparent evaluation of foundation models","github_url":"https://github.com/stanford-crfm/helm","owner":"stanford-crfm","repo":"helm","owner_avatar_url":"https://avatars.githubusercontent.com/u/75054807?v=4","primary_language":"Python","stars":2873,"forks":406,"topics":[],"archived":false,"github_pushed_at":"2026-08-01T01:23:17+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/stanford-crfm-helm","markdown_url":"https://www.graphcanon.com/tools/stanford-crfm-helm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/stanford-crfm-helm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=stanford-crfm-helm","shared_categories":["evaluation-observability"]},{"slug":"jik876-hifi-gan","name":"hifi-gan","tagline":"Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","github_url":"https://github.com/jik876/hifi-gan","owner":"jik876","repo":"hifi-gan","owner_avatar_url":"https://avatars.githubusercontent.com/u/65878508?v=4","primary_language":"Python","stars":2363,"forks":555,"topics":["deep-learning","gan","hifi-gan","pytorch","speech-synthesis","text-to-speech","tts","vocoder"],"archived":false,"github_pushed_at":"2024-07-27T20:56:30+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/jik876-hifi-gan","markdown_url":"https://www.graphcanon.com/tools/jik876-hifi-gan.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jik876-hifi-gan","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jik876-hifi-gan","shared_categories":[]},{"slug":"evalplus-evalplus","name":"evalplus","tagline":"Rigorous evaluation of LLM-synthesized code","github_url":"https://github.com/evalplus/evalplus","owner":"evalplus","repo":"evalplus","owner_avatar_url":"https://avatars.githubusercontent.com/u/132106461?v=4","primary_language":"Python","stars":1794,"forks":205,"topics":["benchmark","chatgpt","efficiency","gpt-4","large-language-models","program-synthesis","testing"],"archived":false,"github_pushed_at":"2025-10-02T22:56:38+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/evalplus-evalplus","markdown_url":"https://www.graphcanon.com/tools/evalplus-evalplus.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/evalplus-evalplus","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=evalplus-evalplus","shared_categories":["evaluation-observability"]},{"slug":"coqui-ai-open-speech-corpora","name":"open-speech-corpora","tagline":"A list of accessible speech corpora for ASR, TTS, and other Speech Technologies","github_url":"https://github.com/coqui-ai/open-speech-corpora","owner":"coqui-ai","repo":"open-speech-corpora","owner_avatar_url":"https://avatars.githubusercontent.com/u/75583352?v=4","primary_language":null,"stars":1398,"forks":151,"topics":["speech-emotion-recognition","speech-processing","speech-recognition","speech-separation","speech-synthesis","speech-to-text","stt","text-to-speech","tts","voice-activity-detection","voice-cloning","voice-recognition"],"archived":false,"github_pushed_at":"2024-06-06T11:33:44+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/coqui-ai-open-speech-corpora","markdown_url":"https://www.graphcanon.com/tools/coqui-ai-open-speech-corpora.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/coqui-ai-open-speech-corpora","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=coqui-ai-open-speech-corpora","shared_categories":[]},{"slug":"gitmylo-audio-webui","name":"audio-webui","tagline":"A web interface for various audio-centric neural network applications","github_url":"https://github.com/gitmylo/audio-webui","owner":"gitmylo","repo":"audio-webui","owner_avatar_url":"https://avatars.githubusercontent.com/u/36931363?v=4","primary_language":"Python","stars":1243,"forks":113,"topics":["ai","aio","all-in-one","artificial-intelligence","audiocraft","audioldm","bark","bark-gui","generative-audio","generative-music","music","rvc","rvc-gui","text-to-audio","text-to-speech","tts","voice-cloning"],"archived":false,"github_pushed_at":"2025-05-19T20:04:32+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/gitmylo-audio-webui","markdown_url":"https://www.graphcanon.com/tools/gitmylo-audio-webui.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/gitmylo-audio-webui","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=gitmylo-audio-webui","shared_categories":[]},{"slug":"glgh-awesome-llm-human-preference-datasets","name":"awesome-llm-human-preference-datasets","tagline":"Curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval","github_url":"https://github.com/glgh/awesome-llm-human-preference-datasets","owner":"glgh","repo":"awesome-llm-human-preference-datasets","owner_avatar_url":"https://avatars.githubusercontent.com/u/16108776?v=4","primary_language":null,"stars":390,"forks":19,"topics":["awesome-list","datasets","eval","human-preferences","llm","machine-learning","nlp","rlhf"],"archived":false,"github_pushed_at":"2023-10-04T19:56:44+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/glgh-awesome-llm-human-preference-datasets","markdown_url":"https://www.graphcanon.com/tools/glgh-awesome-llm-human-preference-datasets.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/glgh-awesome-llm-human-preference-datasets","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=glgh-awesome-llm-human-preference-datasets","shared_categories":["evaluation-observability"]},{"slug":"athina-ai-athina-evals","name":"athina-evals","tagline":"Python SDK for evaluating LLM generated responses","github_url":"https://github.com/athina-ai/athina-evals","owner":"athina-ai","repo":"athina-evals","owner_avatar_url":"https://avatars.githubusercontent.com/u/139258696?v=4","primary_language":"Python","stars":301,"forks":22,"topics":["evaluation","evaluation-framework","evaluation-metrics","llm-eval","llm-evaluation","llm-evaluation-toolkit","llm-ops","llmops"],"archived":false,"github_pushed_at":"2025-06-06T15:54:38+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/athina-ai-athina-evals","markdown_url":"https://www.graphcanon.com/tools/athina-ai-athina-evals.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/athina-ai-athina-evals","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=athina-ai-athina-evals","shared_categories":["evaluation-observability"]},{"slug":"zeno-ml-zeno","name":"zeno","tagline":"AI Data Management & Evaluation Platform","github_url":"https://github.com/zeno-ml/zeno","owner":"zeno-ml","repo":"zeno","owner_avatar_url":"https://avatars.githubusercontent.com/u/109821189?v=4","primary_language":"Svelte","stars":214,"forks":11,"topics":["ai","data-science","evaluation","evaluation-framework","machine-learning","python"],"archived":true,"github_pushed_at":"2023-10-05T19:02:16+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/zeno-ml-zeno","markdown_url":"https://www.graphcanon.com/tools/zeno-ml-zeno.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zeno-ml-zeno","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zeno-ml-zeno","shared_categories":["evaluation-observability"]}]}}