{"data":{"slug":"ailia-ai-ailia-models","name":"ailia-models","tagline":"Repository of pre-trained AI models for ailia SDK","github_url":"https://github.com/ailia-ai/ailia-models","owner":"ailia-ai","repo":"ailia-models","owner_avatar_url":"https://avatars.githubusercontent.com/u/55011924?v=4","primary_language":"Python","stars":2365,"forks":363,"topics":["action-recognition","anomaly-detection","audio-processing","background-removal","crowd-counting","deep-learning","embeddings","face-detection","face-recognition","fashion-ai","gan","hand-detection","image-classification","image-segmentation","llm","neural-network","object-detection","object-recognition","object-tracking","pose-estimation"],"archived":false,"github_pushed_at":"2026-08-21T11:01:27+00:00","maintenance_label":"Very active","stars_delta_30d":8,"url":"https://www.graphcanon.com/tools/ailia-ai-ailia-models","markdown_url":"https://www.graphcanon.com/tools/ailia-ai-ailia-models.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ailia-ai-ailia-models","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ailia-ai-ailia-models","description":"The collection of pre-trained, state-of-the-art AI models for ailia SDK","homepage_url":null,"license":null,"open_issues":321,"watchers":47,"ai_summary":"Collection of state-of-the-art AI models for various applications including action recognition, anomaly detection, audio processing, and more.","readme_excerpt":"[](ABOUT_AINYAN.md)\n\n\n\n\n\n\nThe collection of pre-trained, state-of-the-art AI models: 418 models covering object detection, speech recognition, image generation, LLMs and more — all runnable from the same simple CLI.\n\n[Tutorial](TUTORIAL.md) · [チュートリアル](TUTORIAL_jp.md) · [Google Colaboratory](https://www.ailia.ai/launch_to_colab) · [Documentation](https://docs.ailia.ai/en/) · [deepwiki](https://deepwiki.com/ailia-ai/ailia-models) · [Update history](https://github.com/ailia-ai/ailia-models/wiki)\n\nEvery model works the same way: no arguments needed, weights download automatically.\n\n```\npip3 install ailia\ngit clone https://github.com/ailia-ai/ailia-models\ncd ailia-models\npip3 install -r requirements.txt\ncd object_detection/yolox\npython3 yolox.py\n```\n\n# Models\n\n418 models are available. Use [🔍 Search models](https://github.com/ailia-ai/ailia-models/find/master) to find a model by name.\n\n| | Category | Model list |\n|:---|:---|:---|\n| [](/action_recognition/) | [Action recognition](/action_recognition/) | [va-cnn](/action_recognition/va-cnn/), [st-gcn](/action_recognition/st_gcn/), [mars](/action_recognition/mars/), [ax_action_recognition](/action_recognition/ax_action_recognition/), [driver-action-recognition-adas](/action_recognition/driver-action-recognition-adas/), [action_clip](/action_recognition/action_clip/) |\n| [](/anomaly_detection/) | [Anomaly detection](/anomaly_detection/) | [mahalanobisad](/anomaly_detection/mahalanobisad/), [spade-pytorch](/anomaly_detection/spade-pytorch/), [padim](/anomaly_detection/padim/), [patchcore](/anomaly_detection/patchcore/), [glass](/anomaly_detection/glass/) |\n| | [Audio language model](/audio_language_model/) | [qwen_audio](/audio_language_model/qwen_audio/) |\n| | [Audio processing](/audio_processing/) | **Audio classification**: [crnn_audio_classification](/audio_processing/crnn_audio_classification/), [audioset_tagging_cnn](/audio_processing/audioset_tagging_cnn/), [transformer-cnn-emotion-recognition](/audio_processing/transformer-cnn-emotion-recognition/), [microsoft clap](/audio_processing/msclap/), [clap](/audio_processing/clap/)
**Music enhancement**: [hifigan](/audio_processing/hifigan/), [deep music enhancer](/audio_processing/deep-music-enhancer/)
**Music generation**: [pytorch_wavenet](/audio_processing/pytorch_wavenet/)
**Noise reduction**: [rnnoise](/audio_processing/rnnoise/), [voicefilter](/audio_processing/voicefilter/), [unet_source_separation](/audio_processing/unet_source_separation/), [demucs](/audio_processing/demucs/), [dtln](/audio_processing/dtln/), [audiosep](/audio_processing/audiosep/)
**Phoneme alignment**: [narabas](/audio_processing/narabas/)
**Pitch detection**: [crepe](/audio_processing/crepe/)
**Speaker diarization**: [pyannote-audio](/audio_processing/pyannote-audio/), [auto_speech](/audio_processing/auto_speech/), [wespeaker](/audio_processing/wespeaker/)
**Speech to text**: [deepspeech2](/audio_processing/deepspeech2/), [whisper](/audio_processing/whisper/), [reazon_speech](/audio_processing/reazon_speech/), [distil-whisper](/audio_processing/distil-whisper/), [sensevoice](/audio_processing/sensevoice/), [reazon_speech2](/audio_processing/reazon_speech2/), [kotoba-whisper](/audio_processing/kotoba-whisper/), [lite-whisper](/audio_processing/lite-whisper/)
**Text to speech**: [pytorch-dc-tts](/audio_processing/pytorch-dc-tts/), [tacotron2](/audio_processing/tacotron2/), [vall-e-x](/audio_processing/vall-e-x/), [Bert-VITS2](/audio_processing/bert-vits2/), [gpt-sovits](/audio_processing/gpt-sovits/), [gpt-sovits-v2](/audio_processing/gpt-sovits-v2/), [cosyvoice2](/audio_processing/cosyvoice2/), [gpt-sovits-v3](/audio_processing/gpt-sovits-v3/), [gpt-sovits-v2-pro](/audio_processing/gpt-sovits-v2-pro/), [qwen3-tts](/audio_processing/qwen3-tts/)
**Voice","github_created_at":"2019-09-07T04:50:59+00:00","created_at":"2026-07-11T11:29:22.182969+00:00","updated_at":"2026-08-22T06:01:11.710477+00:00","categories":[{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"},{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"action-recognition","name":"action-recognition"},{"slug":"anomaly-detection","name":"anomaly-detection"},{"slug":"audio-processing","name":"audio-processing"},{"slug":"background-removal","name":"background-removal"},{"slug":"crowd-counting","name":"crowd-counting"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"embeddings","name":"embeddings"},{"slug":"face-detection","name":"face-detection"}],"trust":{"provenance":{"is_fork":false,"github_id":206917330,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-22T06:01:10.935Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":0,"days_since_push":0,"last_release_at":null,"stars_delta_30d":8,"open_issues_delta_30d":5},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:29:23.354Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-22T06:01:11.390Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-22T06:01:11.390Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-22T06:01:11.390Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When developing apps that integrate with the ailia SDK","For quick deployment of state-of-the-art models specific to ailia's supported categories"],"when_not_to_use":["If your project does not align with ailia SDK or its specific model categories","When you require customization beyond what is offered by pre-trained models in this repository"],"source":"enrich:decision_facts","observed_at":"2026-07-12T14:00:03.849Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Pre-trained AI models for ailia SDK, covering broad applications from action recognition to audio processing."}]}}