{"id":13862518,"url":"https://github.com/archinetai/archisound","last_synced_at":"2025-04-05T11:31:06.220Z","repository":{"id":63757201,"uuid":"570473800","full_name":"archinetai/archisound","owner":"archinetai","description":"A collection of pre-trained audio models, in PyTorch.","archived":false,"fork":false,"pushed_at":"2023-01-27T10:35:04.000Z","size":9,"stargazers_count":113,"open_issues_count":2,"forks_count":4,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-04-02T16:02:38.701Z","etag":null,"topics":["artificial-intelligence","audio","deep-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/archinetai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-11-25T09:24:59.000Z","updated_at":"2025-01-30T15:57:12.000Z","dependencies_parsed_at":"2023-02-15T08:00:59.803Z","dependency_job_id":null,"html_url":"https://github.com/archinetai/archisound","commit_stats":null,"previous_names":[],"tags_count":6,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archinetai%2Farchisound","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archinetai%2Farchisound/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archinetai%2Farchisound/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archinetai%2Farchisound/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/archinetai","download_url":"https://codeload.github.com/archinetai/archisound/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247330580,"owners_count":20921658,"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":["artificial-intelligence","audio","deep-learning"],"created_at":"2024-08-05T06:01:46.355Z","updated_at":"2025-04-05T11:31:05.941Z","avatar_url":"https://github.com/archinetai.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"\n# ArchiSound\n\nA collection of pre-trained audio models in PyTorch from [`audio-encoders-pytorch`](https://github.com/archinetai/audio-encoders-pytorch) and [`audio-diffusion-pytorch`](https://github.com/archinetai/audio-diffusion-pytorch).\n\n## Install\n```bash\npip install archisound\n```\n\n[![PyPI - Python Version](https://img.shields.io/pypi/v/archisound?style=flat\u0026colorA=black\u0026colorB=black)](https://pypi.org/project/archisound/)\n\n\n## Autoencoders\n\n* [`dmae1d-ATC32-v3`](https://huggingface.co/archinetai/dmae1d-ATC32-v3/tree/main)\n  \u003cdetails\u003e \u003csummary\u003e Usage and Info \u003c/summary\u003e\n\n  ```py\n  from archisound import ArchiSound\n\n  autoencoder = ArchiSound.from_pretrained(\"dmae1d-ATC32-v3\")\n\n  x = torch.randn(1, 2, 2**18)\n  z = autoencoder.encode(x) # [1, 32, 512]\n  y = autoencoder.decode(z, num_steps=20) # [1, 2, 262144]\n  ```\n\n  | Info  | |\n  | ------------- | ------------- |\n  | Input type | Audio (stereo @ 48kHz) |\n  | Number of parameters  | 86M |\n  | Compression Factor | 32x |\n  | Downsampling Factor | 512x |\n  | Bottleneck Type | Tanh |\n\n  \u003c/details\u003e\n\n\n* [`dmae1d-ATC64-v2`](https://huggingface.co/archinetai/dmae1d-ATC64-v2/tree/main)\n  \u003cdetails\u003e \u003csummary\u003e Usage and Info \u003c/summary\u003e\n\n  ```py\n  from archisound import ArchiSound\n\n  autoencoder = ArchiSound.from_pretrained(\"dmae1d-ATC64-v2\")\n\n  x = torch.randn(1, 2, 2**18)\n  z = autoencoder.encode(x) # [1, 32, 256]\n  y = autoencoder.decode(z, num_steps=20) # [1, 2, 262144]\n  ```\n\n  | Info  | |\n  | ------------- | ------------- |\n  | Input type | Audio (stereo @ 48kHz) |\n  | Number of parameters  | 185M |\n  | Compression Factor | 64x |\n  | Downsampling Factor | 1024x |\n  | Bottleneck Type | Tanh |\n\n  \u003c/details\u003e\n\n\n\n* [`autoencoder1d-AT-v1`](https://huggingface.co/archinetai/autoencoder1d-AT-v1/tree/main)\n  \u003cdetails\u003e \u003csummary\u003e Usage and Info \u003c/summary\u003e\n\n  ```py\n  from archisound import ArchiSound\n\n  autoencoder = ArchiSound.from_pretrained('autoencoder1d-AT-v1')\n\n  x = torch.randn(1, 2, 2**18)    # [1, 2, 262144]\n  z = autoencoder.encode(x)       # [1, 32, 8192]\n  y = autoencoder.decode(z)       # [1, 2, 262144]\n  ```\n\n  | Info  | |\n  | ------------- | ------------- |\n  | Input type | Audio (stereo @ 48kHz) |\n  | Number of parameters  | 20.7M  |\n  | Compression Factor | 2x |\n  | Downsampling Factor | 32x |\n  | Bottleneck Type | Tanh |\n  | Known Limitations | Slight blurriness in high frequency spectrogram reconstruction |\n\n  \u003c/details\u003e\n\n\n\n* [`dmae1d-ATC64-v1`](https://huggingface.co/archinetai/dmae1d-ATC64-v1/tree/main)\n  \u003cdetails\u003e \u003csummary\u003e Usage and Info \u003c/summary\u003e\n\n  A diffusion based autoencoder with high compression ratio. Requires `audio_diffusion_pytorch==0.0.92`.\n\n  ```py\n  from archisound import ArchiSound\n\n  autoencoder = ArchiSound.from_pretrained(\"dmae1d-ATC64-v1\")\n\n  x = torch.randn(1, 2, 2**18)\n  z = autoencoder.encode(x) # [1, 32, 256]\n  y = autoencoder.decode(z, num_steps=20) # [1, 2, 262144]\n  ```\n\n  | Info  | |\n  | ------------- | ------------- |\n  | Input type | Audio (stereo @ 48kHz) |\n  | Number of parameters  | 234.2M  |\n  | Compression Factor | 64x |\n  | Downsampling Factor | 1024x |\n  | Bottleneck Type | Tanh |\n  \u003c/details\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farchinetai%2Farchisound","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farchinetai%2Farchisound","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farchinetai%2Farchisound/lists"}