File size: 4,144 Bytes
cfbcb75 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 | {
"schema_version": "5.1",
"name": "diffrhythm-1.2-p100a",
"tt_metal_version": "0.0.0.dev0",
"arch": "blackhole",
"device_count": 1,
"producer": {
"tt_kernel_version": "0.1.0",
"created_at": "2026-10-10T03:07:37.410607+00:00",
"hostname": ""
},
"weights": {
"repo_id": "ASLP-lab/DiffRhythm-1_2-full",
"revision": null,
"allow_patterns": null,
"ignore_patterns": null,
"repo_type": "model"
},
"mesh": null,
"entrypoint": null,
"resources": null,
"capabilities": null,
"env": {},
"bundled": null,
"deps": null,
"container": {
"image": {
"registry": "hf",
"repository": "diffrhythm-1.2-p100a",
"tag": "tt-model/diffrhythm-1.2-p100a:0cc125e439ef",
"digest": "sha256:0cc125e439ef6882a01bae57bece67f14ec2ad123aec1fb12e86bc50175a4b44"
},
"kind": "tt-dit-server",
"runtime": {
"app": "tt_diffrhythm.server:app",
"mesh_shape_env": "DIFFRHYTHM_MESH_SHAPE",
"packages": [
"torchaudio==2.11.0+cpu",
"torchdiffeq",
"x-transformers",
"transformers",
"librosa",
"soundfile",
"muq",
"mutagen",
"ema-pytorch",
"accelerate",
"einops",
"tqdm",
"wandb",
"scipy",
"numpy",
"huggingface_hub",
"phonemizer",
"espeakng-loader",
"pykakasi",
"jieba",
"onnxruntime",
"cn2an",
"pypinyin",
"Unidecode",
"inflect",
"py3langid==0.2.2"
],
"lock": "requirements.lock"
},
"serve": {
"hardware": "p100a",
"mesh_device": "P100",
"port": 8000,
"max_model_len": null,
"max_num_seqs": null,
"block_size": null,
"server_timeout": null,
"capabilities": null,
"additional_config": {},
"args": [],
"env": {
"ARCH_NAME": "blackhole",
"TT_METAL_OPERATION_TIMEOUT_SECONDS": "600.0"
}
},
"serve_profiles": [
{
"hardware": null,
"mesh_device": null,
"port": null,
"max_model_len": null,
"max_num_seqs": null,
"block_size": null,
"server_timeout": null,
"capabilities": null,
"additional_config": {},
"args": [],
"env": {},
"name": "default",
"description": null
}
],
"default_profile": null,
"code_dir": "code",
"verify": [
"import tt_diffrhythm.server as s; assert s.app",
"from tt_diffrhythm.local import LocalWorker; assert LocalWorker",
"import tt_diffrhythm.server as s; s._enter_checkout(); import infer_utils, model; assert model.CFM and infer_utils.load_checkpoint",
"from tt_diffrhythm.server import _enter_checkout; _enter_checkout(); import os; assert os.path.isfile('infer/example/vocal.npy'), 'the negative style prompt did not ship'",
"from tt_diffrhythm.server import _enter_checkout; _enter_checkout(); import json; assert json.load(open('config/diffrhythm-1b.json'))['model']",
"from tt_diffrhythm.server import _enter_checkout; _enter_checkout(); from infer_utils import CNENTokenizer; assert CNENTokenizer().encode('a quiet morning')",
"from tt_diffrhythm.server import _point_phonemizer_at_a_bundled_espeak as fix; fix(); from phonemizer.backend import EspeakBackend; assert EspeakBackend('en-us').phonemize(['hello'])[0].strip()"
],
"built": {
"image": "tt-model/diffrhythm-1.2-p100a:0cc125e439ef",
"repo": "sunandbean/diffrhythm-1.2-p100a",
"tt_model_version": "0.1.0",
"created_at": "2026-10-10T03:02:08+00:00",
"tt_metal": {
"sha": "58648d44443223041148125843ca7c7d4780463e",
"describe": null,
"dirty": false,
"scm_version": "0.0.0.dev0",
"mode": "git",
"remote": "https://github.com/tenstorrent/tt-metal",
"branch": null,
"pushed": null
},
"code_sha256": "322cdea4755e9a8117adc934aed2edfd1e3a7631fbbe9949bdbdc46c077cf184",
"image_digest": "sha256:0cc125e439ef6882a01bae57bece67f14ec2ad123aec1fb12e86bc50175a4b44"
}
}
}
|