| { |
| "architectures": [ |
| "EmageAudioModel" |
| ], |
| "audio_f": 256, |
| "audio_fps": 16000, |
| "audio_norm": false, |
| "audio_rep": "wave16k", |
| "audio_sr": 16000, |
| "cf": 0, |
| "ch": 1, |
| "cl": 1, |
| "class_name": "EmageAudioModel", |
| "cu": 1, |
| "hidden_size": 768, |
| "joint_mask": null, |
| "lf": 3, |
| "lh": 3, |
| "ll": 3, |
| "lu": 3, |
| "model_type": "emage_audio", |
| "motion_f": 256, |
| "name_pyfile": "models.emage_audio.modeling_emage_audio", |
| "pose_dims": 330, |
| "pose_fps": 30, |
| "pose_length": 64, |
| "pose_rep": "smplx", |
| "seed_frames": 4, |
| "speaker_dims": 1, |
| "speaker_f": 768, |
| "stride": 20, |
| "test_length": 64, |
| "torch_dtype": "float32", |
| "transformers_version": "4.30.2", |
| "vae_codebook_size": 256 |
| } |
|
|
