File size: 1,147 Bytes
86dc2b6 | 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 | {
"architectures": [
"AudioEmbeddingModel"
],
"auto_map": {
"AutoConfig": "configuration_audio.AudioEmbeddingConfig",
"AutoModel": "modeling_audio.AudioEmbeddingModel"
},
"dtype": "float32",
"encoder_kwargs": {
"attn_drop_rate": 0.0,
"depth": 12,
"drop_path_rate": 0.1,
"drop_rate": 0.0,
"embed_dim": 768,
"mlp_ratio": 4.0,
"num_heads": 12,
"num_patches": 128,
"pos_embed_type": "sincos",
"qkv_bias": true
},
"extraction_preset": "overlap50_two_phase",
"feature_encoder_kwargs": {},
"hidden_size": 768,
"model_target": "src.models.best_rq2_module.BestRQ2Module",
"model_type": "audio_embeddings",
"patch_embed_kwargs": {
"embed_dim": 768,
"img_size": [
128,
256
],
"in_chans": 1,
"patch_size": [
16,
16
]
},
"sampling_rate": 16000,
"spectrogram_adjustment_mode": "truncate",
"spectrogram_kwargs": {
"f_max": 8000,
"f_min": 0,
"hop_length_ms": 39.0625,
"n_fft": 2048,
"n_mels": 128,
"power": 2.0,
"sample_rate": 16000,
"win_length_ms": 128
},
"transformers_version": "5.17.0"
}
|