File size: 2,756 Bytes
c05f0fd |
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 |
{
"architectures": [
"Mapperatorinator"
],
"backbone_config": {
"_name_or_path": "openai/whisper-small",
"activation_dropout": 0.0,
"activation_function": "gelu",
"apply_spec_augment": false,
"architectures": [
"WhisperForConditionalGeneration"
],
"attention_dropout": 0.0,
"begin_suppress_tokens": null,
"bos_token_id": 1,
"classifier_proj_size": 256,
"d_model": 768,
"decoder_attention_heads": 12,
"decoder_ffn_dim": 3072,
"decoder_layerdrop": 0.0,
"decoder_layers": 12,
"decoder_start_token_id": 1,
"dropout": 0.0,
"encoder_attention_heads": 12,
"encoder_ffn_dim": 3072,
"encoder_layerdrop": 0.0,
"encoder_layers": 12,
"eos_token_id": 2,
"forced_decoder_ids": null,
"init_std": 0.02,
"mask_feature_length": 10,
"mask_feature_min_masks": 0,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_min_masks": 2,
"mask_time_prob": 0.05,
"max_length": 448,
"max_source_positions": 2048,
"max_target_positions": 8192,
"median_filter_width": 7,
"model_type": "whisper",
"num_hidden_layers": 12,
"num_mel_bins": 464,
"pad_token_id": 0,
"rope_decoder_scaling_factor": 1.0,
"rope_encoder_scaling_factor": 1.0,
"rope_type": "dynamic",
"scale_embedding": false,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"use_cache": false,
"use_weighted_layer_sum": false,
"vocab_size": 5971
},
"backbone_model_name": "Tiger14n/ropewhisper-small",
"bos_token_id": 1,
"cond_dim": 128,
"cond_size": 384,
"decoder_start_token_id": 1,
"disable_compile": true,
"do_difficulty_embed": true,
"do_mapper_embed": true,
"do_sample": true,
"do_song_position_embed": true,
"do_style_embed": false,
"embed_decoder_input": true,
"eos_token_id": 2,
"f_max": 8000,
"f_min": 20,
"hidden_size": 768,
"hop_length": 128,
"init_std": 0.02,
"input_features": true,
"is_encoder_decoder": true,
"max_length": null,
"max_source_positions": 2048,
"max_target_positions": 8192,
"model_type": "mapperatorinator",
"n_fft": 1024,
"n_mels": 80,
"num_attention_heads": 12,
"num_classes": 0,
"num_hidden_layers": 12,
"num_mappers": 5527,
"pad_mode": "reflect",
"pad_token_id": 0,
"project_encoder_input": false,
"rhythm_token_end": 3294,
"rhythm_token_start": 17,
"rhythm_weight": 1.0,
"sample_rate": 16000,
"spectrogram_implementation": "torchaudio",
"spectrogram_log_scale": true,
"top_k": 0,
"torch_dtype": "float32",
"transformers_version": "4.52.1",
"vocab_size": 5971,
"vocab_size_in": 11714
}
|