CoolFace
Modelpublic

suno/bark

sourceHugging Facemitupdated 3y agoView on Hugging Face
1.6klikes30kdownloads
config.json341 linesDownload Raw Back to root
1{2  "_commit_hash": null,3  "architectures": [4    "BarkModel"5  ],6  "coarse_acoustics_config": {7    "_name_or_path": "",8    "add_cross_attention": false,9    "architectures": [10      "BarkCoarseModel"11    ],12    "bad_words_ids": null,13    "begin_suppress_tokens": null,14    "bias": false,15    "block_size": 1024,16    "bos_token_id": null,17    "chunk_size_feed_forward": 0,18    "cross_attention_hidden_size": null,19    "decoder_start_token_id": null,20    "diversity_penalty": 0.0,21    "do_sample": false,22    "dropout": 0.0,23    "early_stopping": false,24    "encoder_no_repeat_ngram_size": 0,25    "eos_token_id": null,26    "exponential_decay_length_penalty": null,27    "finetuning_task": null,28    "forced_bos_token_id": null,29    "forced_eos_token_id": null,30    "hidden_size": 1024,31    "id2label": {32      "0": "LABEL_0",33      "1": "LABEL_1"34    },35    "initializer_range": 0.02,36    "input_vocab_size": 12096,37    "is_decoder": false,38    "is_encoder_decoder": false,39    "label2id": {40      "LABEL_0": 0,41      "LABEL_1": 142    },43    "length_penalty": 1.0,44    "max_length": 20,45    "min_length": 0,46    "model_type": "coarse_acoustics",47    "no_repeat_ngram_size": 0,48    "num_beam_groups": 1,49    "num_beams": 1,50    "num_heads": 16,51    "num_layers": 24,52    "num_return_sequences": 1,53    "output_attentions": false,54    "output_hidden_states": false,55    "output_scores": false,56    "output_vocab_size": 12096,57    "pad_token_id": null,58    "prefix": null,59    "problem_type": null,60    "pruned_heads": {},61    "remove_invalid_values": false,62    "repetition_penalty": 1.0,63    "return_dict": true,64    "return_dict_in_generate": false,65    "sep_token_id": null,66    "suppress_tokens": null,67    "task_specific_params": null,68    "temperature": 1.0,69    "tf_legacy_loss": false,70    "tie_encoder_decoder": false,71    "tie_word_embeddings": true,72    "tokenizer_class": null,73    "top_k": 50,74    "top_p": 1.0,75    "torch_dtype": "float32",76    "torchscript": false,77    "transformers_version": "4.31.0.dev0",78    "typical_p": 1.0,79    "use_bfloat16": false,80    "use_cache": true81  },82  "codec_config": {83    "_name_or_path": "facebook/encodec_24khz",84    "add_cross_attention": false,85    "architectures": [86      "EncodecModel"87    ],88    "audio_channels": 1,89    "bad_words_ids": null,90    "begin_suppress_tokens": null,91    "bos_token_id": null,92    "chunk_length_s": null,93    "chunk_size_feed_forward": 0,94    "codebook_dim": 128,95    "codebook_size": 1024,96    "compress": 2,97    "cross_attention_hidden_size": null,98    "decoder_start_token_id": null,99    "dilation_growth_rate": 2,100    "diversity_penalty": 0.0,101    "do_sample": false,102    "early_stopping": false,103    "encoder_no_repeat_ngram_size": 0,104    "eos_token_id": null,105    "exponential_decay_length_penalty": null,106    "finetuning_task": null,107    "forced_bos_token_id": null,108    "forced_eos_token_id": null,109    "hidden_size": 128,110    "id2label": {111      "0": "LABEL_0",112      "1": "LABEL_1"113    },114    "is_decoder": false,115    "is_encoder_decoder": false,116    "kernel_size": 7,117    "label2id": {118      "LABEL_0": 0,119      "LABEL_1": 1120    },121    "last_kernel_size": 7,122    "length_penalty": 1.0,123    "max_length": 20,124    "min_length": 0,125    "model_type": "encodec",126    "no_repeat_ngram_size": 0,127    "norm_type": "weight_norm",128    "normalize": false,129    "num_beam_groups": 1,130    "num_beams": 1,131    "num_filters": 32,132    "num_lstm_layers": 2,133    "num_residual_layers": 1,134    "num_return_sequences": 1,135    "output_attentions": false,136    "output_hidden_states": false,137    "output_scores": false,138    "overlap": null,139    "pad_mode": "reflect",140    "pad_token_id": null,141    "prefix": null,142    "problem_type": null,143    "pruned_heads": {},144    "remove_invalid_values": false,145    "repetition_penalty": 1.0,146    "residual_kernel_size": 3,147    "return_dict": true,148    "return_dict_in_generate": false,149    "sampling_rate": 24000,150    "sep_token_id": null,151    "suppress_tokens": null,152    "target_bandwidths": [153      1.5,154      3.0,155      6.0,156      12.0,157      24.0158    ],159    "task_specific_params": null,160    "temperature": 1.0,161    "tf_legacy_loss": false,162    "tie_encoder_decoder": false,163    "tie_word_embeddings": true,164    "tokenizer_class": null,165    "top_k": 50,166    "top_p": 1.0,167    "torch_dtype": "float32",168    "torchscript": false,169    "transformers_version": "4.31.0.dev0",170    "trim_right_ratio": 1.0,171    "typical_p": 1.0,172    "upsampling_ratios": [173      8,174      5,175      4,176      2177    ],178    "use_bfloat16": false,179    "use_causal_conv": true,180    "use_conv_shortcut": true181  },182  "fine_acoustics_config": {183    "_name_or_path": "",184    "add_cross_attention": false,185    "architectures": [186      "BarkFineModel"187    ],188    "bad_words_ids": null,189    "begin_suppress_tokens": null,190    "bias": false,191    "block_size": 1024,192    "bos_token_id": null,193    "chunk_size_feed_forward": 0,194    "cross_attention_hidden_size": null,195    "decoder_start_token_id": null,196    "diversity_penalty": 0.0,197    "do_sample": false,198    "dropout": 0.0,199    "early_stopping": false,200    "encoder_no_repeat_ngram_size": 0,201    "eos_token_id": null,202    "exponential_decay_length_penalty": null,203    "finetuning_task": null,204    "forced_bos_token_id": null,205    "forced_eos_token_id": null,206    "hidden_size": 1024,207    "id2label": {208      "0": "LABEL_0",209      "1": "LABEL_1"210    },211    "initializer_range": 0.02,212    "input_vocab_size": 1056,213    "is_decoder": false,214    "is_encoder_decoder": false,215    "label2id": {216      "LABEL_0": 0,217      "LABEL_1": 1218    },219    "length_penalty": 1.0,220    "max_length": 20,221    "min_length": 0,222    "model_type": "fine_acoustics",223    "n_codes_given": 1,224    "n_codes_total": 8,225    "no_repeat_ngram_size": 0,226    "num_beam_groups": 1,227    "num_beams": 1,228    "num_heads": 16,229    "num_layers": 24,230    "num_return_sequences": 1,231    "output_attentions": false,232    "output_hidden_states": false,233    "output_scores": false,234    "output_vocab_size": 1056,235    "pad_token_id": null,236    "prefix": null,237    "problem_type": null,238    "pruned_heads": {},239    "remove_invalid_values": false,240    "repetition_penalty": 1.0,241    "return_dict": true,242    "return_dict_in_generate": false,243    "sep_token_id": null,244    "suppress_tokens": null,245    "task_specific_params": null,246    "temperature": 1.0,247    "tf_legacy_loss": false,248    "tie_encoder_decoder": false,249    "tie_word_embeddings": true,250    "tokenizer_class": null,251    "top_k": 50,252    "top_p": 1.0,253    "torch_dtype": "float32",254    "torchscript": false,255    "transformers_version": "4.31.0.dev0",256    "typical_p": 1.0,257    "use_bfloat16": false,258    "use_cache": true259  },260  "initializer_range": 0.02,261  "model_type": "bark",262  "semantic_config": {263    "_name_or_path": "",264    "add_cross_attention": false,265    "architectures": [266      "BarkSemanticModel"267    ],268    "bad_words_ids": null,269    "begin_suppress_tokens": null,270    "bias": false,271    "block_size": 1024,272    "bos_token_id": null,273    "chunk_size_feed_forward": 0,274    "cross_attention_hidden_size": null,275    "decoder_start_token_id": null,276    "diversity_penalty": 0.0,277    "do_sample": false,278    "dropout": 0.0,279    "early_stopping": false,280    "encoder_no_repeat_ngram_size": 0,281    "eos_token_id": null,282    "exponential_decay_length_penalty": null,283    "finetuning_task": null,284    "forced_bos_token_id": null,285    "forced_eos_token_id": null,286    "hidden_size": 1024,287    "id2label": {288      "0": "LABEL_0",289      "1": "LABEL_1"290    },291    "initializer_range": 0.02,292    "input_vocab_size": 129600,293    "is_decoder": false,294    "is_encoder_decoder": false,295    "label2id": {296      "LABEL_0": 0,297      "LABEL_1": 1298    },299    "length_penalty": 1.0,300    "max_length": 20,301    "min_length": 0,302    "model_type": "semantic",303    "no_repeat_ngram_size": 0,304    "num_beam_groups": 1,305    "num_beams": 1,306    "num_heads": 16,307    "num_layers": 24,308    "num_return_sequences": 1,309    "output_attentions": false,310    "output_hidden_states": false,311    "output_scores": false,312    "output_vocab_size": 10048,313    "pad_token_id": null,314    "prefix": null,315    "problem_type": null,316    "pruned_heads": {},317    "remove_invalid_values": false,318    "repetition_penalty": 1.0,319    "return_dict": true,320    "return_dict_in_generate": false,321    "sep_token_id": null,322    "suppress_tokens": null,323    "task_specific_params": null,324    "temperature": 1.0,325    "tf_legacy_loss": false,326    "tie_encoder_decoder": false,327    "tie_word_embeddings": true,328    "tokenizer_class": null,329    "top_k": 50,330    "top_p": 1.0,331    "torch_dtype": "float32",332    "torchscript": false,333    "transformers_version": "4.31.0.dev0",334    "typical_p": 1.0,335    "use_bfloat16": false,336    "use_cache": true337  },338  "torch_dtype": "float32",339  "transformers_version": null340}341