suno/bark
1.6k30k
1{2 "coarse_acoustics_config": {3 "_from_model_config": false,4 "bad_words_ids": null,5 "begin_suppress_tokens": null,6 "bos_token_id": null,7 "coarse_infer_token": 12050,8 "coarse_rate_hz": 75,9 "coarse_semantic_pad_token": 12048,10 "constraints": null,11 "decoder_start_token_id": null,12 "diversity_penalty": 0.0,13 "do_sample": true,14 "early_stopping": false,15 "encoder_no_repeat_ngram_size": 0,16 "encoder_repetition_penalty": 1.0,17 "eos_token_id": null,18 "epsilon_cutoff": 0.0,19 "eta_cutoff": 0.0,20 "exponential_decay_length_penalty": null,21 "force_words_ids": null,22 "forced_bos_token_id": null,23 "forced_decoder_ids": null,24 "forced_eos_token_id": null,25 "generation_kwargs": {},26 "guidance_scale": null,27 "length_penalty": 1.0,28 "max_coarse_history": 630,29 "max_coarse_input_length": 256,30 "max_length": 20,31 "max_new_tokens": null,32 "max_time": null,33 "min_length": 0,34 "min_new_tokens": null,35 "n_coarse_codebooks": 2,36 "no_repeat_ngram_size": 0,37 "num_beam_groups": 1,38 "num_beams": 1,39 "num_return_sequences": 1,40 "output_attentions": false,41 "output_hidden_states": false,42 "output_scores": false,43 "pad_token_id": null,44 "penalty_alpha": null,45 "remove_invalid_values": false,46 "renormalize_logits": true,47 "repetition_penalty": 1.0,48 "return_dict_in_generate": false,49 "sequence_bias": null,50 "sliding_window_len": 60,51 "suppress_tokens": null,52 "temperature": 0.7,53 "top_k": 50,54 "top_p": 1.0,55 "transformers_version": "4.31.0.dev0",56 "typical_p": 1.0,57 "use_cache": true58 },59 "codebook_size": 1024,60 "fine_acoustics_config": {61 "_from_model_config": false,62 "bad_words_ids": null,63 "begin_suppress_tokens": null,64 "bos_token_id": null,65 "constraints": null,66 "decoder_start_token_id": null,67 "diversity_penalty": 0.0,68 "do_sample": false,69 "early_stopping": false,70 "encoder_no_repeat_ngram_size": 0,71 "encoder_repetition_penalty": 1.0,72 "eos_token_id": null,73 "epsilon_cutoff": 0.0,74 "eta_cutoff": 0.0,75 "exponential_decay_length_penalty": null,76 "force_words_ids": null,77 "forced_bos_token_id": null,78 "forced_decoder_ids": null,79 "forced_eos_token_id": null,80 "generation_kwargs": {},81 "guidance_scale": null,82 "length_penalty": 1.0,83 "max_fine_history_length": 512,84 "max_fine_input_length": 1024,85 "max_length": 20,86 "max_new_tokens": null,87 "max_time": null,88 "min_length": 0,89 "min_new_tokens": null,90 "n_fine_codebooks": 8,91 "no_repeat_ngram_size": 0,92 "num_beam_groups": 1,93 "num_beams": 1,94 "num_return_sequences": 1,95 "output_attentions": false,96 "output_hidden_states": false,97 "output_scores": false,98 "pad_token_id": null,99 "penalty_alpha": null,100 "remove_invalid_values": false,101 "renormalize_logits": false,102 "repetition_penalty": 1.0,103 "return_dict_in_generate": false,104 "sequence_bias": null,105 "suppress_tokens": null,106 "temperature": 0.5,107 "top_k": 50,108 "top_p": 1.0,109 "transformers_version": "4.31.0.dev0",110 "typical_p": 1.0,111 "use_cache": true112 },113 "model_type": "bark",114 "sample_rate": 24000,115 "semantic_config": {116 "_from_model_config": false,117 "bad_words_ids": null,118 "begin_suppress_tokens": null,119 "bos_token_id": null,120 "constraints": null,121 "decoder_start_token_id": null,122 "diversity_penalty": 0.0,123 "do_sample": true,124 "early_stopping": false,125 "encoder_no_repeat_ngram_size": 0,126 "encoder_repetition_penalty": 1.0,127 "eos_token_id": 10000,128 "epsilon_cutoff": 0.0,129 "eta_cutoff": 0.0,130 "exponential_decay_length_penalty": null,131 "force_words_ids": null,132 "forced_bos_token_id": null,133 "forced_decoder_ids": null,134 "forced_eos_token_id": null,135 "generation_kwargs": {},136 "guidance_scale": null,137 "length_penalty": 1.0,138 "max_input_semantic_length": 256,139 "max_length": 20,140 "max_new_tokens": 768,141 "max_time": null,142 "min_length": 0,143 "min_new_tokens": null,144 "no_repeat_ngram_size": 0,145 "num_beam_groups": 1,146 "num_beams": 1,147 "num_return_sequences": 1,148 "output_attentions": false,149 "output_hidden_states": false,150 "output_scores": false,151 "pad_token_id": null,152 "penalty_alpha": null,153 "remove_invalid_values": false,154 "renormalize_logits": true,155 "repetition_penalty": 1.0,156 "return_dict_in_generate": false,157 "semantic_infer_token": 129599,158 "semantic_pad_token": 10000,159 "semantic_rate_hz": 49.9,160 "semantic_vocab_size": 10000,161 "sequence_bias": null,162 "suppress_tokens": null,163 "temperature": 0.7,164 "text_encoding_offset": 10048,165 "text_pad_token": 129595,166 "top_k": 50,167 "top_p": 1.0,168 "transformers_version": "4.31.0.dev0",169 "typical_p": 1.0,170 "use_cache": true171 }172}173 