bark / generation_config.json
ylacombe's picture
7e798c0f9215fd0587d45f7f7eebe375fa8dedd010053abca86960e842a24f93
af7abdf
raw
history blame
4.91 kB
{
"coarse_acoustics_config": {
"_from_model_config": false,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"coarse_infer_token": 12050,
"coarse_rate_hz": 75,
"coarse_semantic_pad_token": 12048,
"constraints": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": true,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"encoder_repetition_penalty": 1.0,
"eos_token_id": null,
"epsilon_cutoff": 0.0,
"eta_cutoff": 0.0,
"exponential_decay_length_penalty": null,
"force_words_ids": null,
"forced_bos_token_id": null,
"forced_decoder_ids": null,
"forced_eos_token_id": null,
"generation_kwargs": {},
"guidance_scale": null,
"length_penalty": 1.0,
"max_coarse_history": 630,
"max_coarse_input_length": 256,
"max_length": 20,
"max_new_tokens": null,
"max_time": null,
"min_length": 0,
"min_new_tokens": null,
"n_coarse_codebooks": 2,
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"penalty_alpha": null,
"remove_invalid_values": false,
"renormalize_logits": true,
"repetition_penalty": 1.0,
"return_dict_in_generate": false,
"sequence_bias": null,
"sliding_window_len": 60,
"suppress_tokens": null,
"temperature": 0.7,
"top_k": 50,
"top_p": 1.0,
"transformers_version": "4.31.0.dev0",
"typical_p": 1.0,
"use_cache": true
},
"codebook_size": 1024,
"fine_acoustics_config": {
"_from_model_config": false,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"constraints": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"encoder_repetition_penalty": 1.0,
"eos_token_id": null,
"epsilon_cutoff": 0.0,
"eta_cutoff": 0.0,
"exponential_decay_length_penalty": null,
"force_words_ids": null,
"forced_bos_token_id": null,
"forced_decoder_ids": null,
"forced_eos_token_id": null,
"generation_kwargs": {},
"guidance_scale": null,
"length_penalty": 1.0,
"max_fine_history_length": 512,
"max_fine_input_length": 1024,
"max_length": 20,
"max_new_tokens": null,
"max_time": null,
"min_length": 0,
"min_new_tokens": null,
"n_fine_codebooks": 8,
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"penalty_alpha": null,
"remove_invalid_values": false,
"renormalize_logits": false,
"repetition_penalty": 1.0,
"return_dict_in_generate": false,
"sequence_bias": null,
"suppress_tokens": null,
"temperature": 0.5,
"top_k": 50,
"top_p": 1.0,
"transformers_version": "4.31.0.dev0",
"typical_p": 1.0,
"use_cache": true
},
"model_type": "bark",
"sample_rate": 24000,
"semantic_config": {
"_from_model_config": false,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"constraints": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": true,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"encoder_repetition_penalty": 1.0,
"eos_token_id": 10000,
"epsilon_cutoff": 0.0,
"eta_cutoff": 0.0,
"exponential_decay_length_penalty": null,
"force_words_ids": null,
"forced_bos_token_id": null,
"forced_decoder_ids": null,
"forced_eos_token_id": null,
"generation_kwargs": {},
"guidance_scale": null,
"length_penalty": 1.0,
"max_input_semantic_length": 256,
"max_length": 20,
"max_new_tokens": 768,
"max_time": null,
"min_length": 0,
"min_new_tokens": null,
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"penalty_alpha": null,
"remove_invalid_values": false,
"renormalize_logits": true,
"repetition_penalty": 1.0,
"return_dict_in_generate": false,
"semantic_infer_token": 129599,
"semantic_pad_token": 10000,
"semantic_rate_hz": 49.9,
"semantic_vocab_size": 10000,
"sequence_bias": null,
"suppress_tokens": null,
"temperature": 0.7,
"text_encoding_offset": 10048,
"text_pad_token": 129595,
"top_k": 50,
"top_p": 1.0,
"transformers_version": "4.31.0.dev0",
"typical_p": 1.0,
"use_cache": true
}
}