bark-large / config.json
ylacombe's picture
ylacombe HF staff
Upload model
356b82e
{
"_commit_hash": null,
"architectures": [
"BarkModel"
],
"coarse_acoustics_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": [
"BarkCoarseModel"
],
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bias": false,
"block_size": 1024,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0.0,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"input_vocab_size": 12096,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "coarse_acoustics",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_heads": 16,
"num_layers": 24,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"output_vocab_size": 12096,
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "float32",
"torchscript": false,
"transformers_version": "4.31.0.dev0",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true
},
"codec_config": {
"_name_or_path": "ArthurZ/encodec_24khz",
"add_cross_attention": false,
"architectures": [
"EncodecModel"
],
"audio_channels": 1,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_length_s": null,
"chunk_size_feed_forward": 0,
"codebook_dim": 128,
"codebook_size": 1024,
"compress": 2,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"dilation_growth_rate": 2,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_size": 128,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"is_decoder": false,
"is_encoder_decoder": false,
"kernel_size": 7,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"last_kernel_size": 7,
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "encodec",
"no_repeat_ngram_size": 0,
"norm_type": "weight_norm",
"normalize": false,
"num_beam_groups": 1,
"num_beams": 1,
"num_filters": 32,
"num_lstm_layers": 2,
"num_residual_layers": 1,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"overlap": null,
"pad_mode": "reflect",
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"residual_kernel_size": 3,
"return_dict": true,
"return_dict_in_generate": false,
"sampling_rate": 24000,
"sep_token_id": null,
"suppress_tokens": null,
"target_bandwidths": [
1.5,
3.0,
6.0,
12.0,
24.0
],
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "float32",
"torchscript": false,
"transformers_version": "4.31.0.dev0",
"trim_right_ratio": 1.0,
"typical_p": 1.0,
"upsampling_ratios": [
8,
5,
4,
2
],
"use_bfloat16": false,
"use_causal_conv": true,
"use_conv_shortcut": true
},
"fine_acoustics_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": [
"BarkFineModel"
],
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bias": false,
"block_size": 1024,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0.0,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"input_vocab_size": 1056,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "fine_acoustics",
"n_codes_given": 1,
"n_codes_total": 8,
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_heads": 16,
"num_layers": 24,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"output_vocab_size": 1056,
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "float32",
"torchscript": false,
"transformers_version": "4.31.0.dev0",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true
},
"initializer_range": 0.02,
"model_type": "bark",
"semantic_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": [
"BarkSemanticModel"
],
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bias": false,
"block_size": 1024,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0.0,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"input_vocab_size": 129600,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "semantic",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_heads": 16,
"num_layers": 24,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"output_vocab_size": 10048,
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "float32",
"torchscript": false,
"transformers_version": "4.31.0.dev0",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true
},
"torch_dtype": "float32",
"transformers_version": null
}