{ "architectures": [ "XttsGPT" ], "audio_config": { "fmax": 8000, "fmin": 0, "hop_length": 256, "mel_channels": 80, "mel_norms_file": null, "n_fft": 1024, "output_sample_rate": 24000, "power": 1.0, "sample_rate": 22050, "win_length": 1024 }, "auto_map": { "AutoConfig": "AstraMindAI/xtts2--xtts2_config.XTTSConfig", "AutoModelForCausalLM": "AstraMindAI/xtts2--xtts2_modeling.Xtts", "AutoTokenizer": "AstraMindAI/xtts2--tokenizer.XTTSTokenizerFast" }, "cond_d_vector_in_each_upsampling_layer": true, "d_vector_dim": 512, "decoder_input_dim": 1024, "duration_const": 102400, "gpt": { "model_type": "xtts_gpt" }, "gpt_code_stride_len": 1024, "gpt_config": { "_attn_implementation_autoset": false, "_name_or_path": "", "activation_function": "gelu", "add_cross_attention": false, "architectures": [ "XttsGPT" ], "attn_pdrop": 0.1, "audio_config": { "mel_channels": 80, "output_sample_rate": 24000, "sample_rate": 22050 }, "auto_map": { "AutoConfig": "AstraMindAI/xtts2-gpt--gpt_config.XTTSGPTConfig", "AutoModelForCausalLM": "AstraMindAI/xtts2-gpt--xtts2_gpt_modeling.XttsGPT" }, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_input_dim": 1024, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "enable_redaction": 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, "gpt_batch_size": 1, "gpt_max_audio_tokens": 605, "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "is_decoder": false, "is_encoder_decoder": false, "kv_cache": true, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_epsilon": 1e-05, "length_penalty": 1.0, "max_audio_tokens": 605, "max_length": 20, "max_prompt_tokens": 70, "max_text_tokens": 402, "min_length": 0, "model_type": "xtts_gpt", "n_inner": 4096, "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_audio_tokens": 1026, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 30, "num_return_sequences": 1, "number_text_tokens": 6681, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "reorder_and_upcast_attn": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "scale_attn_by_inverse_layer_idx": false, "sep_token_id": null, "start_audio_token": 1024, "start_text_token": null, "stop_audio_token": 1025, "stop_text_token": 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": null, "torchscript": false, "transformers_version": "4.46.0", "typical_p": 1.0, "use_bfloat16": false, "use_masking_gt_prompt_approach": true, "use_perceiver_resampler": true, "vocab_size": 6681 }, "input_sample_rate": 22050, "languages": [ "en", "es", "fr", "de", "it", "pt", "pl", "tr", "ru", "nl", "cs", "ar", "zh-cn", "hu", "ko", "ja", "hi" ], "model_type": "xtts", "num_chars": 255, "output_hop_length": 256, "output_sample_rate": 24000, "tokenizer_file": "", "transformers_version": "4.46.0" }