config.json
| 1 | { |
| 2 | "architectures": [ |
| 3 | "Qwen3TTSForConditionalGeneration" |
| 4 | ], |
| 5 | "assistant_token_id": 77091, |
| 6 | "im_end_token_id": 151645, |
| 7 | "im_start_token_id": 151644, |
| 8 | "tts_bos_token_id": 151672, |
| 9 | "tts_eos_token_id": 151673, |
| 10 | "tts_pad_token_id": 151671, |
| 11 | "model_type": "qwen3_tts", |
| 12 | "tokenizer_type": "qwen3_tts_tokenizer_12hz", |
| 13 | "tts_model_size": "1b7", |
| 14 | "tts_model_type": "custom_voice", |
| 15 | "talker_config": { |
| 16 | "attention_bias": false, |
| 17 | "attention_dropout": 0, |
| 18 | "code_predictor_config": { |
| 19 | "_name_or_path": "", |
| 20 | "add_cross_attention": false, |
| 21 | "architectures": null, |
| 22 | "attention_bias": false, |
| 23 | "attention_dropout": 0, |
| 24 | "bad_words_ids": null, |
| 25 | "begin_suppress_tokens": null, |
| 26 | "bos_token_id": null, |
| 27 | "chunk_size_feed_forward": 0, |
| 28 | "cross_attention_hidden_size": null, |
| 29 | "decoder_start_token_id": null, |
| 30 | "diversity_penalty": 0.0, |
| 31 | "do_sample": false, |
| 32 | "early_stopping": false, |
| 33 | "encoder_no_repeat_ngram_size": 0, |
| 34 | "eos_token_id": null, |
| 35 | "exponential_decay_length_penalty": null, |
| 36 | "finetuning_task": null, |
| 37 | "forced_bos_token_id": null, |
| 38 | "forced_eos_token_id": null, |
| 39 | "head_dim": 128, |
| 40 | "hidden_act": "silu", |
| 41 | "hidden_size": 1024, |
| 42 | "id2label": { |
| 43 | "0": "LABEL_0", |
| 44 | "1": "LABEL_1" |
| 45 | }, |
| 46 | "initializer_range": 0.02, |
| 47 | "intermediate_size": 3072, |
| 48 | "is_decoder": false, |
| 49 | "is_encoder_decoder": false, |
| 50 | "label2id": { |
| 51 | "LABEL_0": 0, |
| 52 | "LABEL_1": 1 |
| 53 | }, |
| 54 | "layer_types": [ |
| 55 | "full_attention", |
| 56 | "full_attention", |
| 57 | "full_attention", |
| 58 | "full_attention", |
| 59 | "full_attention" |
| 60 | ], |
| 61 | "length_penalty": 1.0, |
| 62 | "max_length": 20, |
| 63 | "max_position_embeddings": 65536, |
| 64 | "max_window_layers": 28, |
| 65 | "min_length": 0, |
| 66 | "model_type": "qwen3_tts_talker_code_predictor", |
| 67 | "no_repeat_ngram_size": 0, |
| 68 | "num_attention_heads": 16, |
| 69 | "num_beam_groups": 1, |
| 70 | "num_beams": 1, |
| 71 | "num_code_groups": 16, |
| 72 | "num_hidden_layers": 5, |
| 73 | "num_key_value_heads": 8, |
| 74 | "num_return_sequences": 1, |
| 75 | "output_attentions": false, |
| 76 | "output_hidden_states": false, |
| 77 | "output_scores": false, |
| 78 | "pad_token_id": null, |
| 79 | "prefix": null, |
| 80 | "problem_type": null, |
| 81 | "pruned_heads": {}, |
| 82 | "remove_invalid_values": false, |
| 83 | "repetition_penalty": 1.0, |
| 84 | "return_dict": true, |
| 85 | "return_dict_in_generate": false, |
| 86 | "rms_norm_eps": 1e-06, |
| 87 | "rope_scaling": null, |
| 88 | "rope_theta": 1000000, |
| 89 | "sep_token_id": null, |
| 90 | "sliding_window": null, |
| 91 | "suppress_tokens": null, |
| 92 | "task_specific_params": null, |
| 93 | "temperature": 1.0, |
| 94 | "tf_legacy_loss": false, |
| 95 | "tie_encoder_decoder": false, |
| 96 | "tie_word_embeddings": false, |
| 97 | "tokenizer_class": null, |
| 98 | "top_k": 50, |
| 99 | "top_p": 1.0, |
| 100 | "dtype": null, |
| 101 | "torchscript": false, |
| 102 | "typical_p": 1.0, |
| 103 | "use_bfloat16": false, |
| 104 | "use_cache": true, |
| 105 | "use_sliding_window": false, |
| 106 | "vocab_size": 2048 |
| 107 | }, |
| 108 | "codec_bos_id": 2149, |
| 109 | "codec_eos_token_id": 2150, |
| 110 | "codec_think_id": 2154, |
| 111 | "codec_language_id": { |
| 112 | "chinese": 2055, |
| 113 | "english": 2050, |
| 114 | "german": 2053, |
| 115 | "italian": 2070, |
| 116 | "portuguese": 2071, |
| 117 | "spanish": 2054, |
| 118 | "japanese": 2058, |
| 119 | "korean": 2064, |
| 120 | "french": 2061, |
| 121 | "russian": 2069, |
| 122 | "beijing_dialect": 2074, |
| 123 | "sichuan_dialect": 2062 |
| 124 | }, |
| 125 | "codec_nothink_id": 2155, |
| 126 | "codec_pad_id": 2148, |
| 127 | "codec_think_bos_id": 2156, |
| 128 | "codec_think_eos_id": 2157, |
| 129 | "spk_id": { |
| 130 | "serena": 3066, |
| 131 | "vivian": 3065, |
| 132 | "uncle_fu": 3010, |
| 133 | "ryan": 3061, |
| 134 | "aiden": 2861, |
| 135 | "ono_anna": 2873, |
| 136 | "sohee": 2864, |
| 137 | "eric": 2875, |
| 138 | "dylan": 2878 |
| 139 | }, |
| 140 | "spk_is_dialect": { |
| 141 | "serena": false, |
| 142 | "vivian": false, |
| 143 | "uncle_fu": false, |
| 144 | "ryan": false, |
| 145 | "aiden": false, |
| 146 | "ono_anna": false, |
| 147 | "sohee": false, |
| 148 | "eric": "sichuan_dialect", |
| 149 | "dylan": "beijing_dialect" |
| 150 | }, |
| 151 | "head_dim": 128, |
| 152 | "hidden_act": "silu", |
| 153 | "hidden_size": 2048, |
| 154 | "initializer_range": 0.02, |
| 155 | "intermediate_size": 6144, |
| 156 | "max_position_embeddings": 32768, |
| 157 | "model_type": "qwen3_tts_talker", |
| 158 | "num_attention_heads": 16, |
| 159 | "num_code_groups": 16, |
| 160 | "num_hidden_layers": 28, |
| 161 | "num_key_value_heads": 8, |
| 162 | "position_id_per_seconds": 13, |
| 163 | "rms_norm_eps": 1e-06, |
| 164 | "rope_scaling": { |
| 165 | "interleaved": true, |
| 166 | "mrope_section": [ |
| 167 | 24, |
| 168 | 20, |
| 169 | 20 |
| 170 | ], |
| 171 | "rope_type": "default", |
| 172 | "type": "default" |
| 173 | }, |
| 174 | "rope_theta": 1000000, |
| 175 | "sliding_window": null, |
| 176 | "text_hidden_size": 2048, |
| 177 | "text_vocab_size": 151936, |
| 178 | "use_cache": true, |
| 179 | "use_sliding_window": false, |
| 180 | "vocab_size": 3072 |
| 181 | }, |
| 182 | "transformers_version": "4.57.3" |
| 183 | } |
| 184 | |