|
{ |
|
"_name_or_path": "output_dir_training_multi_task/fit-train", |
|
"architectures": [ |
|
"ParlerTTSForConditionalGeneration" |
|
], |
|
"audio_encoder": { |
|
"_name_or_path": "ylacombe/dac_44khZ_8kbps", |
|
"add_cross_attention": false, |
|
"architectures": [ |
|
"DACModel" |
|
], |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"bos_token_id": null, |
|
"chunk_size_feed_forward": 0, |
|
"codebook_size": 1024, |
|
"cross_attention_hidden_size": null, |
|
"decoder_rates": [ |
|
8, |
|
8, |
|
4, |
|
2 |
|
], |
|
"decoder_start_token_id": null, |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"encoder_rates": [ |
|
2, |
|
4, |
|
8, |
|
8 |
|
], |
|
"eos_token_id": null, |
|
"exponential_decay_length_penalty": null, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"frame_rate": 86, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"latent_dim": 1024, |
|
"length_penalty": 1.0, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"model_bitrate": 8, |
|
"model_type": "cac", |
|
"no_repeat_ngram_size": 0, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_codebooks": 9, |
|
"num_return_sequences": 1, |
|
"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, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sampling_rate": 16000, |
|
"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, |
|
"typical_p": 1.0, |
|
"use_bfloat16": false |
|
}, |
|
"decoder": { |
|
"_name_or_path": "", |
|
"activation_dropout": 0.0, |
|
"activation_function": "gelu", |
|
"add_cross_attention": false, |
|
"architectures": [ |
|
"Qwen2ForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"bos_token_id": 1025, |
|
"chunk_size_feed_forward": 0, |
|
"cross_attention_hidden_size": null, |
|
"decoder_start_token_id": null, |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"dropout": 0.1, |
|
"early_stopping": false, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eos_token_id": 1024, |
|
"exponential_decay_length_penalty": null, |
|
"ffn_dim": 4096, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"hidden_act": "silu", |
|
"hidden_size": 1536, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"initializer_factor": 0.02, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 8960, |
|
"is_decoder": true, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"layerdrop": 0.0, |
|
"length_penalty": 1.0, |
|
"max_length": 20, |
|
"max_position_embeddings": 131072, |
|
"max_window_layers": 28, |
|
"min_length": 0, |
|
"model_type": "parler_tts_decoder", |
|
"no_repeat_ngram_size": 0, |
|
"num_attention_heads": 12, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_codebooks": 9, |
|
"num_hidden_layers": 28, |
|
"num_key_value_heads": 2, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": 1024, |
|
"prefix": null, |
|
"problem_type": null, |
|
"prompt_vocab_size": 153824, |
|
"pruned_heads": {}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"rms_norm_eps": 1e-06, |
|
"rope_theta": 1000000.0, |
|
"scale_embedding": false, |
|
"sep_token_id": null, |
|
"sliding_window": 131072, |
|
"suppress_tokens": null, |
|
"task_specific_params": null, |
|
"temperature": 1.0, |
|
"tf_legacy_loss": false, |
|
"tie_encoder_decoder": false, |
|
"tie_word_embeddings": false, |
|
"tokenizer_class": null, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"torch_dtype": "bfloat16", |
|
"torchscript": false, |
|
"typical_p": 1.0, |
|
"use_bfloat16": false, |
|
"use_cache": false, |
|
"use_sliding_window": false, |
|
"vocab_size": 1088 |
|
}, |
|
"decoder_start_token_id": 1025, |
|
"model_type": "parler_tts", |
|
"pad_token_id": 1024, |
|
"speaker_encoder": { |
|
"_name_or_path": "speech_eres2net_sv_zh-cn_16k-common", |
|
"add_cross_attention": false, |
|
"architectures": [ |
|
"SpeakerRecERes2Net" |
|
], |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"bos_token_id": null, |
|
"chunk_size_feed_forward": 0, |
|
"config_str": "batchnorm-relu", |
|
"cross_attention_hidden_size": null, |
|
"decoder_start_token_id": null, |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"embedding_size": 192, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eos_token_id": null, |
|
"exponential_decay_length_penalty": null, |
|
"feat_dim": 80, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"growth_rate": 32, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"init_channels": 128, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"length_penalty": 1.0, |
|
"m_channels": 64, |
|
"max_length": 20, |
|
"memory_efficient": true, |
|
"min_length": 0, |
|
"model_type": "speaker_rec", |
|
"no_repeat_ngram_size": 0, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_level": "segment", |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"pooling_func": "TSTP", |
|
"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, |
|
"typical_p": 1.0, |
|
"use_bfloat16": false |
|
}, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.44.2", |
|
"vocab_size": 153824 |
|
} |
|
|