mirror of
https://www.modelscope.cn/iic/speech_sambert-hifigan_tts_zh-cn_16k.git
synced 2026-04-02 10:22:54 +08:00
130 lines
3.2 KiB
JSON
130 lines
3.2 KiB
JSON
{
|
|
"framework": "pytorch",
|
|
"task" : "text-to-speech",
|
|
"model" : {
|
|
"type" : "sambert-hifigan",
|
|
"lang_type" : "zhcn",
|
|
"sample_rate" : 16000,
|
|
"am": {
|
|
"am": {
|
|
"max_len": 800,
|
|
|
|
"embedding_dim": 512,
|
|
"encoder_num_layers": 8,
|
|
"encoder_num_heads": 8,
|
|
"encoder_num_units": 128,
|
|
"encoder_ffn_inner_dim": 1024,
|
|
"encoder_dropout": 0.1,
|
|
"encoder_attention_dropout": 0.1,
|
|
"encoder_relu_dropout": 0.1,
|
|
"encoder_projection_units": 32,
|
|
|
|
"speaker_units": 32,
|
|
"emotion_units": 32,
|
|
|
|
"predictor_filter_size": 41,
|
|
"predictor_fsmn_num_layers": 3,
|
|
"predictor_num_memory_units": 128,
|
|
"predictor_ffn_inner_dim": 256,
|
|
"predictor_dropout": 0.1,
|
|
"predictor_shift": 0,
|
|
"predictor_lstm_units": 128,
|
|
"dur_pred_prenet_units": [128, 128],
|
|
"dur_pred_lstm_units": 128,
|
|
|
|
"decoder_prenet_units": [256, 256],
|
|
"decoder_num_layers": 12,
|
|
"decoder_num_heads": 8,
|
|
"decoder_num_units": 128,
|
|
"decoder_ffn_inner_dim": 1024,
|
|
"decoder_dropout": 0.1,
|
|
"decoder_attention_dropout": 0.1,
|
|
"decoder_relu_dropout": 0.1,
|
|
|
|
"outputs_per_step": 3,
|
|
"num_mels": 80,
|
|
|
|
"postnet_filter_size": 41,
|
|
"postnet_fsmn_num_layers": 4,
|
|
"postnet_num_memory_units": 256,
|
|
"postnet_ffn_inner_dim": 512,
|
|
"postnet_dropout": 0.1,
|
|
"postnet_shift": 17,
|
|
"postnet_lstm_units": 128
|
|
|
|
},
|
|
|
|
"audio": {
|
|
"frame_shift_ms": 12.5
|
|
},
|
|
|
|
"linguistic_unit": {
|
|
"cleaners": "english_cleaners",
|
|
"lfeat_type_list": "sy,tone,syllable_flag,word_segment,emo_category,speaker_category",
|
|
"sy": "dict/sy_dict.txt",
|
|
"tone": "dict/tone_dict.txt",
|
|
"syllable_flag": "dict/syllable_flag_dict.txt",
|
|
"word_segment": "dict/word_segment_dict.txt",
|
|
"emo_category": "dict/emo_category_dict.txt",
|
|
"speaker_category": "dict/speaker_dict.txt"
|
|
},
|
|
|
|
"num_gpus": 1,
|
|
"batch_size": 32,
|
|
"group_size": 1024,
|
|
"learning_rate": 0.001,
|
|
"adam_b1": 0.9,
|
|
"adam_b2": 0.98,
|
|
"seed": 1234,
|
|
|
|
"num_workers": 4,
|
|
|
|
"dist_config": {
|
|
"dist_backend": "nccl",
|
|
"dist_url": "tcp://localhost:11111",
|
|
"world_size": 1
|
|
}
|
|
},
|
|
"vocoder" : {
|
|
"resblock": "1",
|
|
"num_gpus": 1,
|
|
"batch_size": 16,
|
|
"learning_rate": 0.0002,
|
|
"adam_b1": 0.8,
|
|
"adam_b2": 0.99,
|
|
"lr_decay": 0.999,
|
|
"seed": 1234,
|
|
|
|
"upsample_rates": [10,5,2,2],
|
|
"upsample_kernel_sizes": [20,11,4,4],
|
|
"upsample_initial_channel": 256,
|
|
"resblock_kernel_sizes": [3,7,11],
|
|
"resblock_dilation_sizes": [[1,3,5,7], [1,3,5,7], [1,3,5,7]],
|
|
|
|
"segment_size": 6400,
|
|
"num_mels": 80,
|
|
"num_freq": 1025,
|
|
"n_fft": 2048,
|
|
"hop_size": 200,
|
|
"win_size": 1000,
|
|
|
|
"sampling_rate": 16000,
|
|
|
|
"fmin": 0,
|
|
"fmax": 8000,
|
|
"fmax_for_loss": null,
|
|
|
|
"num_workers": 4,
|
|
|
|
"dist_config": {
|
|
"dist_backend": "nccl",
|
|
"dist_url": "tcp://localhost:54312",
|
|
"world_size": 1
|
|
}
|
|
}
|
|
},
|
|
"pipeline": {
|
|
"type": "sambert-hifigan-tts"
|
|
}
|
|
}
|