|
{ |
|
"add_postnet": true, |
|
"architectures": [ |
|
"FastSpeech2Model" |
|
], |
|
"attention_dropout": 0, |
|
"decoder_attention_heads": 2, |
|
"decoder_embed_dim": 256, |
|
"decoder_layers": 4, |
|
"encoder_attention_heads": 2, |
|
"encoder_embed_dim": 256, |
|
"encoder_layers": 4, |
|
"energy_max": 5.646703243255615, |
|
"energy_min": -3.548804759979248, |
|
"fft_dropout": 0.2, |
|
"fft_hidden_dim": 1024, |
|
"fft_kernel_size": 9, |
|
"initializer_range": 0.0625, |
|
"max_source_positions": 1024, |
|
"model_type": "fastspeech2", |
|
"num_speakers": 200, |
|
"pad_token_id": 1, |
|
"pitch_max": 5.164862652912731, |
|
"pitch_min": -2.5049682966705484, |
|
"postnet_conv_dim": 512, |
|
"postnet_conv_kernel_size": 5, |
|
"postnet_dropout": 0.5, |
|
"postnet_layers": 5, |
|
"speaker_embed_dim": 64, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.19.0.dev0", |
|
"use_mean": true, |
|
"use_standard_deviation": true, |
|
"var_pred_dropout": 0.5, |
|
"var_pred_hidden_dim": 256, |
|
"var_pred_kernel_size": 3, |
|
"vocab_size": 74 |
|
} |
|
|