| { | |
| "architectures": [ | |
| "FastSpeech2" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 0, | |
| "decoder_attention_heads": 2, | |
| "decoder_ffn_dim": 1536, | |
| "decoder_layerdrop": 0.1, | |
| "decoder_layers": 4, | |
| "decoder_start_token_id": 2, | |
| "d_model": 384, | |
| "dropout": 0.1, | |
| "encoder_attention_heads": 2, | |
| "encoder_ffn_dim": 1536, | |
| "encoder_layerdrop": 0.1, | |
| "encoder_layers": 6, | |
| "eos_token_id": 2, | |
| "ffn_dim": 1536, | |
| "init_std": 0.02, | |
| "is_decoder": false, | |
| "is_encoder_decoder": true, | |
| "max_position_embeddings": 2048, | |
| "model_type": "fastspeech2", | |
| "num_attention_heads": 2, | |
| "num_hidden_layers": 6, | |
| "pad_token_id": 1, | |
| "pitch_feature_level": "phoneme", | |
| "position_embedding_type": "absolute", | |
| "reduction_factor": 1, | |
| "speaker_embed_dim": 256, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.35.2", | |
| "use_cache": true, | |
| "vocab_size": 300, | |
| "max_duration_ms": 25600, | |
| "min_duration_ms": 1, | |
| "scaling_factor": 1.0 | |
| } |