| { | |
| "base_config": "config/vits.json", | |
| "model_type": "VITS", | |
| "dataset": [ | |
| "LJSpeech", | |
| //"hifitts" | |
| ], | |
| "dataset_path": { | |
| // TODO: Fill in your dataset path | |
| "LJSpeech": "[LJSpeech dataset path]", | |
| //"hifitts": "[Hi-Fi TTS dataset path] | |
| }, | |
| // TODO: Fill in the output log path. The default value is "Amphion/ckpts/tts" | |
| "log_dir": "ckpts/tts", | |
| "preprocess": { | |
| //"extract_audio":true, | |
| "use_phone": true, | |
| // linguistic features | |
| "extract_phone": true, | |
| "phone_extractor": "espeak", // "espeak, pypinyin, pypinyin_initials_finals, lexicon (only for language=en-us right now)" | |
| // TODO: Fill in the output data path. The default value is "Amphion/data" | |
| "processed_dir": "data", | |
| "sample_rate": 22050, // target sampling rate | |
| "valid_file": "valid.json", // validation set | |
| //"use_spkid": true // use speaker ID to train multi-speaker TTS model | |
| }, | |
| "model":{ | |
| //"n_speakers": 10 // number of speakers, greater than or equal to the number of speakers in the dataset(s) used. The default value is 0 if not specified. | |
| }, | |
| "train": { | |
| "batch_size": 16, | |
| //"multi_speaker_training": true | |
| } | |
| } | |