{ "audio":{ "audio_processor": "audio", // to use dictate different audio processors, if available. "num_mels": 80, // size of the mel spec frame. "num_freq": 1025, // number of stft frequency levels. Size of the linear spectogram frame. "sample_rate": 22050, // wav sample-rate. If different than the original data, it is resampled. "frame_length_ms": 50, // stft window length in ms. "frame_shift_ms": 12.5, // stft window hop-lengh in ms. "preemphasis": 0.97, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis. "min_level_db": -100, // normalization range "ref_level_db": 20, // reference level db, theoretically 20db is the sound of air. "power": 1.5, // value to sharpen wav signals after GL algorithm. "griffin_lim_iters": 30,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation. "signal_norm": true, // normalize the spec values in range [0, 1] "symmetric_norm": true, // move normalization to range [-1, 1] "clip_norm": true, // clip normalized values into the range. "max_norm": 4, // scale normalization to range [-max_norm, max_norm] or [0, max_norm] "mel_fmin": 95, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!! "mel_fmax": 7600 // maximum freq level for mel-spec. Tune for dataset!! }, "hidden_size": 128, "embedding_size": 256, "text_cleaner": "english_cleaners", "epochs": 2000, "lr": 0.003, "lr_patience": 5, "lr_decay": 0.5, "batch_size": 2, "r": 5, "mk": 1.0, "priority_freq": false, "num_loader_workers": 4, "save_step": 200, "data_path": "/home/erogol/Data/LJSpeech-1.1/", "data_path_cache": "/home/erogol/Data/LJSpeech-1.1/tts_cache/", "output_path": "result", "min_seq_len": 0, "log_dir": "/home/erogol/projects/TTS/logs/" }