| { | |
| "audio":{ | |
| "audio_processor": "audio", // to use dictate different audio processors, if available. | |
| "num_mels": 80, // size of the mel spec frame. | |
| "fft_size": 1024, // 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": null, // stft window length in ms. | |
| "frame_shift_ms": null, // stft window hop-lengh in ms. | |
| "hop_length": 256, | |
| "win_length": 1024, | |
| "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": 0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!! | |
| "mel_fmax": 8000, // maximum freq level for mel-spec. Tune for dataset!! | |
| "do_trim_silence": false, | |
| "spec_gain": 20 | |
| }, | |
| "characters":{ | |
| "pad": "_", | |
| "eos": "~", | |
| "bos": "^", | |
| "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!'(),-.:;? ", | |
| "punctuations":"!'(),-.:;? ", | |
| "phonemes":"iyɨʉɯuɪʏʊeøɘəɵɤoɛœɜɞʌɔæɐaɶɑɒᵻʘɓǀɗǃʄǂɠǁʛpbtdʈɖcɟkɡqɢʔɴŋɲɳnɱmʙrʀⱱɾɽɸβfvθðszʃʒʂʐçʝxɣχʁħʕhɦɬɮʋɹɻjɰlɭʎʟˈˌːˑʍwɥʜʢʡɕʑɺɧɚ˞ɫ" | |
| }, | |
| "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, | |
| "num_loader_workers": 4, | |
| "memory_size": 5, | |
| "save_step": 200, | |
| "data_path": "tests/data/ljspeech/", | |
| "output_path": "result", | |
| "min_seq_len": 0, | |
| "max_seq_len": 300, | |
| "log_dir": "tests/outputs/", | |
| // MULTI-SPEAKER and GST | |
| "use_speaker_embedding": false, // use speaker embedding to enable multi-speaker learning. | |
| "use_gst": true, // use global style tokens | |
| "gst": { // gst parameter if gst is enabled | |
| "gst_style_input": null, // Condition the style input either on a | |
| // -> wave file [path to wave] or | |
| // -> dictionary using the style tokens {'token1': 'value', 'token2': 'value'} example {"0": 0.15, "1": 0.15, "5": -0.15} | |
| // with the dictionary being len(dict) <= len(gst_style_tokens). | |
| "gst_use_speaker_embedding": true, // if true pass speaker embedding in attention input GST. | |
| "gst_embedding_dim": 512, | |
| "gst_num_heads": 4, | |
| "gst_style_tokens": 10 | |
| } | |
| } | |