| { | |
| "model": "glow_tts", | |
| "run_name": "glow-tts-gatedconv", | |
| "run_description": "glow-tts model training with gated conv.", | |
| // AUDIO PARAMETERS | |
| "audio":{ | |
| "fft_size": 1024, // number of stft frequency levels. Size of the linear spectogram frame. | |
| "win_length": 1024, // stft window length in ms. | |
| "hop_length": 256, // stft window hop-lengh in ms. | |
| "frame_length_ms": null, // stft window length in ms.If null, 'win_length' is used. | |
| "frame_shift_ms": null, // stft window hop-lengh in ms. If null, 'hop_length' is used. | |
| // Audio processing parameters | |
| "sample_rate": 22050, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled. | |
| "preemphasis": 0.0, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis. | |
| "ref_level_db": 0, // reference level db, theoretically 20db is the sound of air. | |
| // Griffin-Lim | |
| "power": 1.1, // value to sharpen wav signals after GL algorithm. | |
| "griffin_lim_iters": 60,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation. | |
| // Silence trimming | |
| "do_trim_silence": true,// enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true) | |
| "trim_db": 60, // threshold for timming silence. Set this according to your dataset. | |
| // MelSpectrogram parameters | |
| "num_mels": 80, // size of the mel spec frame. | |
| "mel_fmin": 50.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!! | |
| "mel_fmax": 7600.0, // maximum freq level for mel-spec. Tune for dataset!! | |
| "spec_gain": 1.0, // scaler value appplied after log transform of spectrogram. | |
| // Normalization parameters | |
| "signal_norm": true, // normalize spec values. Mean-Var normalization if 'stats_path' is defined otherwise range normalization defined by the other params. | |
| "min_level_db": -100, // lower bound for normalization | |
| "symmetric_norm": true, // move normalization to range [-1, 1] | |
| "max_norm": 1.0, // scale normalization to range [-max_norm, max_norm] or [0, max_norm] | |
| "clip_norm": true, // clip normalized values into the range. | |
| "stats_path": null // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored | |
| }, | |
| // VOCABULARY PARAMETERS | |
| // if custom character set is not defined, | |
| // default set in symbols.py is used | |
| // "characters":{ | |
| // "pad": "_", | |
| // "eos": "~", | |
| // "bos": "^", | |
| // "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!'(),-.:;? ", | |
| // "punctuations":"!'(),-.:;? ", | |
| // "phonemes":"iyɨʉɯuɪʏʊeøɘəɵɤoɛœɜɞʌɔæɐaɶɑɒᵻʘɓǀɗǃʄǂɠǁʛpbtdʈɖcɟkɡqɢʔɴŋɲɳnɱmʙrʀⱱɾɽɸβfvθðszʃʒʂʐçʝxɣχʁħʕhɦɬɮʋɹɻjɰlɭʎʟˈˌːˑʍwɥʜʢʡɕʑɺɧɚ˞ɫ" | |
| // }, | |
| "add_blank": false, // if true add a new token after each token of the sentence. This increases the size of the input sequence, but has considerably improved the prosody of the GlowTTS model. | |
| // DISTRIBUTED TRAINING | |
| "mixed_precision": false, | |
| "distributed":{ | |
| "backend": "nccl", | |
| "url": "tcp:\/\/localhost:54323" | |
| }, | |
| "reinit_layers": [], // give a list of layer names to restore from the given checkpoint. If not defined, it reloads all heuristically matching layers. | |
| // MODEL PARAMETERS | |
| "use_mas": false, // use Monotonic Alignment Search if true. Otherwise use pre-computed attention alignments. | |
| // TRAINING | |
| "batch_size": 8, // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'. | |
| "eval_batch_size": 8, | |
| "r": 1, // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled. | |
| "loss_masking": true, // enable / disable loss masking against the sequence padding. | |
| "data_dep_init_iter": 1, | |
| // VALIDATION | |
| "run_eval": true, | |
| "test_delay_epochs": 0, //Until attention is aligned, testing only wastes computation time. | |
| "test_sentences_file": null, // set a file to load sentences to be used for testing. If it is null then we use default english sentences. | |
| // OPTIMIZER | |
| "noam_schedule": true, // use noam warmup and lr schedule. | |
| "grad_clip": 5.0, // upper limit for gradients for clipping. | |
| "epochs": 1, // total number of epochs to train. | |
| "lr": 1e-3, // Initial learning rate. If Noam decay is active, maximum learning rate. | |
| "wd": 0.000001, // Weight decay weight. | |
| "warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr" | |
| "seq_len_norm": false, // Normalize eash sample loss with its length to alleviate imbalanced datasets. Use it if your dataset is small or has skewed distribution of sequence lengths. | |
| "hidden_channels_encoder": 192, | |
| "hidden_channels_decoder": 192, | |
| "hidden_channels_duration_predictor": 256, | |
| "use_encoder_prenet": true, | |
| "encoder_type": "rel_pos_transformer", | |
| "encoder_params": { | |
| "kernel_size":3, | |
| "dropout_p": 0.1, | |
| "num_layers": 6, | |
| "num_heads": 2, | |
| "hidden_channels_ffn": 768, | |
| "input_length": null | |
| }, | |
| // TENSORBOARD and LOGGING | |
| "print_step": 25, // Number of steps to log training on console. | |
| "tb_plot_step": 100, // Number of steps to plot TB training figures. | |
| "print_eval": false, // If True, it prints intermediate loss values in evalulation. | |
| "save_step": 5000, // Number of training steps expected to save traninpg stats and checkpoints. | |
| "checkpoint": true, // If true, it saves checkpoints per "save_step" | |
| "keep_all_best": true, // If true, keeps all best_models after keep_after steps | |
| "keep_after": 10000, // Global step after which to keep best models if keep_all_best is true | |
| "tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging. | |
| "apex_amp_level": null, | |
| // DATA LOADING | |
| "text_cleaner": "phoneme_cleaners", | |
| "enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars. | |
| "num_loader_workers": 0, // number of training data loader processes. Don't set it too big. 4-8 are good values. | |
| "num_eval_loader_workers": 0, // number of evaluation data loader processes. | |
| "batch_group_size": 0, //Number of batches to shuffle after bucketing. | |
| "min_seq_len": 3, // DATASET-RELATED: minimum text length to use in training | |
| "max_seq_len": 500, // DATASET-RELATED: maximum text length | |
| "compute_f0": false, // compute f0 values in data-loader | |
| "compute_input_seq_cache": true, | |
| "use_noise_augment": true, | |
| // PATHS | |
| "output_path": "tests/train_outputs/", | |
| // PHONEMES | |
| "phoneme_cache_path": "tests/outputs/phoneme_cache/", // phoneme computation is slow, therefore, it caches results in the given folder. | |
| "use_phonemes": false, // use phonemes instead of raw characters. It is suggested for better pronounciation. | |
| "phoneme_language": "en-us", // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages | |
| // MULTI-SPEAKER and GST | |
| "use_d_vector_file": false, | |
| "d_vector_file": null, | |
| "use_speaker_embedding": false, // use speaker embedding to enable multi-speaker learning. | |
| // DATASETS | |
| "datasets": // List of datasets. They all merged and they get different speaker_ids. | |
| [ | |
| { | |
| "formatter": "ljspeech", | |
| "path": "tests/data/ljspeech/", | |
| "meta_file_train": "metadata.csv", | |
| "meta_file_val": "metadata.csv" | |
| } | |
| ] | |
| } | |