{ | |
"model": "speedy_speech", | |
"run_name": "test_sample_dataset_run", | |
"run_description": "sample dataset test run", | |
// AUDIO PARAMETERS | |
"audio":{ | |
// stft parameters | |
"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. | |
"preemphasis": 0.0, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis. | |
"ref_level_db": 20, // reference level db, theoretically 20db is the sound of air. | |
// Silence trimming | |
"do_trim_silence": true,// enable trimming of slience of audio as you load it. LJspeech (true), TWEB (false), Nancy (true) | |
"trim_db": 60, // threshold for timming silence. Set this according to your dataset. | |
// Griffin-Lim | |
"power": 1.5, // 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. | |
// 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, | |
// 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": 4.0, // 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": "ABCDEFGHIJKLMNOPQRSTUVWXYZÇÃÀÁÂÊÉÍÓÔÕÚÛabcdefghijklmnopqrstuvwxyzçãàáâêéíóôõúû!(),-.:;? ", | |
// "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 | |
"distributed":{ | |
"backend": "nccl", | |
"url": "tcp:\/\/localhost:54321" | |
}, | |
"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 | |
"positional_encoding": true, | |
"hidden_channels": 128, | |
"encoder_type": "residual_conv_bn", | |
"encoder_type": "residual_conv_bn", | |
"encoder_params":{ | |
"kernel_size": 4, | |
"dilations": [1, 2, 4, 1, 2, 4, 1, 2, 4, 1, 2, 4, 1], | |
"num_conv_blocks": 2, | |
"num_res_blocks": 13 | |
}, | |
"decoder_type": "residual_conv_bn", | |
"decoder_params":{ | |
"kernel_size": 4, | |
"dilations": [1, 2, 4, 8, 1, 2, 4, 8, 1, 2, 4, 8, 1, 2, 4, 8, 1], | |
"num_conv_blocks": 2, | |
"num_res_blocks": 17 | |
}, | |
// TRAINING | |
"batch_size":64, // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'. | |
"eval_batch_size":32, | |
"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. | |
// LOSS PARAMETERS | |
"ssim_alpha": 1, | |
"l1_alpha": 1, | |
"huber_alpha": 1, | |
// VALIDATION | |
"run_eval": true, | |
"test_delay_epochs": -1, //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": 1.0, // upper limit for gradients for clipping. | |
"epochs": 1, // total number of epochs to train. | |
"lr": 0.002, // Initial learning rate. If Noam decay is active, maximum learning rate. | |
"warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr" | |
// TENSORBOARD and LOGGING | |
"print_step": 1, // 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.:set n | |
"mixed_precision": false, | |
// DATA LOADING | |
"text_cleaner": "english_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": 2, // DATASET-RELATED: minimum text length to use in training | |
"max_seq_len": 300, // DATASET-RELATED: maximum text length | |
"compute_f0": false, // compute f0 values in data-loader | |
"compute_input_seq_cache": false, // if true, text sequences are computed before starting training. If phonemes are enabled, they are also computed at this stage. | |
// PATHS | |
"output_path": "tests/train_outputs/", | |
// PHONEMES | |
"phoneme_cache_path": "tests/train_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 pronoun[ciation. | |
"phoneme_language": "en-us", // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages | |
// MULTI-SPEAKER and GST | |
"use_speaker_embedding": false, // use speaker embedding to enable multi-speaker learning. | |
"use_d_vector_file": false, // if true, forces the model to use external embedding per sample instead of nn.embeddings, that is, it supports external embeddings such as those used at: https://arxiv.org/abs /1806.04558 | |
"d_vector_file": "/home/erogol/Data/libritts/speakers.json", // if not null and use_d_vector_file is true, it is used to load a specific embedding file and thus uses these embeddings instead of nn.embeddings, that is, it supports external embeddings such as those used at: https://arxiv.org/abs /1806.04558 | |
// 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", | |
"meta_file_attn_mask": "tests/data/ljspeech/metadata_attn_mask.txt" | |
} | |
] | |
} |