mirror of
https://github.com/wassname/TTS.git
synced 2026-09-24 13:10:16 +08:00
Mass refactoring
This commit is contained in:
erogol
@@ -0,0 +1,55 @@
|
||||
{
|
||||
"audio":{
|
||||
"audio_processor": "audio", // to use dictate different audio processors, if available.
|
||||
"num_mels": 80, // size of the mel spec frame.
|
||||
"num_freq": 513, // 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/"
|
||||
}
|
||||
@@ -0,0 +1,151 @@
|
||||
{
|
||||
"model": "Tacotron2",
|
||||
"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": 0.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
|
||||
"mel_fmax": 8000.0, // maximum freq level for mel-spec. Tune for dataset!!
|
||||
"spec_gain": 20.0,
|
||||
|
||||
// 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": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!'(),-.:;? ",
|
||||
// "punctuations":"!'(),-.:;? ",
|
||||
// "phonemes":"iyɨʉɯuɪʏʊeøɘəɵɤoɛœɜɞʌɔæɐaɶɑɒᵻʘɓǀɗǃʄǂɠǁʛpbtdʈɖcɟkɡqɢʔɴŋɲɳnɱmʙrʀⱱɾɽɸβfvθðszʃʒʂʐçʝxɣχʁħʕhɦɬɮʋɹɻjɰlɭʎʟˈˌːˑʍwɥʜʢʡɕʑɺɧɚ˞ɫ"
|
||||
// },
|
||||
|
||||
// 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.
|
||||
|
||||
// TRAINING
|
||||
"batch_size": 1, // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
|
||||
"eval_batch_size":1,
|
||||
"r": 7, // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled.
|
||||
"gradual_training": [[0, 7, 4]], //set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled. For Tacotron, you might need to reduce the 'batch_size' as you proceeed.
|
||||
"loss_masking": true, // enable / disable loss masking against the sequence padding.
|
||||
"ga_alpha": 10.0, // weight for guided attention loss. If > 0, guided attention is enabled.
|
||||
|
||||
// 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": false, // 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": 0.0001, // 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.
|
||||
|
||||
// TACOTRON PRENET
|
||||
"memory_size": -1, // ONLY TACOTRON - size of the memory queue used fro storing last decoder predictions for auto-regression. If < 0, memory queue is disabled and decoder only uses the last prediction frame.
|
||||
"prenet_type": "bn", // "original" or "bn".
|
||||
"prenet_dropout": false, // enable/disable dropout at prenet.
|
||||
|
||||
// TACOTRON ATTENTION
|
||||
"attention_type": "original", // 'original' or 'graves'
|
||||
"attention_heads": 4, // number of attention heads (only for 'graves')
|
||||
"attention_norm": "sigmoid", // softmax or sigmoid.
|
||||
"windowing": false, // Enables attention windowing. Used only in eval mode.
|
||||
"use_forward_attn": false, // if it uses forward attention. In general, it aligns faster.
|
||||
"forward_attn_mask": false, // Additional masking forcing monotonicity only in eval mode.
|
||||
"transition_agent": false, // enable/disable transition agent of forward attention.
|
||||
"location_attn": true, // enable_disable location sensitive attention. It is enabled for TACOTRON by default.
|
||||
"bidirectional_decoder": false, // use https://arxiv.org/abs/1907.09006. Use it, if attention does not work well with your dataset.
|
||||
"double_decoder_consistency": true, // use DDC explained here https://erogol.com/solving-attention-problems-of-tts-models-with-double-decoder-consistency-draft/
|
||||
"ddc_r": 7, // reduction rate for coarse decoder.
|
||||
|
||||
// STOPNET
|
||||
"stopnet": true, // Train stopnet predicting the end of synthesis.
|
||||
"separate_stopnet": true, // Train stopnet seperately if 'stopnet==true'. It prevents stopnet loss to influence the rest of the model. It causes a better model, but it trains SLOWER.
|
||||
|
||||
// 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": 10000, // Number of training steps expected to save traninpg stats and checkpoints.
|
||||
"checkpoint": true, // If true, it saves checkpoints per "save_step"
|
||||
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
|
||||
|
||||
// DATA LOADING
|
||||
"text_cleaner": "phoneme_cleaners",
|
||||
"enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars.
|
||||
"num_loader_workers": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values.
|
||||
"num_val_loader_workers": 4, // number of evaluation data loader processes.
|
||||
"batch_group_size": 0, //Number of batches to shuffle after bucketing.
|
||||
"min_seq_len": 6, // DATASET-RELATED: minimum text length to use in training
|
||||
"max_seq_len": 153, // DATASET-RELATED: maximum text length
|
||||
|
||||
// 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": true, // 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_speaker_embedding": false, // use speaker embedding to enable multi-speaker learning.
|
||||
"style_wav_for_test": null, // path to style wav file to be used in TacotronGST inference.
|
||||
"use_gst": false, // TACOTRON ONLY: use global style tokens
|
||||
|
||||
// DATASETS
|
||||
"train_portion": 0.1, // dataset portion used for training. It is mainly for internal experiments.
|
||||
"eval_portion": 0.1, // dataset portion used for training. It is mainly for internal experiments.
|
||||
"datasets": // List of datasets. They all merged and they get different speaker_ids.
|
||||
[
|
||||
{
|
||||
"name": "ljspeech",
|
||||
"path": "tests/data/ljspeech/",
|
||||
"meta_file_train": "metadata.csv",
|
||||
"meta_file_val": "metadata.csv"
|
||||
}
|
||||
]
|
||||
|
||||
}
|
||||
|
||||
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"audio":{
|
||||
"num_mels": 80, // size of the mel spec frame.
|
||||
"num_freq": 513, // 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
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,144 @@
|
||||
{
|
||||
"run_name": "multiband-melgan",
|
||||
"run_description": "multiband melgan mean-var scaling",
|
||||
|
||||
// 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.
|
||||
|
||||
// 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": 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
|
||||
},
|
||||
|
||||
// DISTRIBUTED TRAINING
|
||||
// "distributed":{
|
||||
// "backend": "nccl",
|
||||
// "url": "tcp:\/\/localhost:54321"
|
||||
// },
|
||||
|
||||
// MODEL PARAMETERS
|
||||
"use_pqmf": true,
|
||||
|
||||
// LOSS PARAMETERS
|
||||
"use_stft_loss": true,
|
||||
"use_subband_stft_loss": true,
|
||||
"use_mse_gan_loss": true,
|
||||
"use_hinge_gan_loss": false,
|
||||
"use_feat_match_loss": false, // use only with melgan discriminators
|
||||
|
||||
// loss weights
|
||||
"stft_loss_weight": 0.5,
|
||||
"subband_stft_loss_weight": 0.5,
|
||||
"mse_G_loss_weight": 2.5,
|
||||
"hinge_G_loss_weight": 2.5,
|
||||
"feat_match_loss_weight": 25,
|
||||
|
||||
// multiscale stft loss parameters
|
||||
"stft_loss_params": {
|
||||
"n_ffts": [1024, 2048, 512],
|
||||
"hop_lengths": [120, 240, 50],
|
||||
"win_lengths": [600, 1200, 240]
|
||||
},
|
||||
|
||||
// subband multiscale stft loss parameters
|
||||
"subband_stft_loss_params":{
|
||||
"n_ffts": [384, 683, 171],
|
||||
"hop_lengths": [30, 60, 10],
|
||||
"win_lengths": [150, 300, 60]
|
||||
},
|
||||
|
||||
"target_loss": "avg_G_loss", // loss value to pick the best model to save after each epoch
|
||||
|
||||
// DISCRIMINATOR
|
||||
"discriminator_model": "melgan_multiscale_discriminator",
|
||||
"discriminator_model_params":{
|
||||
"base_channels": 16,
|
||||
"max_channels":512,
|
||||
"downsample_factors":[4, 4, 4]
|
||||
},
|
||||
"steps_to_start_discriminator": 200000, // steps required to start GAN trainining.1
|
||||
|
||||
// GENERATOR
|
||||
"generator_model": "multiband_melgan_generator",
|
||||
"generator_model_params": {
|
||||
"upsample_factors":[8, 4, 2],
|
||||
"num_res_blocks": 4
|
||||
},
|
||||
|
||||
// DATASET
|
||||
"data_path": "tests/data/ljspeech/wavs/",
|
||||
"feature_path": null,
|
||||
"seq_len": 16384,
|
||||
"pad_short": 2000,
|
||||
"conv_pad": 0,
|
||||
"use_noise_augment": false,
|
||||
"use_cache": true,
|
||||
|
||||
"reinit_layers": [], // give a list of layer names to restore from the given checkpoint. If not defined, it reloads all heuristically matching layers.
|
||||
|
||||
// TRAINING
|
||||
"batch_size": 4, // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
|
||||
|
||||
// VALIDATION
|
||||
"run_eval": true,
|
||||
"test_delay_epochs": 10, //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
|
||||
"epochs": 1, // total number of epochs to train.
|
||||
"wd": 0.0, // Weight decay weight.
|
||||
"gen_clip_grad": -1, // Generator gradient clipping threshold. Apply gradient clipping if > 0
|
||||
"disc_clip_grad": -1, // Discriminator gradient clipping threshold.
|
||||
"lr_scheduler_gen": "MultiStepLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_gen_params": {
|
||||
"gamma": 0.5,
|
||||
"milestones": [100000, 200000, 300000, 400000, 500000, 600000]
|
||||
},
|
||||
"lr_scheduler_disc": "MultiStepLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_disc_params": {
|
||||
"gamma": 0.5,
|
||||
"milestones": [100000, 200000, 300000, 400000, 500000, 600000]
|
||||
},
|
||||
"lr_gen": 1e-4, // Initial learning rate. If Noam decay is active, maximum learning rate.
|
||||
"lr_disc": 1e-4,
|
||||
|
||||
// TENSORBOARD and LOGGING
|
||||
"print_step": 1, // Number of steps to log traning on console.
|
||||
"print_eval": false, // If True, it prints loss values for each step in eval run.
|
||||
"save_step": 25000, // Number of training steps expected to plot training stats on TB and save model checkpoints.
|
||||
"checkpoint": true, // If true, it saves checkpoints per "save_step"
|
||||
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
|
||||
|
||||
// DATA LOADING
|
||||
"num_loader_workers": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values.
|
||||
"num_val_loader_workers": 4, // number of evaluation data loader processes.
|
||||
"eval_split_size": 10,
|
||||
|
||||
// PATHS
|
||||
"output_path": "tests/outputs/train_outputs/"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user