From fa206380839c488bcad0c4552ac6a9f0c58a2fe8 Mon Sep 17 00:00:00 2001 From: erogol Date: Sat, 12 Dec 2020 20:15:56 +0100 Subject: [PATCH] config for ljspeech dynamic conv attention --- .../ljspeech_tacotron2_dynamic_conv_attn.json | 171 ++++++++++++++++++ 1 file changed, 171 insertions(+) create mode 100644 TTS/tts/configs/ljspeech_tacotron2_dynamic_conv_attn.json diff --git a/TTS/tts/configs/ljspeech_tacotron2_dynamic_conv_attn.json b/TTS/tts/configs/ljspeech_tacotron2_dynamic_conv_attn.json new file mode 100644 index 00000000..40f1ac86 --- /dev/null +++ b/TTS/tts/configs/ljspeech_tacotron2_dynamic_conv_attn.json @@ -0,0 +1,171 @@ +{ + "model": "Tacotron2", + "run_name": "ljspeech-dcattn", + "run_description": "tacotron2 with dynamic convolution attention.", + + // 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": "/home/erogol/Data/LJSpeech-1.1/scale_stats.npy" // 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": 2, // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'. + "eval_batch_size":16, + "r": 7, // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled. + "gradual_training": [[0, 7, 64], [1, 5, 64], [50000, 3, 32], [130000, 2, 32], [290000, 1, 32]], //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. + "mixed_precision": true, // level of optimization with NVIDIA's apex feature for automatic mixed FP16/FP32 precision (AMP), NOTE: currently only O1 is supported, and use "O1" to activate. + + // LOSS SETTINGS + "loss_masking": true, // enable / disable loss masking against the sequence padding. + "decoder_loss_alpha": 0.5, // original decoder loss weight. If > 0, it is enabled + "postnet_loss_alpha": 0.25, // original postnet loss weight. If > 0, it is enabled + "postnet_diff_spec_alpha": 0.25, // differential spectral loss weight. If > 0, it is enabled + "decoder_diff_spec_alpha": 0.25, // differential spectral loss weight. If > 0, it is enabled + "decoder_ssim_alpha": 0.5, // decoder ssim loss weight. If > 0, it is enabled + "postnet_ssim_alpha": 0.25, // postnet ssim loss weight. If > 0, it is enabled + "ga_alpha": 5.0, // weight for guided attention loss. If > 0, guided attention is enabled. + "stopnet_pos_weight": 15.0, // pos class weight for stopnet loss since there are way more negative samples than positive samples. + + + // 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 + "noam_schedule": false, // use noam warmup and lr schedule. + "grad_clip": 1.0, // upper limit for gradients for clipping. + "epochs": 1000, // 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": "original", // "original" or "bn". + "prenet_dropout": false, // enable/disable dropout at prenet. + + // TACOTRON ATTENTION + "attention_type": "dynamic_convolution", // 'original' , 'graves', 'dynamic_convolution' + "attention_heads": 4, // number of attention heads (only for 'graves') + "attention_norm": "softmax", // 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": 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": 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": 4, //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 + "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": "/home/erogol/Models/LJSpeech/", + + // PHONEMES + "phoneme_cache_path": "/home/erogol/Models/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. + "use_gst": false, // use global style tokens + "use_external_speaker_embedding_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 + "external_speaker_embedding_file": "../../speakers-vctk-en.json", // if not null and use_external_speaker_embedding_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 + "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_embedding_dim": 512, + "gst_num_heads": 4, + "gst_style_tokens": 10, + "gst_use_speaker_embedding": false + }, + + // DATASETS + "datasets": // List of datasets. They all merged and they get different speaker_ids. + [ + { + "name": "ljspeech", + "path": "/home/erogol/Data/LJSpeech-1.1/", + "meta_file_train": "metadata.csv", // for vtck if list, ignore speakers id in list for train, its useful for test cloning with new speakers + "meta_file_val": null + } + ] +} +